july 2020 International Journal of Innovative Technology and Creative Engineering (ISSN:2045-8711) by Editor IJITCE

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

UK: Managing Editor International Journal of Innovative Technology and Creative Engineering 1a park lane, Cranford London TW59WA UK

USA: Editor International Journal of Innovative Technology and Creative Engineering Dr. Arumugam Department of Chemistry University of Georgia GA-30602, USA.

India: Editor International Journal of Innovative Technology & Creative Engineering 36/4 12th Avenue, 1st cross St, Vaigai Colony Ashok Nagar Chennai , India 600083 Email: editor@ijitce.co.uk

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

IJITCE PUBLICATION

International Journal of Innovative Technology & Creative Engineering Vol.10 No.7 July 2020

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

Dear Researcher, Greetings! Articles in this issue discusses about Feature based Natural Image Dataset. It has been an absolute pleasure to present you articles that you wish to read. We look forward many more new technologies in the next month.

Thanks, Editorial Team IJITCE

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

Editorial Members Dr. Chee Kyun Ng Ph.D Department of Computer and Communication Systems, Faculty of Engineering,Universiti Putra Malaysia,UPMSerdang, 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 ShangaiJiaotong 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. BianchiniPh.D Italian National Research Council; IBAF-CNR,Via Salaria km 29.300, 00015 MonterotondoScalo (RM),Italy Dr. NijadKabbara 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 Dr. M. Sivakumar M.C.A.,ITIL.,PRINCE2.,ISTQB.,OCP.,ICP. Ph.D. Project Manager - Software,Applied Materials,1a park lane,cranford,UK Dr. Bulent AcmaPh.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. Dr. S.Prasath Ph.D Assistant Professor, Department of Computer Science, Nandha Arts & Science College, Erode , Tamil Nadu, India

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

Review Board Members Mr. Rajaram Venkataraman Chief Executive Officer, Vel Tech TBI || Convener, FICCI TN State Technology Panel || Founder, Navya Insights || President, SPIN Chennai 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. MutamedTurkiNayefKhatib Assistant Professor of Telecommunication Engineering,Head of Telecommunication Engineering Department,Palestine Technical University (Kadoorie), TulKarm, PALESTINE. Dr.P.UmaMaheswari Prof &Head,Depaartment of CSE/IT, INFO Institute of Engineering,Coimbatore. 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,RuaItapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Visiting Scholar at INSEAD,INSEAD Social Innovation Centre,Boulevard de Constance,77305 Fontainebleau - France Y. BenalYurtlu Assist. Prof. OndokuzMayis University Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. ChutimaBoonthum-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 SchoolRuaItapeva, 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 JavadRobati Crop Production Departement,University of Maragheh,Golshahr,Maragheh,Iran VineshSukumar (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. RostislavChoteborský, Ph.D. Katedramateriálu a strojírenskétechnologieTechnickáfakulta,Ceskázemedelskáuniverzita 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

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 DR.ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg.,HamptonUniversity,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. RostislavChotěborský,ph.d, Katedramateriálu a strojírenskétechnologie, Technickáfakulta,Českázemědělskáuniverzita v Praze,Kamýcká 129, Praha 6, 165 21

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

Naik Nitin AshokraoB.sc,M.Sc Lecturer in YeshwantMahavidyalayaNanded University 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-BangloreWesternly 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,MechanicalEngineering,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 SeraphinChallyAbou Professor,Mechanical& Industrial Engineering Depart,MEHS Program, 235 Voss-Kovach Hall,1305 OrdeanCourt,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. BenalYurtlu Assist. Prof. OndokuzMayis 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. ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business School,RuaItapeva, 474 (8° andar)01332-000, São 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 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 PremaSelvarajBsc,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),UniversitiSainsMalaysia,School of Mathematical Sciences, Pulau Pinang-11800,[PENANG],MALAYSIA. Manoj Sharma Associate Professor Deptt. of ECE, PrannathParnami 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

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 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. SeraphinChallyAbou 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,GianiZail Singh Campus,Bathinda -151001 (Punjab),INDIA Dr. Oliver Jukić Vice Dean for education,Virovitica College,MatijeGupca 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

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

Contents

Feature-based Thresholds on Alpha Matting for Images for Natural Image Dataset ……………………..…...[ 822]

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

Feature-based Thresholds on Alpha Matting for Images for Natural Image Dataset Dr.T. Velumani1, Assistant Professor, Department of Computer Science, Rathinam College of Arts and Science College (Autonomous), Coimbatore, TamilNadu, India. Abstract- The aim of the research is to separate the foreground and background in natural images. The objects separation is performed by analysing the boundary area between foreground and background or the unknown. The analysis of unknown area is used to determine the threshold value to separate definitive foreground and background in alpha matting. The process begins with defining a sub-image of the grayscale image dataset with Region of Interest (ROI). Furthermore, the features of each sub-image consisting of contrast, correlation, energy and entropy are extracted using the Grey Level Co-Occurrence Matrix (GLCM) in angles of 0, 45, 90, and 135. Local extraction results are averaged and normalized and then, it is treated as a threshold for alpha matting. The result is evaluated using Peak Signal Noise to Ratio (PSNR) and shows a significant increase in performance.

Keywords: alpha matting, threshold, region of interest and GLCM. I. INTRODUCTION In recent decades, researches related to the extraction of objects are massively performed as its accuracy will greatly affect the quality of the image or video editing. In addition, object extraction for image or video editing is very important in multimedia applications due to the dramatic increase of the growth of the network multimedia industry. In the beginning, Porter and Duff [1]introduce alpha channels as a function to control linear interpolation of foreground and background colours for anti-aliasing purposes when the foreground joins the background. This is called "pulling matte" or "digital matting" technique in object extraction. "Pulling matte" is performed by combining the semi-transparent colours of the foreground with the background to produce a new blend colour. The degree of gradation of the foreground colour ranges from full black to white. Mixed colour will be foreground if it is full white and be the background for black. Mixed colours are the measured average of foreground and background colours. The accuracy of separation of foreground and background within the boundary of the object determines the success of its process. A qualified matte extraction result should have an even colour distribution, neither too white nor black. If the pixel is too white, it will be dominant in the area correlated with extracted foreground, and it will be the contrary if it is too black which will be the background. The object separation of segmentation and matting are different in how to treat foreground and background pixels. In the hard segmentation technique, the process is firmly performed against the pixels, so that the pixel becomes

part of the foreground or background only. In contrast to the matting technique, the unknown region pixel (α = alpha) becomes part of the foreground and background. The withdrawal process of alpha values (alpha matting) is performed by differentiating the pixels as part of the foreground and background. Alpha matting is a convex combination of two colours allowing the transparency effect in computer graphics. Alpha values range is 0.0 - 1.0 with a full transparent value of 0.0 and full opaque value of 1.0, and the unknown region is determined by defining a threshold value. Initially Levin et al[2]use the alpha threshold was defined as 0.17 - 0.15 assuming that the noise value in an image is within the range. Threshold definition is performed based on user perception by considering the characteristics of the image extracted, so certain expertise is needed in determining the threshold in order to get a qualified matte. User error in determining the threshold will affect the quality of matte. To overcome this problem, an adaptive threshold-based algorithm is proposed to determine the threshold value referring to image characteristics used as alpha threshold. Computation of alpha channel based on global adaptive threshold is performed by using Fuzzy C-Means algorithm [3] and linear optimization [4]. However, the change in illumination causes certain parts to be brighter and darker on another. To overcome the problem, local adaptive threshold is applied by dividing the image into several sub-images, which then compute the threshold value by normalizing feature extraction. Determination of the threshold value is performed by calculating the Region of Interest (ROI) as a block based processing model of the image for initialization in determining the background and background areas. The purpose of selecting an ROI area is intended to divide the image into sub-images. Furthermore, the sub-image is used as a basis for analysing and testing extracted features from the selected image area. Threshold value is determined from the normalization of the average feature extraction value which consists of contrast, correlation, energy and entropy. II. RELATED WORKS Research related to alpha matting-based image segmentation has been carried out in recent decades. J. Wang and M.F. Cohen applies trimap[5][6][7][8][9][10]which is a pre-segmented image to distinguish the foreground, background and unknown areas. Limitation of the approach is misclassification of colour samples in complex scenes. Levin et al [11] define

822

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 user-specific-constraints by applying manual scribble as sampling-sets to define foreground (F) and background (B) to overcome this problem, while unknown or alpha (α) is determined by the specified threshold value of 0 and 1. The use of trimap in separating the foreground and background areas results a visually near perfect[12]. However, the thickness level of manual scratches in the process of defining scribble requires a high level experience, especially in complex and complicated images such as the image of hair, feathers and falling snow [13]. The determination of threshold values in the range of 0-1 for alpha (α) values is adapted to Fuzzy CMeans by Basuki, et al [3]. The threshold value is obtained by calculating the average maximum value in the class having smallest and lowest middle value among others, where the pixel value uses three class concepts in Fuzzy C-Means. Thresholding in this method is calculated by collecting clusters in the areas having the same level of similarity and proximity to each other, by developing grey-level similarity of grey based on interclass and intra-class so that the separation of background, foreground, and alpha is hoped to be more expressive. This technique is then used repetitively for segmenting semi-automatic video objects [14][15]. Before, threshold determination in images was globally calculated. P. Case and H. R. Rana use local thresholding for alpha matting to improve the level of threshold quality in image segmentation [16]. Combinations of image segmentation techniques are performed to obtain optimal results, including Edge and Region Based Segmentation. The Grey-Histogram Technique and Gradient-Based Method are used to define alpha matting of Edge Base Segmentation, and Thresholding method (Local and Global) and Region Operating are for Region Based Segmentation. From the experiments, it is concluded that each segmentation technique in image matting has both advantages and disadvantages that lie in the homogeneity of the natural image dataset used, spatial character structure, and image texture. Therefore, they propose KNN Matting because it can integrate both. In general, the threshold is divided into two: global and local threshold. The problem of using global threshold is that there is a change in illumination compared to the same T value for the entire pixel. This will cause certain parts to be brighter and darker in others (for example, shadows of objects in the original image). However, these problems is overcome by local thresholding [17] adaptively applied to several techniques such as Niblack’s Techniques, Sauvola’s Technique, Bernsen’s Technique, Yanowitz and Bruckstein’s Method, and Maximum Entropy [18]. Local adaptive threshold is able to produce optimal values in the segmentation of an image because the threshold is calculated by dividing the image into new sub-images and not from the entire surface as one. Based on the previous research, the alpha threshold will be calculated in the local adaptive

threshold, where the maximum entropy threshold value obtained from the Region of Interest (ROI) area is normalized as the input of alpha threshold. The feature extraction from each sub-image of ROI produces a successful result for determining the threshold [19]. Feature extraction applied is the GLCM (Grey Level CoOccurrence Matrix) which is a feature extraction method using statistical analysis of using grayscale images. In addition, GLCM is also able to examine textures by considering the spatial relationship of pixels in an image. III. RESEARCH FRAMEWORK The proposed feature-based object extraction system is illustrated in Fig. 1. The first step in the extraction process began with image acquisition as a source of data analysed. Each image in the RGB domain was transformed into the grayscale domain to simplify the computational process. The next grayscale image was cut and divided into 16 sub-image blocks using the Region of Interest (ROI) method. It was performed in order to locally calculate the feature. image accuisition

image transformation

ROI determination

image matting

threshold determination

feature extraction

evaluation Fig. 1. Research framework

Feature extraction was performed over the subimages generated from ROI by the parameters of contrast, correlation, energy and entropy in angles 0, 45, 90 and 135 using the GLCM (Grey Level of CoOccurrence Matrix) method. The feature extraction results were then normalized and treated as a threshold value (α) in the image matting. The accuracy of the extracted object was evaluated using PSNR (Peak Signal Noise to Ratio) by comparing the matte produced by the system with the ground truth (matte reference from the dataset). IV. DISCUSSION The matte extraction test was performed using a public matting dataset consisting of teddy.bmp, kid.bmp, teddy_ear.bmp, fire.bmp and hair.bmp (as well as shown in Fig. 2.), in following stages: • Image transformation: image conversion from RGB to Grayscale domain aimed to simplify the computational process. The image composition with 1 (one) channel would be simpler compared to 3 (three) channels with a value range of 0 - 255. The conversion process was performed, following the Equation (1).

823

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

GrayImage = 0.2989R + 0.5870G + 0.1140 B

(1)

In which R is red, G is green and B is blue channel of the intensity value.In addition, the computational process was also simplified for the efficiency of processing time by considering the threshold value so that the intensity value became binary (0 and 1) so that it was able to be used in the extraction process. â&#x20AC;˘ Region of Interest (ROI):Region of Interest is a part of an image identified for a particular purpose. In this research, the determination of ROI was performed using the block processing method [20] where the converted image in the grayscale domain was divided into 16 blocks of the same size as shown in Fig. 3.

1) Contrast Contrast was a measure of the existence of variations in the level of gray pixel images, calculated using Equation (2). L ď&#x192;Ź ď&#x192;ź ď&#x192;Ż ď&#x192;Ż Contrast = ď&#x192;Ľn 2 ď&#x192; ď&#x192;Ľ GLCM (i, j ) ď&#x192;˝ (2) n =1 ď&#x192;Ż ď&#x192;Ż ď&#x192;Ž iâ&#x2C6;&#x2019; j =n ď&#x192;ž in which L was the number of levels used in computing, nwas the number of pixels, iwas the smallest pixel intensity, and jwas the largest pixel intensity. 2) Correlation Correlation is a measure of linear dependency between gray levels in an image which is

Fig. 2. Dataset of image matting, while figure (a) to (e) showing original image and figure (f) to (j) showing image reference

Furthermore, ROI was treated as a sub-image in which each block was labelled as initialization to distinguish the foreground and background regions. â&#x20AC;˘ Feature extraction:GLCM (Gray Level Co-0ccurrence Matrix) was used to extract features which based on the two order texture calculation to calculate the relationship of pairs of two pixels in the original image. Sub-images were used as data sources tested. The GLCM features analyzed were: Contrast, Correlation, Energy, and Entropy. Feature extraction was performed by taking a window of 5x5 pixels from each sub-image. The window was taken from the upper left corner of each sub image as shown in Fig. 3 and calculated to determine the value of each feature as follows:

824

calculated using the following Equation (3).

ď&#x192;Ľ ď&#x192;Ľ Correlation =

(ij )(GLCM ( i, j ) â&#x2C6;&#x2019; ď i ' ď j '

i =1

j =1

ď ł i 'ď ł j '

(3)

in which L was the number of levels used in the computation proses, n was number of pixels, i was the smallest pixel intensity, and j was the largest pixel intensity. Then, đ?&#x153;&#x17D;đ?&#x2018;&#x2013; â&#x20AC;˛ đ?&#x153;&#x17D;đ?&#x2018;&#x2014; â&#x20AC;˛ was deviation standard for all pixel intensity in matrix GLCM. 3) Energy Energy was the intensity measure of region area variation, calculated by the Equation (4).

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 G â&#x2C6;&#x2019;1

Energy = ď&#x192;Ľ ď &#x203A;GLCM (i )ď ?

i =0

(4)

in which i was the pixel intensity average in matrix GLCM. 4) Entropy Entropy was used to express the size of gray level irregularities in the image calculated by applying the Equation (5). L

Entropy = â&#x2C6;&#x2019;ď&#x192;Ľď&#x192;Ľ(GLCM ( i, j ) log(GLCM (i, j ) i =1 j =1

(5)

Feature value determination of contrast, correlation, energy and entropy at rotation angles of 00, 450, 950 and 1350was applied in all windows in each sub image. The average value in eachfeature value was summed and divided by the number of features analyzed. â&#x20AC;˘ Alpha matting: A qualified matte extraction result should have an even color distribution, neither too white nor black. If the pixel is too white, it will be dominant in the area correlated with extracted foreground, and it will be the contrary if it is too black

which will be the background.The object separation of segmentation and matting were different in how to treat foreground and background pixels. In the hard segmentation technique, the process was firmly performed against the pixels, so that the pixel would be part of the foreground or background only. In matting technique, the unknown region pixel (Îą = alpha) would be part of the foreground and background. Thus, the threshold value in this area would decide the quality of separation result.The object separation process was performed by the assumption that dominant pixels with the white (đ?&#x203A;ź = 1) would correlate with foreground and black (đ?&#x203A;ź = 0) with background. The accuracy will meet the problem in the unknown region which is located at the edge of an object. Image matting operations were performed by specifying a threshold value between 0-1 to define the unknown region value.The threshold determination was previously performed by Levin and Lischinski where the alpha threshold was defined between0.17 â&#x2C6;&#x2019; 0.15 , assuming that the noise value in an image ranges within. Threshold definition was performed based on user perception by considering characteristics of the image extracted, so users need certain expertise in determining the threshold in order to obtain the best result. User error in determining the threshold will affect the quality of matte [2]. Basuki et al, propose an adaptive threshold-based algorithm by applying Fuzzy C-Means to determine threshold

Fig. 3. Image transformation and ROI determination

825

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 values referring to the image characteristics used as thresholds in the unknown region to overcome this problem [3][21].In this research, the threshold value was calculated in each sub-image resulting from the local determination of ROI. The average value of feature extraction from GLCM (contrast, correlation, energy and entropy) in each sub-image (Equation 2 5) was normalized by dividing the entropy value in each sub-image by the average number of GLCM values in an image as l as shown in Equation (6).

compared to closed-form solution with FCM as alpha threshold [3],[14],[15]. Evaluation of each image was performed using PSNR (Peak Signal Noise to Ratio) as in the Equation 9 and the results are shown in Fig. 5.

ď&#x192;Š 2552 ď&#x192;š PSNR = 10log10 ď&#x192;Ş ď&#x192;ş ď&#x192;Ť MSE ď&#x192;ť

(8)

in which

Fig. 4. Extraction stage : (a). original image, (b). scribble image, (c). matte reference from dataset, (d). matte extraction from the proposed approach, and (e). object extraction the result from the proposed approach

Threshold =

Average (Contrass + Correlations + Energys + Entropys ) ď&#x192;Ľaverageimage feature

M â&#x2C6;&#x2019;1N â&#x2C6;&#x2019;1 ď&#x192;Ś abs( grdImg â&#x2C6;&#x2019; matteExt ) ď&#x192;ś MSE = ď&#x192;Ľď&#x192;Ľ ď&#x192;§ ď&#x192;ˇ M ď&#x201A;´N ď&#x192;¸ i =1 j =1 ď&#x192;¨

(6)

(9)

With đ?&#x2018;&#x201D;đ?&#x2018;&#x;đ?&#x2018;&#x2018;đ??źđ?&#x2018;&#x161;đ?&#x2018;&#x201D; was the ground truth image as the reference image, đ?&#x2018;&#x161;đ?&#x2018;&#x17D;đ?&#x2018;Ąđ?&#x2018;Ąđ?&#x2018;&#x2019;đ??¸đ?&#x2018;Ľđ?&#x2018;Ą was a matte extracted by the system and đ?&#x2018;&#x20AC; Ă&#x2014; đ?&#x2018; was the size of the executable image.

in which s was feature value on sub-image. The result of the Equation (6) was treated as threshold value for alpha matting [11]as input for Equation (7). â&#x20AC;˘

Experiment result and evaluation: Testing of the image matting dataset was performed by input images in the form of original, terrible and reference images as a reference for testing comparisons between proposed method and intended results. Each image (teddy.bmp, teddy_ear.bmp, kid.bmp, fire.bmp and hair.bmp) was converted into gray image and divided into 16 blocks of sub-image. Each sub-image is taken by a 5x5 pixel window which was calculated by GLCM to obtain the feature value and normalized to the threshold value treated as an input alpha value (Îą) in the matting image as shown in the Equation (7).

I i = ď Ą i Fi + (1 â&#x2C6;&#x2019; ď Ą i ) Bi

(7)

Fig. 5. Performance evaluation using PSNR

in which đ??šđ?&#x2018;&#x2013; was definitive foreground value, đ??ľđ?&#x2018;&#x2013; was definitive background and đ?&#x203A;źđ?&#x2018;&#x2013; was unknown region. Then, matte was extracted using closed-form matting [3][11][14][15]. The result was replaced by original image in order to obtain object desired as described in Fig. 4.The trial result conducted on each of the analyzed images showed that the proposed method had a significant increase in the performance

V. CONCLUSION Alpha matting based of object extraction was tested on 5 images from the matting image dataset. Initially, the image was transformed into the grayscale domain and divided into 16 sub-images and using ROI for each. Each sub-image feature was extracted (local threshold) using GLCM with contrast, correlation, energy and entropy parameters, then results were normalized and treated as threshold values in alpha matting.

826

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020 The trial results showed that the object extraction process with a feature-based threshold for natural images worked well in extracting matte. The visually matte which correlates with foreground pixels was able to correlate more accurate. In addition, an increase in accuracy was quantitatively shown by the results of evaluations using Peak Signal Noise to Ratio (PSNR) which showed an average increase up to 63% from the previous [3][14][15][21].

REFERENCES [1] T. Porter and T. Duff, “Compositing Digital Images,” Computer Graphics, vol. 18, no. 3, pp. 253 - 259, 1984.

Engineering & Technology (IJARCET), vol. 2, no. 2, pp. 387 - 389, 2013. [18] N. Senthilkumaran and S. Vaithegi, “Image Segmentation by Using Thresholding Techniques fo Medical Images,” Computer Science & Engineering : An International Journal, vol. 6, no. 1, pp. 1 - 13, 2016. [19] N. Zayed and H. A. Elnemr, “Statistical Analysis of Haralick Texture Features to Discriminate Lung Abnormalities,” Journal of Biomedical Imaging, vol. 12, 2015. [20] G. R. Jothilakshmi, J. R. Christilda, A. Raaza, Y. SreenivasaVarma and V. Rajendran, “Extracting Region of Interest Using Distinct Block Processing Method in Sonomammogram Images,” in International Conference on Computer, Communication and Signal Processing (ICCCSP), Chennai, India, 2017. [21] R. S. Basuki, M. A. Soeleman, M. Hariadi, M. H. Purnomo, R. A. Pramunendar and A. F. Yogananti, “Spectral-Based Video Object Segmentation Using Alpha Matting and Background Subtraction,” in Fourth IIEEJ International Workshop on Image Electronic and Visual Computing, Koh Samui, Thailand, 2014.

[2] A. Levin, A. Rav-Acha and D. Lischinski, “Spectral Matting,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, pp. 1699 -1712, 2008. [3] R. S. Basuki, M. Hariadi and R. A. Pramunendar, “Fuzzy C-Means Algorithm for Adaptive Threshold on Alpha Matting,” in Conference on Information Technology and Electrical Engineering, Yogyakarta, 2012. [4] S. Chen, Z. Li, J. Liu and X. Tang, “Image Matting Using Linear Optimization,” in Proc. 15th International Conference Multimedia, 2007. [5] J. Wang and M. F. Cohen, “Optimized Color Sampling for Robust Matting,” in Computer Vision and Pattern Recognition (CVPR), Minneapolis, 2007. [6] N. E. Apostoloff and A. W. Fitzgibbon, “Bayesian Video Matting Using Learn Image Priors,” in Proc. Fifth LASTED International Conference Visualization Imaging and Image Processing, 2004. [7] J. Sun, J. Jia, C. Tang and H. Shum, “Poisson Matting,” ACM Transaction on Graphics, vol. 23, no. 3, pp. 315 - 321, 2004. [8] Y. Y. Chuang, A. Agarwala, B. Curless, D. H. Salesin and R. Szeliski, “Video Matting on Complex Scenes,” ACM Transaction on Graphics, vol. 21, no. 3, pp. 243 - 248, 2001. [9] Y. Y. Chuang, B. Curless, D. H. Salesin and R. Szeliski, “A Bayesian Approach to Digital Matting,” in Proc. IEEE Conference Computer Vision and Pattern Recognition, 2001. [10] M. A. Ruzon and C. Tomasi, “Alpha Estimation in Natural Images,” in Proc. IEEE Conference Computer Vision and Pattern Recognition, 2000. [11] A. Levin, D. Lischinski and Y. Weiss, “A Closed-Form Solution to Natural Image Matting,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 30, no. 1, pp. 228 - 242, 2008. [12] J. Wang and M. F. Cohen, “Image and Video Matting : A Survey,” Foundation Trends Computer Graphics and Visual, vol. 3, pp. 97 - 175, 2007. [13] H. Liu, L. Ma, X. Cai, Z. Chen and Y. Shen, “A Closed-Form to Video Matting of Natural Snow,” Information Processing Letter, vol. 109, no. 18, pp. 1097 - 1104, 2009. [14] R. S. Basuki, M. A. Soeleman, R. A. Pramunendar, A. F. Yogananti and C. Supriyanto, “Video Object Segmentation Aplying Spectral Analysis and Background Subtraction,” Journal of Theoretical and Applied Information Technology, vol. 72, no. 2, pp. 208 - 214, 2015. [15] R. S. Basuki, M. Hariadi, E. M. Yuniarno and M. H. Purnomo, “Spectral-Based Temporal-Constraint Estimation for SemiAutomatic Video Object Segmentation,” International Review on Computer and Software, vol. 10, no. 9, pp. 959 - 965, 2015. [16] H. R. Rana and S. Kumar, “Color Tree Image Extraction Using KNN Matting,” International Journal of Advanced Research in Computer Engineering and Technology, vol. 2, no. 6, pp. 57 - 62, 2014. [17] H. J. Vala and A. Baxi, “A Review on Otsu Image Segmentation,” International Journal of Advanced Research in Computer

827

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.10 NO.7 JULY 2020

828