Apr13

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

UK: Managing Editor International Journal of Innovative Technology and Creative Engineering 1a park lane, Cranford London TW59WA UK E-Mail: editor@ijitce.co.uk Phone: +44-773-043-0249 USA: Editor International Journal of Innovative Technology and Creative Engineering Dr. Arumugam Department of Chemistry University of Georgia GA-30602, USA. Phone: 001-706-206-0812 Fax:001-706-542-2626 India: Editor International Journal of Innovative Technology & Creative Engineering Dr. Arthanariee. A. M Finance Tracking Center India 17/14 Ganapathy Nagar 2nd Street Ekkattuthangal Chennai -600032 Mobile: 91-7598208700

www.ijitce.co.uk

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

IJITCE PUBLICATION

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY & CREATIVE ENGINEERING Vol.3 No.4 April 2013

www.ijitce.co.uk

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

From Editor's Desk Dear Researcher, Greetings!

Research article in this issue discusses about Categorization of Brain Tumour, Labial Teeth structure for human identity.

Let us review research around the world this month; Voice-based web access helps illiterate get online. A new voice-based web system could help, making it easier for illiterate people in Mali and other West African nations to use the internet. The project, sponsored by the European Commission, is called Voices and it has already been used to build an information system for farmers and as a platform for citizen journalism. The system is based on a programming language called VoiceXML, which lets users vocally control specially created web content. Malians can navigate by listening to options and pressing buttons on their phone.

MIND reading can be as simple as slapping a sticker on your forehead. An "electronic tattoo" containing flexible electronic circuits can now record some complex brain activity as accurately as an EEG. The tattoo could also provide a cheap way to monitor a developing fetus. The team is now modifying the tattoo to transmit data wirelessly to a Smartphone.

International Space Station to get 787-style batteries. NASA is pressing ahead with a plan to install lithium-ion batteries on the International Space Station (ISS). The batteries are similar to those used on Boeing's 787 Dreamliner aircraft, all 50 of which have been taken out of commercial service worldwide since January following battery fires on two planes. NASA says that lithium-ion cells offer compelling benefits, and it is confident that any safety issues can be overcome. NASA is going ahead because, it says, "proper design" of the battery packs will let it take advantage of the lightness and extra power delivered by lithium-ion technology – which is easily better than the current nickel metal-hydride batteries used on the ISS. It has been an absolute pleasure to present you articles that you wish to read. We look forward to many more new technologies related research articles from you and your friends. We are anxiously awaiting the rich and thorough research papers that have been prepared by our authors for the next issue.

Thanks, Editorial Team IJITCE

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

Editorial Members Dr. Chee Kyun Ng Ph.D Department of Computer and Communication Systems, Faculty of Engineering, Universiti Putra Malaysia,UPM Serdang, 43400 Selangor,Malaysia.

Dr. Simon SEE Ph.D Chief Technologist and Technical Director at Oracle Corporation, Associate Professor (Adjunct) at Nanyang Technological University Professor (Adjunct) at Shangai Jiaotong University, 27 West Coast Rise #08-12,Singapore 127470 Dr. sc.agr. Horst Juergen SCHWARTZ Ph.D, Humboldt-University of Berlin, Faculty of Agriculture and Horticulture, Asternplatz 2a, D-12203 Berlin, Germany Dr. Marco L. Bianchini Ph.D Italian National Research Council; IBAF-CNR, Via Salaria km 29.300, 00015 Monterotondo Scalo (RM), Italy Dr. Nijad Kabbara Ph.D Marine Research Centre / Remote Sensing Centre/ National Council for Scientific Research, P. O. Box: 189 Jounieh, Lebanon Dr. Aaron Solomon Ph.D Department of Computer Science, National Chi Nan University, No. 303, University Road, Puli Town, Nantou County 54561, Taiwan Dr. Arthanariee. A. M M.Sc.,M.Phil.,M.S.,Ph.D Director - Bharathidasan School of Computer Applications, Ellispettai, Erode, Tamil Nadu,India Dr. Takaharu KAMEOKA, Ph.D Professor, Laboratory of Food, Environmental & Cultural Informatics Division of Sustainable Resource Sciences, Graduate School of Bioresources, Mie University, 1577 Kurimamachiya-cho, Tsu, Mie, 514-8507, Japan Mr. M. Sivakumar M.C.A.,ITIL.,PRINCE2.,ISTQB.,OCP.,ICP Project Manager - Software, Applied Materials, 1a park lane, cranford, UK Dr. Bulent Acma Ph.D Anadolu University, Department of Economics, Unit of Southeastern Anatolia Project(GAP), 26470 Eskisehir, TURKEY Dr. Selvanathan Arumugam Ph.D Research Scientist, Department of Chemistry, University of Georgia, GA-30602, USA.

Review Board Members Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic & Ceramic Materials,CSIRO Process Science & Engineering Private Bag 33, Clayton South MDC 3169,Gate 5 Normanby Rd., Clayton Vic. 3168, Australia Dr. Zhiming Yang MD., Ph. D. Department of Radiation Oncology and Molecular Radiation Science,1550 Orleans Street Rm 441, Baltimore MD, 21231,USA Dr. Jifeng Wang Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign Urbana, Illinois, 61801, USA Dr. Giuseppe Baldacchini ENEA - Frascati Research Center, Via Enrico Fermi 45 - P.O. Box 65,00044 Frascati, Roma, ITALY. Dr. Mutamed Turki Nayef Khatib Assistant Professor of Telecommunication Engineering,Head of Telecommunication Engineering Department,Palestine Technical University (Kadoorie), Tul Karm, PALESTINE. Dr.P.Uma Maheswari Prof & Head,Depaartment of CSE/IT, INFO Institute of Engineering,Coimbatore.

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Dr. T. Christopher, Ph.D., Assistant Professor & Head,Department of Computer Science,Government Arts College(Autonomous),Udumalpet, India.

Dr. T. DEVI Ph.D. Engg. (Warwick, UK), Head,Department of Computer Applications,Bharathiar University,Coimbatore-641 046, India.

Dr. Renato J. orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business School,Rua Itapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Visiting Scholar at INSEAD,INSEAD Social Innovation Centre,Boulevard de Constance,77305 Fontainebleau - France Y. Benal Yurtlu Assist. Prof. Ondokuz Mayis University Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. Chutima Boonthum-Denecke, Ph.D Department of Computer Science,Science & Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business SchoolRua Itapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Dr. Lucy M. Brown, Ph.D. Texas State University,601 University Drive,School of Journalism and Mass Communication,OM330B,San Marcos, TX 78666 Javad Robati Crop Production Departement,University of Maragheh,Golshahr,Maragheh,Iran Vinesh Sukumar (PhD, MBA) Product Engineering Segment Manager, Imaging Products, Aptina Imaging Inc. Dr. Binod Kumar PhD(CS), M.Phil.(CS), MIAENG,MIEEE HOD & Associate Professor, IT Dept, Medi-Caps Inst. of Science & Tech.(MIST),Indore, India Dr. S. B. Warkad Associate Professor, Department of Electrical Engineering, Priyadarshini College of Engineering, Nagpur, India Dr. doc. Ing. Rostislav Choteborský, Ph.D. Katedra materiálu a strojírenské technologie Technická fakulta,Ceská zemedelská univerzita v Praze,Kamýcká 129, Praha 6, 165 21 Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic & Ceramic Materials,CSIRO Process Science & Engineering Private Bag 33, Clayton South MDC 3169,Gate 5 Normanby Rd., Clayton Vic. 3168 DR.Chutima Boonthum-Denecke, Ph.D Department of Computer Science,Science & Technology Bldg.,Hampton University,Hampton, VA 23688 Mr. Abhishek Taneja B.sc(Electronics),M.B.E,M.C.A.,M.Phil., Assistant Professor in the Department of Computer Science & Applications, at Dronacharya Institute of Management and Technology, Kurukshetra. (India).

Dr. Ing. Rostislav Chotěborský,ph.d, Katedra materiálu a strojírenské technologie, Technická fakulta,Česká zemědělská univerzita v Praze,Kamýcká 129, Praha 6, 165 21

Dr. Amala VijayaSelvi Rajan, B.sc,Ph.d, Faculty – Information Technology Dubai Women’s College – Higher Colleges of Technology,P.O. Box – 16062, Dubai, UAE

Naik Nitin Ashokrao B.sc,M.Sc Lecturer in Yeshwant Mahavidyalaya Nanded University

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Dr.A.Kathirvell, B.E, M.E, Ph.D,MISTE, MIACSIT, MENGG Professor - Department of Computer Science and Engineering,Tagore Engineering College, Chennai Dr. H. S. Fadewar B.sc,M.sc,M.Phil.,ph.d,PGDBM,B.Ed. Associate Professor - Sinhgad Institute of Management & Computer Application, Mumbai-Banglore Westernly Express Way Narhe, Pune - 41 Dr. David Batten Leader, Algal Pre-Feasibility Study,Transport Technologies and Sustainable Fuels,CSIRO Energy Transformed Flagship Private Bag 1,Aspendale, Vic. 3195,AUSTRALIA Dr R C Panda (MTech & PhD(IITM);Ex-Faculty (Curtin Univ Tech, Perth, Australia))Scientist CLRI (CSIR), Adyar, Chennai - 600 020,India Miss Jing He PH.D. Candidate of Georgia State University,1450 Willow Lake Dr. NE,Atlanta, GA, 30329 Jeremiah Neubert Assistant Professor,Mechanical Engineering,University of North Dakota Hui Shen Mechanical Engineering Dept,Ohio Northern Univ.

Dr. Xiangfa Wu, Ph.D. Assistant Professor / Mechanical Engineering,NORTH DAKOTA STATE UNIVERSITY Seraphin Chally Abou Professor,Mechanical & Industrial Engineering Depart,MEHS Program, 235 Voss-Kovach Hall,1305 Ordean Court,Duluth, Minnesota 55812-3042 Dr. Qiang Cheng, Ph.D. Assistant Professor,Computer Science Department Southern Illinois University CarbondaleFaner Hall, Room 2140-Mail Code 45111000 Faner Drive, Carbondale, IL 62901 Dr. Carlos Barrios, PhD Assistant Professor of Architecture,School of Architecture and Planning,The Catholic University of America Y. Benal Yurtlu Assist. Prof. Ondokuz Mayis University Dr. Lucy M. Brown, Ph.D. Texas State University,601 University Drive,School of Journalism and Mass Communication,OM330B,San Marcos, TX 78666 Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic & Ceramic Materials CSIRO Process Science & Engineering Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. Chutima Boonthum-Denecke, Ph.D Department of Computer Science,Science & Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,S찾o Paulo Business School,Rua Itapeva, 474 (8째 andar)01332-000, S찾o Paulo (SP), Brazil Dr. Wael M. G. Ibrahim Department Head-Electronics Engineering Technology Dept.School of Engineering Technology ECPI College of Technology 5501 Greenwich Road - Suite 100,Virginia Beach, VA 23462

Dr. Messaoud Jake Bahoura Associate Professor-Engineering Department and Center for Materials Research Norfolk State University,700 Park avenue,Norfolk, VA 23504

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Dr. V. P. Eswaramurthy M.C.A., M.Phil., Ph.D., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 007, India.

Dr. P. Kamakkannan,M.C.A., Ph.D ., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 007, India.

Dr. V. Karthikeyani Ph.D., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 008, India.

Dr. K. Thangadurai Ph.D., Assistant Professor, Department of Computer Science, Government Arts College ( Autonomous ), Karur - 639 005,India.

Dr. N. Maheswari Ph.D., Assistant Professor, Department of MCA, Faculty of Engineering and Technology, SRM University, Kattangulathur, Kanchipiram Dt - 603 203, India.

Mr. Md. Musfique Anwar B.Sc(Engg.)

Lecturer, Computer Science & Engineering Department, Jahangirnagar University, Savar, Dhaka, Bangladesh.

Mrs. Smitha Ramachandran M.Sc(CS)., SAP Analyst, Akzonobel, Slough, United Kingdom.

Dr. V. Vallimayil Ph.D., Director, Department of MCA, Vivekanandha Business School For Women, Elayampalayam, Tiruchengode - 637 205, India.

Mr. M. Moorthi M.C.A., M.Phil., Assistant Professor, Department of computer Applications, Kongu Arts and Science College, India Prema Selvaraj Bsc,M.C.A,M.Phil Assistant Professor,Department of Computer Science,KSR College of Arts and Science, Tiruchengode Mr. G. Rajendran M.C.A., M.Phil., N.E.T., PGDBM., PGDBF., Assistant Professor, Department of Computer Science, Government Arts College, Salem, India.

Dr. Pradeep H Pendse B.E.,M.M.S.,Ph.d Dean - IT,Welingkar Institute of Management Development and Research, Mumbai, India Muhammad Javed Centre for Next Generation Localisation, School of Computing, Dublin City University, Dublin 9, Ireland Dr. G. GOBI Assistant Professor-Department of Physics,Government Arts College,Salem - 636 007 Dr.S.Senthilkumar Post Doctoral Research Fellow, (Mathematics and Computer Science & Applications),Universiti Sains Malaysia,School of Mathematical Sciences, Pulau Pinang-11800,[PENANG],MALAYSIA. Manoj Sharma Associate Professor Deptt. of ECE, Prannath Parnami Institute of Management & Technology, Hissar, Haryana, India RAMKUMAR JAGANATHAN Asst-Professor,Dept of Computer Science, V.L.B Janakiammal college of Arts & Science, Coimbatore,Tamilnadu, India Dr. S. B. Warkad Assoc. Professor, Priyadarshini College of Engineering, Nagpur, Maharashtra State, India Dr. Saurabh Pal Associate Professor, UNS Institute of Engg. & Tech., VBS Purvanchal University, Jaunpur, India Manimala Assistant Professor, Department of Applied Electronics and Instrumentation, St Joseph’s College of Engineering & Technology, Choondacherry Post, Kottayam Dt. Kerala -686579

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Dr. Qazi S. M. Zia-ul-Haque Control Engineer Synchrotron-light for Experimental Sciences and Applications in the Middle East (SESAME),P. O. Box 7, Allan 19252, Jordan Dr. A. Subramani, M.C.A.,M.Phil.,Ph.D. Professor,Department of Computer Applications, K.S.R. College of Engineering, Tiruchengode - 637215 Dr. Seraphin Chally Abou Professor, Mechanical & Industrial Engineering Depart. MEHS Program, 235 Voss-Kovach Hall, 1305 Ordean Court Duluth, Minnesota 558123042 Dr. K. Kousalya Professor, Department of CSE,Kongu Engineering College,Perundurai-638 052 Dr. (Mrs.) R. Uma Rani Asso.Prof., Department of Computer Science, Sri Sarada College For Women, Salem-16, Tamil Nadu, India.

MOHAMMAD YAZDANI-ASRAMI Electrical and Computer Engineering Department, Babol "Noshirvani" University of Technology, Iran.

Dr. Kulasekharan, N, Ph.D Technical Lead - CFD,GE Appliances and Lighting, GE India,John F Welch Technology Center, Plot # 122, EPIP, Phase 2,Whitefield Road,Bangalore – 560066, India.

Dr. Manjeet Bansal Dean (Post Graduate),Department of Civil Engineering ,Punjab Technical University,Giani Zail Singh Campus, Bathinda -151001 (Punjab),INDIA Dr. Oliver Jukić Vice Dean for education, Virovitica College, Matije Gupca 78,33000 Virovitica, Croatia Dr. Lori A. Wolff, Ph.D., J.D. Professor of Leadership and Counselor Education, The University of Mississippi, Department of Leadership and Counselor Education, 139 Guyton University, MS 38677

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

Contents The Prophecision and Categorization of Brain Tumour using Artificial Neural Network by Mr.D.Arun Nehru, Ms.D.Rubini 4......................................................................................................................................................[51] Labial Teeth structure for human identity by Sivakumar M, Arthanari. M .......................................................[57]

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

The Prophecision and Categorization of Brain Tumour using Artificial Neural Network Mr.D.Arun Nehru1 ,Ms.D.Rubini2 1M.E (control and instrumentation) PG Scholar, Department of Electrical and Electronics Engineering, Anna University of technology, Coimbatore. darunnehru@gmail.com 2B.E (Computer Science Engineering) UG Scholar, Department of Computer Science Engineering, kalaignar karunanidhi institute of technology,Coimbatore. rubycoolbuddy@gmail.com

Abstract - The method of human analysis on medical images is the difficult task. This is mainly due to very minute variations and the co-resemblance between affected & original biological part and it also requires a larger data set for analysis. This makes the biological analysis for prediction a tedious one. This problem grows complicated under the prediction of cancer basically in brain. The challenging task is to develop an automated recognition system which could process on a large information of patient and provide a correct estimation of the results. This project deals with an automated cancer recognition system for MRI images. We implement the neural network algorithm on the given MRI image for the classification and estimation of affected regions.

Mostly ANNs are the Adaptive system, but the modern uses the non-statistical data modeling tools.

These are being organized by different architectural modeling tools. Applications include the system identification, game playing, decision making, medical recognition and data mining.

Image processing is one of the signal processing for which the input is an image. This involves the image as the two dimensional view. The most active area of research in such diverse fields as medicine, astronomy, microscopy, seismology, defense, industrial quality control, and the publication and entertainment industries is the Image processing. One of the biggest advantages is that the ability of the operator to post process the image. This also allows the electronic transmission of Keywords - Co-resemblance, MRI images, Neural the signals.

Network, Biological analysis, Backpropogation.

II. BRAIN TUMOUR I.

INTRODUCTION

Brain tumours are usually defined as the group of similar cells that do no follow normal cell division and growth patterns. This can be both cancerous and noncancerous (benign). Tumours are found by CT or MRI brain scans. In general the benign tumours do not reoccur after the removal. Some of the causes are Radiation Exposure or the Exposure to the Chemicals.

The symptoms of the brain tumour can vary based on the onset of the disease. Some of the symptoms include weakness, difficulty in walking, seizures, blurry vision.

An Artificial Neural Network (ANN) is the computational model inspired by its functions and the aspects of the biological analysis. This is also called as the Simulated Neural Network (SNN) or commonly just neural network (NN). This commonly consists of interconnected group of artificial neurons. This is used as a mathematical or computational model for processing the information based on a connectionist approach to computation models. A technique in which the data from an image are digitized and various mathematical Primary and secondary brain tumours are the operations are applied ANNs are being defined by 3 types of the brain tumours. Primary brain tumours arise parameters namely from the brain or the spinal cord. Primary tumours can be Malignant and they rarely spread beyond the central nervous system. This is increased partly due to the fact • Interconnection Patterns. that people now have higher life expectancy and we are • Weights of the Interconnections. much more skilled. The causes are the Environmental • Activation Functions.

51

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Exposures and the role of Genetic development. The symptoms vary based on the location of the tumour and V. EVALUATION MODELS the size.

The given query sample are evaluated by using Secondary brain tumours are often called the following models. This is used both for database Metastatic tumours, are the result of cancer cells images and the query images. originating from another part of the body that have spread to the brain. These tumours are more common A. Histogram equalization than the primary tumours. In rare case is that Metastatic brain tumour is discovered before the originating cancer Histogram is the Graphical representation site is being detected. showing the visual impression of the distributed data.

This is one of the methods in image processing. This is Both the tumours are life threatening and are the contrast adjustments using the images. Histogram usually very aggressive. The early detection of a brain equalization accomplishes the effective spreading of the tumour only occurs when diagnostic tools are directed at most frequent intensity values. This method is useful for the intracranial cavity. Usually detection occurs in either the images with foreground and background which advanced stages when the presence of the tumour has are being both bright or both dark. This produces the caused unexplained symptoms. Many diagnostic tools unrealistic effects and also the undesirable effects like are being discovered for the detection of these tumours. image gradient. Applied to the images like thermal, satellites or the X-ray images.

III. MRI IMAGE This is also used in the Biological neural network Magnetic resonance imaging (MRI), nuclear to maximize the output firing rate of the neuron as the magnetic resonance imaging (NMRI), or magnetic function of input. This method seeks to adjust the resonance tomography (MRT) is a medical imaging images to make it easier to analyze or improve visual technique used in radiology to visualize detailed internal quality structures. MRI makes use of the property of nuclear The important operations are based upon the magnetic resonance (NMR) to image nuclei of atoms manipulation of an Image histogram or a Region inside the body. histogram. The most important Histogram based operations are given below MRI provides good contrast between the different soft tissues of the body, which makes it • Contrast Stretching. especially useful in imaging the brain, muscles, the • Equalization. heart, and cancers compared with other medical imaging The histogram equalization has three steps techniques such as computed tomography (CT) or X- when it is being applied on an image rays.

• Histogram Formation.

• New Intensity Values calculation for each IV. PROPOSED SYSTEM Intensity Levels.

• Replace the previous Intensity values with the new intensity values.

B. Binarization

Fig.1 Block diagram of proposed method.

Binary image is the digital image that has two possible values for each pixel used namely Black and White. Binarization is the process of converting the image of 256 pixels to the image of black and white.

Some of the operations performed are Segmentation, Thresholding and Dithering. The simplest way to use image Binarization is to choose a threshold value.

52

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Binarization is recognized to be one of the most D. Region Extraction important steps in high-level image analysis systems.

This is being proposed particularly for Medical image The area which is obtained by Region Growing data. The following are the steps followed in Binarization method is considered as a new base image in the next step, and this extraction process is repeated for all slice • Extract the affected or the accumulated regions images. Finally, we extracted the area of tumour and brain, and both are visualized in three-dimensional and choose threshold value.

• Next the Thresholding method used for the domain simultaneously to understand the position relations of the tumour. To filled image, centroids are binarized image. calculated to localize the regions as shown beside. The Binarized image b(i,j)= 255 final extracted region is then logically operated for { extraction of Massive region in given MRI image. if e (i, j) > T else b (i, j) = 0 E. Feature Extraction } (i) Where e (i, j) is the equalized MRI image and T This is the special form of the dimensionality is threshold derived for the equalized image. reduction.

Transforming the input data into the set of • A masking matrix is derived by using a features is called as the feature Extraction. This can be neighbourhood estimation method. applied for the extracted region with 5 invariant features.

M is the masking matrix derived using • F1 Area neighbourhood estimation method, The quality that expresses the extent of the Let e = p1 p2 p3 region. p4 p5 p6 p7 p8 p9 • F2 Homogeneity (Inverse Difference Moment) Let e be the equalized image matrix. Then the This is defined as the state of being similar masking element extent.

M (p5) = max (| p4 – p6 |, |p2 – p8 |) (ii) N-1 F2 = ∑ (Pi,j) / (i – (i*j)2) (v) C. Morphological Operations i,j=0 • F3 Contrast The word morphology commonly denotes a branch of biology that deals with the form and structure of Contrast is the difference in luminance that animals and plants. This is usually being for identifying makes an object representation. of the object boundaries. This morphological operation N-1 used for image filtering, thinning, and fill the gaps of the F3 = ∑ Pi, j (i-j) 2 (vi) image. Operations are being applied on the 3x3 pixel i,j=0 neighbours. Pixel of interest lies at the center • F4 Angular Second Moment (ASM) represented as X and surroundings are represented by This is also called as uniformity. Each p(i,j) is X0 to X7. The following are some of the important used as a weight for itself. operations used for the MRI image detection of the N-1 tumour Pi,j F4 = ∑ (vii) i,j=0 1)Erosion: • F5 Entropy Erosion eliminates the unwanted white noise This is the property that can be used to pixels from black area. The pixel in the determine the energy that is not available. neighbourhood should be 1.

E (A, B) = AΘ (-B) ∩ (A-β) (iii) N-1 Uses AND operations for the functions.

F5 = ∑ Pi,j (i-j) 2 (viii) 2) Dilation: i,j=0 Dilation makes the white area grow or dilate.

This is useful for removing the isolated black pixels from The above functions are being applied on a an image. clustered database consisting of different distinct MRI D (A, B) =AΘ U (A+β) (iv) images. The database is divided into Low grade and the Uses NAND operation for the functions.

High grade classes.

53

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 F. Low Grade Classes These are slow growing with relatively well defined borders. These are assigned to I and II. 1) Class I – Gliomas: Composes the supportive tissue of the brain.

Fig.5 Glioblastoma Multiforme

VI ALGORITHM USED The algorithm used for the processing is the Back Propagation. One of the feed forward mechanisms such that training patterns are the input through the neural Fig.2 Gliomas Class network in order to generate the output propagations.

This is a multilayer feed forward network with one layer 2) Class II – Astrocytoma: of Z-hidden units. This usually allows for the quick Abnormal growth of tissue which usually spread convergence. Bias acts as a connection from units outside the brain and the spinal cord. whose output is always 1. back prorogation occurs actively in the spinal cord while in cerebellum it occurs passively.

Back propagation training takes place in three stages.

• Initialization of the weights.

Some random values are being assigned for the calculation.

• Feed forward mechanism.

Fig.3 Astrocytoma Each hidden units are calculated for the activation function to form the response of the G.High Grade Classes given output • Back propagation of the associated error.

Grows much quickly and are being assigned to III The output is being compared with the and IV. target value for the determination of the error.

• Updating of weights and biases.

1) Class III – Anaplastic Astrocytoma: Most high grade and occurs sporadically and The weighted and the bias corrections are used for the invades the neighbouring tissues. minimization of the errors.

During feed forward, each input neuron receives an input signal and broadcasts it to each hidden neuron.

During training, the net output is compared with the target value and the appropriate error is calculated. The following are some of the merits of these algorithms • Fig.4 Anaplastic Astrocytoma • 2) Class IV – Glioblastoma Multiforme: Most aggressive malignant brain tumour that has the worst prognosis of CNS.

•

54

Relatively simple implementation, standard method and relatively works well.

The mathematical formula used can be applied to any network.

Computing time is reduced if the weights choosen are small at the beginning.

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 VII RESULTS

Fig.9 Filled image

Fig.6 Input MRI image for processing.

Fig.10 Segmented Tumour Fig.7 Histogram Equalization

Fig.11 Classified Tumor Classes Fig.8 Binarization.

55

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 VIII. CONCLUSION This project, the image processing part has been successfully done with the use of MRI image. The features of image processing , Histogram equalization gives the better result for image intensity , Binarization has been classify the black and white operation , morphological operation has been used to contract or expand the image , with the use of feature extraction the area , contrast , angular second moment , entropy were predicted. This image processing part exposed the exact position of the brain tumour. This technique gives the accurate result of the brain tumour. This is used to classify the different type of brain tumours present in human. With the help of Back propagation technique from which neural network has been trained and the brain tumour has been segmented.

REFERENCES [1] Mrs.Mamata S.Kalas, @ (2010), International journal of Computer Applications, Kolhapur, Maharashtra.

[2] Tinku Acharya and Ajoy K.Ray (2006), Image processing- Principles and Applications, Wiley interscience, ISBN. [3] Primary Brain Tumours in the United States Statistical Report 2002-2003, Central Brain Tumour Registry of the United States (CBTRUS).

[4] Bob Cromwell, “Localized Contrast Enhancements: Histogram Equalization”, New Jersey: Prentice Hall, 1991.

[5] Gonzalez, R.C. Richard, E.W. (2004), Digital Image Processing, II Indian Edition, Pearson Education, New Delhi, India. th [6] In Wang, h., Shen, y., Huang, t., Zeng, Z., 6 International Symposium on Neural Networks, ISNN 2009, Springer, Retrieved 2012-01-01.

[7] Hendee, James William R : Morgan, Christopher J(1984).”Magnetic Resonance Imaging”, West J med, 141 (4): 491-500, PMC 1021860 , PMID 6506686.

[8]A Dramatic Evolution in seeing & treating tumoursFeatured Article by Jonnie Rohrer from Visions, Fall/Winter 2004 [9] Stuart, Greg : Nelson Sprutsun, Bert Sackmann, Michael Hausser (1997). “Action potential and Back Propagation in neurons of CNS”. TINS 20(3) . retrieved 2010-12-23.

[10] University of Alberta Brain Tumor Growth Project: Automated Tumor Segmentation.

56

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

Labial Teeth structure for human identity 1

Sivakumar M , Arthanari M

2

1. Research Scholar,Anna University, Chennai, Tamil Nadu, India, sivala@gmail.com 2. Dean, Department of Science and Humanities,Nehru Institute of Technology,Kaliyapalayam, Coimbatore – 105, India, arthanarimsvc@gmail.com Abstract:

are practically used very rarely because of any insufficient data in the database.

In this paper, we have proposed a model of teeth recognition to identify a person. The teeth image of a person is matched against the teeth image database.

We have developed an algorithm to recognize the teeth using image processing techniques. The proposed work is an application of pattern recognition, which analyses the pattern of teeth images. A similarity criterion has been derived to match against the specified threshold value. This similarity measure has been used for person identification. The experiment results has been carried on 20 teeth images of the same person and 100 teeth images of different persons from our database and Labial Teeth Database of Color Imaging Lab - University of Granada – Spain. MATLAB 7.4 has been used for this purpose. The paper is described in different sections: section I introduces the proposed system of teeth recognition. In section II, we have proposed the model for teeth recognition, methodology and working of the proposed algorithm. We have analyzed the results in section III. Finally, section IV provides a conclusion.

As the digital imaging device and the computer recognition algorithm are improving quickly, more effort will be spent on digital image recognition to facilitate the biometrics and medical decision-making process. There are many theories and methods of pattern recognition that can be used for teeth image recognition [3]. This paper introduces a new approach to recognize the teeth of people. Teeth images have been used as templates and saved in the image database. The research on teeth recognition is based on the image processing techniques. Most biometric methods utilize a single image for person identification. These processes are complex and need sophisticated equipment and a controlled environment to be correctly used. It is almost impossible to fulfill these conditions to recognize the teeth [3] [8]. We have taken the RGB image of teeth of person.

The RGB image is converted into the gray-scale image.

The gray-scale image is converted into image of size 20 × 20 by applying the resize operation. We have recognized the pattern of teeth and converted the image into binary image by applying the threshold value [1]. The binary image has cropped into smaller size and number of one’s has been counted present in the pattern [4] [5]. Then, the teeth image is fetched from the image database and matched with the existing teeth image. We have derived the similarity criteria. If similarity measure between these two teeth images is more than the threshold value, the image belongs to the same person [2] [6] [7].

Key words: Dental identity, Forensic Dental Biometric, Dental Biometric, Segmentation, Matching, image processing.

I. INTRODUCTION During the Roman Empire period, killing of LoillaPaulina, was identified by her dental caries. Disaster occurred in Amoedo, Paris during 1897 French dental society used dental identification technique for identifying victims [10].

In forensic department, the police perform manual comparisons of ante-mortem (AM) and post-mortem (PM) dental records, for identifying a person during fire accidents or disasters because teeth and components of dental restorations have a very high melting point and is annealed only at high temperatures. A teeth filling retains its shape upto 600°C and the amalgam withstands up to 1100°C. A person’s dental pattern can be used as same degree of reliability as DNA; this report has been released by the University of Grandana because they used this method used by the forensic police to identify dead bodies [13]. All these methods

II. PROPOSED MODEL OF TEETH RECOGNITION In this proposed typical architecture consist of preprocessor, dental recording, processing of image, matrix generation, storing of processed data in to database, search data, retrieval, comparison of processed data, makes decision and trigger authorization. During preprocessing Meta data of all the remaining records about individuals like name, age, employee number, etc. are filled. During dental

57

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 recording, a high resolution camera needs to be the Color ImagingLab at the Optics Department of the attached with system to record face of the individual to University of Granadain Spain.The LTG-IDB currently capture. The distance between camera and human face contains more than 90 photographic digital still of teeth should be less than 50cm. There should be face chin images. Images in this database are available in raw holder to capture teeth image very clearly. System will image format (which is the unprocessed sensor data of give instruction on the posture for taking face image the camera in a specific vendor dependent data format, with teeth exposed. This image will be extracted and in this case the Canon raw image format cr2), as well as trimmed for only teeth portion. The segmentation of the JPEG and TIFF. The strengths of this database are the teeth is extracted from the whole face image using fixed, well-defined and well known parameters of image clustering technique. This algorithm groups the pixels acquisition.We have downloaded these images to into a number of clusters such that the intensity of extract teeth image for testing purpose [14]. pixels of a cluster has almost similar values.

The algorithm also detects the skin part of human body present in the image. We have used a face detection system based on the algorithms by applying a series of operations like edge detector, morphological operator, filled region, and non-face. We have to record each image into matrix form into database for future processing.This image is getting resized for 256X256 for consistency purpose. Later, this will be converted into grayscale image. The image is again resized into 20X20 to enable captured data to record into database.

There is an option to fix dynamically, fixed value of threshold or use the formula furnished. So we take 18X18 matrix data for calculation. It will be input for converting image into matrix format. Decision logic will be used by creating multiple threshold values but whole experiment should have similar setup which means same camera and same threshold is used in this experiment. The block diagram of proposed model is shown below in Figure1.

Figure 1: Block Diagram of teeth recognition

2.2

There are two major formulas used for executing proposed algorithm. One is find the difference and similarity of the cropped matrix which is created around middle point of the image. As stated above, one uses percent difference when comparing two calculated or experimental valuesto each other. Typically, one is interested in the percent difference of two values pertaining to the same property or characteristic of an object or system (mass, velocity, charge, etc.) Typically, both values are calculated using different methods, theories, or devices. Just as with percent error, calculating percent difference is as follows.

There are different types of dental radiograph, Bitewing X-ray- Bitewing x-ray is taken at routine check-ups.

Periapical x-ray- It shows entire tooth, including crown, root and bone, external picture as JPG. Panoramic xray- It gives broader overview of entire dentition. It shows not only teeth also sinus, upper and lower jawbone. X-ray based picture required special equipment related to medical purpose. Normal Tooth pictures can be taken using camera installed in experimental area with facility to take picture while user reading letters “EEEEE” which gives wide coverage of user teeth. In our experiment we take this JPG images as input.

2.1

METHODOLOGY

Difference %‫ = ܦ‬ቚ( )⁄ ቚ × 100

Similarity %(ܵ) = 100 − ‫ܦ‬

[[[[[[..(1)

[[[[[[[[.(2)

Where I1 and I 2 correspond to the experiment values of interest [15].

LABIAL TEETH DATABASE

Color Imaging Lab - University of Granada, Spain has images of human teeth, Labial Teeth and Gingiva Image photographic image database (LTG-IDB), developed at

58

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Algorithm: Step 1.

Collect Meta data like employee id about the person’s image and store in database assign unique id for image.

Step 2.

Read the RGB image.

Step 3.

Extract teeth part.

Step 4.

Resize the image into size 256 Ă— 256.

Step 5.

Convert the RGB image into gray-scale image.

Step 6.

Resize the image into size 20 Ă— 20 and store in database.

Step 7.

Find ܜℎ‍Ý?Ý ÝŽâ€Źâ„Žâ€Ť= Ý€ÝˆÝ‹â€Ź

Step 8.

Step 9.

Step 10.

Step 11.

Step 12.

Convert gray-scale image into binary image by using threshold value.

Crop the binary image from row focused as 5X18 in the middle.

Count the number of one’s store Take another RGB image from learning database and repeat steps 1 to 10.

Calculate the percentage difference between these two images.

Step 13.

â€ŤÝ ÜżÝŠÝ ÝŽÝ Ý‚Ý‚Ý…ÜŚâ€Ź% = ቚ

(

)

( )â „

ቚ × 100

[[[[[[[[(3)

Step 14.

Find the similarity between these two images Step 15. ÜľÝ…Ý‰Ý…ÝˆÜ˝â€ŤÝ•Ý?݅ݎ‏% = 100 − â€ŤÝ ÜżÝŠÝ ÝŽÝ Ý‚Ý‚Ý…ÜŚâ€Ź ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌(4) Step 16.

Repeat above steps with multiple images of the same person in the learning database. If Similarity is within Acceptance Range consecutively compared with multiple image of same person, images belongs to the same person otherwise they belong to different persons.

Step 17.

End. Acceptance range is derived from difference of percentage between various sample images of the same person taken during the training time. Let us take for example a person is taken 10 images during the training. All these10 images are cross compared with one another and the difference range is determined.

Toleration level acceptance criteria is defined based on learning images. While pattern regeneration compares the key data with multiple test data of same person, if similarity is above specified threshold value, Teeth images belong to same person; otherwise they belong to different persons. Once the person is identified using his Meta data his previous experimental data range is compared to ensure accuracy.

In the database, every image Meta data is stored. Meta data contains like name, age, employee number. We may store up to 50 images or more of the same person.

More number of learning data will give higher accuracy.

Every trail data will be stored and kept for future use.

The similarity has been calculated at random of two images of the same person. Average of the previous images similarity should be matching within threshold range; if not system will identify as different person.

Based on this calculation authentication activity will be done. We can compare the pattern between the same person image and different person images. These patterns can be arrived only when you compare images in cross comparison. For the same person min and max range will be within certain limit but for different person’s image. Based on this observation the system can very easily make out if the image belongs to a particular individual or not. If the images match, the person is granted access to proceed with further steps else access is denied.

59

www.ijitce.co.uk

2.3

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 WORKING OF PROPOSED ALGORITHM The following steps are carried using algorithm to calculate similarity % of two images.

Description of Operation

First Image

Secound Image

The maximum threshold value of image:threshold1 = 180 The minimum threshold value of image:threshold2 = 2 The average threshold value of image:threshold = 91

The maximum threshold value of image:threshold1 = 185 The minimum threshold value of image:threshold2 = 2 The average threshold value of image: threshold = 94

150

148

RGB Image

gray image

The matrix of first grayscale image

Calculate the Threshold

The matrix of binary-scale image is

The matrix of cropped image 18X18

ones in image Difference %

1.3423%

Similarity%

98.6577% Figure 2: Step by step execution of algorithms

60

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 III. EXPERIMENTAL RESULT ANALYSIS We have been taken 20 teeth images of same person and 100 teeth images of different persons. An experiment has conducted to match the teeth images of a person against the teeth image database. The table 1 has shown the results on the teeth image belongs to the same person. Both the images match against the similarity criteria. If they are more than specified threshold old value, then they belong to the same person.

Matching is critical and tricky stage of dental biometric system which finds out difference between two dental processed data. Here we consider cropped data in matrix format for matching of the dental image.

Conclusion can be made by matching one original image in order to increase the accuracy. Algorithm can create pattern of the same person image created using learning data. When comparison is made though all of the training data it is based on more number numbe of sample.

It will ensure accuracy of the result is always high.

S No 1 2 3 4 5 6 7 8 9 10

Same person Image 1 Image 1 Image 1 Image 1 Image 1 Image 2 Image 2 Image 2 Image 2 Image 3

Image 2 Image 3 Image 4 Image 5 Image 6 Image 3 Image 4 Image 5 Image 6 Image 4

Similarity(%) 98.66 100 98.66 91.66 87.26 98.66 100 93.01 88.57 98.66

Figure 3: Similarity among same person teeth images variations within limits In Table 2, We have taken set of teeth images belonging to different persons. The experiment results show that the teeth images of different persons and its similarity percentage. The similarity between two teeth tee images of different persons as shown in figure 4 and 5: We need to observe the patterns of which range from 1 to 95%. So the range difference can’t vary this much for the same person. Based on the range observation system can easily make out this image e is belongs to different person.

Below figure demonstrates teeth structure as one of parameters in verification process.

Table 1: Teeth Image of Same Person The similarity between two teeth images of same person was taken and calculated similarity using proposed algorithm. Randomly taken images are compared with each other images of the same person. We may observe the pattern in Figure 3 it may vary between 88 to 100%. The table needs to be compared for accuracy of the individual teeth image.

Figure 3a.. Teeth structure verification being used in ATM machine.

S No. 1 2 3 4 5 6 7 8 9 10

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Similarity Different Persons Simil Similarity(%) S No. Different Persons (%) Image Image 11 Image 12 74 11 Image 15 51 2 Image Image 11 Image 13 27 12 Image 16 25 2 Image Image 11 Image 14 1 13 Image 11 79 3 Image Image 11 Image 15 45 14 Image 14 18 3 Image Image 11 Image 16 20 15 Image 15 65 3 Image Image 12 Image 13 50 16 Image 16 38 3 Image Image 12 Image 14 22 17 Image 11 79 4 Image Image 12 Image 15 69 18 Image 12 94 4 Image Image 12 Image 16 42 19 Image 13 45 4 Image Image 13 Image 14 68 20 Image 14 17 4 Table 2: Teeth Image of Different Persons

Similarity (%) 100 90 80 70 60 50 40 30 20 10 0 Image 15 Image 16 Image 11 Image 14 Image 15 Image 16 Image 11 Image 12 Image 13 Image 14 Image 2 Image 2 Image 3 Image 3 Image 3 Image 3 Image 4 Image 4 Image 4 Image 4

Figure 4: Similarity among different person teeth variation outside limits

Figure 5: Similarity among different person teeth variation outside limits

S.N o

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 Original Gray-scale Sub-Image Gray-Matrix Binary-Matrix Image Image Matrix

1

2

3

4

5

Figure 6 Teeth images belongs to same person Figure 6 has list of images taken from same person with different variations. Figure 7 has list of images taken from different individuals with different variations. It has gray images and its matrix along with binary matrix to enable calculating similarity.

S.N o

Original Image

Gray-scale Image

Gray-Matrix

Binary-Matrix

Sub-Image Matrix

1

2

63

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

3

4

5

6

Figure 7.Teeth images belongs to different person snap is taken. This can be used in most of common IV. CONCLUSION corporate and restricted areas where their data is present always. It can be used as additional parameter In this paper, the model of teeth recognition for person to identify a person in voter’s database, National security identification has been proposed. The image processing database, employee records. Even this can be used as techniques have been used to match the pattern of teeth key to open doors, office, Bank, schools attendance image against the teeth image database. If the similarity purpose addition to thumb impression reading. We have between two teeth images is above the specified used this method in ATM simulator design as additional threshold value, then they belong to the same person static parameter for identifying banking customer during otherwise they belong to different persons. We have transactional based security authorization[12]. Front concluded that the accuracy of the proposed system is elevation of the radiograph and X-ray images of teeth of more than 90% when the teeth images belong to same cadavers can be compared with this image to get person. The proposed system is accurate when the comparison results for the purpose of forensic analysis. teeth images belong to different persons because consistency is missing. In short, the conclusion is that ACKNOWLEDGMENTS the accuracy of the proposed system is more than 85% We would like to express their gratitude to the on the given set of teeth images belongs to same participants of various imaging sessions who person. This paper proposed algorithm for dental image volunteered for the initial set of images for creating the registration using the phase-based image matching. image database and Color Imaging Lab of University of Experimental performance evaluation demonstrates Granada – Spain for sharing images in Labial Teeth efficient performance of proposed algorithm.

Database for conducting experiments.

Algorithm is developed as semi automatic on JPG images because during the cropping stage we can define the size of the matrix for maximum accuracy.

Threshold point also selected manually, these can be automated based on the usage and alignment to the application and infrastructure. In this method collection of sample image is user friendly. It is very simple image when the individual is reading letters “EEEEEE” face

64

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013 References [1] Armangue, X., Salvi, J., “Overall view regarding fundamental matrix estimation”. Image and Vision Computing, p 205-220, 2003.

[2] Chih-Hong Kao, Sheng-Ping Hsieh and Chih-Cheng Peng, "Study of Feature-Based Image Capturing and Recognition Algorithm", ‘International Conference on Control, Automation and Systems’ 2010,PP 1855-1861.

[3] Forsyth D. A., Ponce, J., “Computer Vision: a Modern Approach”, 1st Ed., Prentice Hall, 1998. 693p.

[4] Gonzalez RC, Woods RE. Digital Image Processing Using MATLAB. New Jersey, USA: Pearson, PrenticeHall, Pearson Education, Inc. 2004.

[5] Rafael C., Gonzalez and Richard E., Wood, Digital Image Processing, 2nd Edition.

[6] S SapnaVarshney, NavinRajpal andRavindarPurwar, “Comparative Study of ImageSegmentation Techniques and Object Matchingusing [7] Segmentation”, International Conferenceon MethodsandModelsin ComputerScience,2009.

[8] Wang Haihui, Wang Yanli, Zhao Tongzhou,Wang Miao, Wu Mingpeng, “ImagesSegmentation Method on Comparison of FeatureExtraction Techniques”, IEEE 2010.

[9] XitaoZheng,YongweiZhang,Qian Song,and Hong Ding, “A New Approach on TeethImage Recognition”, ‘Proceedings of the 2010International Conference on Image Processing,Computer Vision, & Pattern Recognition’, 2010,PP 769-773.

[10] AparecidoNilceu Marana, Elizabeth B. Barboza, João Paulo Papa,Michael Hofer and Denise Tostes Oliveira "Dental Biometrics for Human Identification" Biometrics - Unique and Diverse Applications in Nature, Science,and Technology, 04, April, 2011 [11] Mr. M. Moorthi, Dr. M. Arthanari, Mr. M. Sivakumar, ”The Extraction of the Tooth Contour for Biometric Identification Device is included”, GJCST Volume 10 Issue 14 [12]Sivakumar M, Arthanariee A. M, Enhanced banking framework for improved transaction security, European Journal of Scientific Research, Volume 91 Issue 3.

[13]http://www.sciencedaily.com/releases/2010/06/1006 29094145.htm [14]http://www.ugr.es/~colorimg/LTG_image_database.h tml [15]http://www.mathsisfun.com/percentagedifference.html

65

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.3 NO.4 APRIL 2013

66

www.ijitce.co.uk