Feb2015

ISSN (ONLINE) : 2045 -8711 ISSN (PRINT) : 2045 -869X

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY & CREATIVE ENGINEERING FEBRUARY 2015 VOL- 5 NO - 2

@IJITCE Publication

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015

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 66/2 East mada st, Thiruvanmiyur, Chennai -600041 Mobile: 91-7598208700

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015

www.ijitce.co.uk

IJITCE PUBLICATION

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY & CREATIVE ENGINEERING Vol.5 No.2 February 2015

www.ijitce.co.uk

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015

From Editor's Desk Dear Researcher, Greetings!

Research article in this issue discusses about motivational factor analysis.

Let us review research around the world this month.

Inkjet-Printing System Could Enable Mass-Production of Large-Screen OLED Displays based on years has developed an inkjet printing system that could cut manufacturing costs enough to pave the way for mass-producing flexible and large-screen OLED displays. Flexible smart phones and color-saturated television displays were some highlights at this year’s Consumer Electronics Showcase, held in January in Las Vegas. Many of those displays were made using organic light-emitting diodes or OLEDs semiconducting films about 100 nanometers thick, made of organic compounds and sandwiched between two electrodes that emit light in response to electricity. They’re not very cost-effective to make en masse.

Image mining is the process of searching and discovering valuable information and knowledge in large volumes of data.

Image mining draws basic principles from concepts in databases, machine learning, statistics, pattern recognition and soft computing. Using data mining techniques enables a more efficient use of data banks of earth observation data. An emerging research field in geosciences because of the increasing amount of data which lead to new promising applications.

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.5 NO.2 FEBRUARY 2015

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. NijadKabbaraPh.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. SelvanathanArumugamPh.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. MutamedTurkiNayefKhatib Assistant Professor of Telecommunication Engineering,Head of Telecommunication Engineering Department,Palestine Technical University (Kadoorie), TulKarm, PALESTINE.

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 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 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

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 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

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,S찾o Paulo Business School,RuaItapeva, 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 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

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 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 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 55812-3042 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

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015

Contents An Enhanced Technique for Image Indexing and Retrieval with Orientation Features Using Autocorrelation Function K.Selvarajan & Dr.S.Pannirselvam ….…………………………………………….……………………….[259]

www.ijitce.co.uk

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015

An Enhanced Technique for Image Indexing and Retrieval with Orientation Features Using Autocorrelation Function K.Selvarajan* Ph.D Research Scholar & Associate Professor, Department of Computer Science, Bishop Thorp College, Dharapuram Email: ks_btc@yahoo.in Dr.S.Pannirselvam Research Supervisor & Head Department of Computer Science, Erode Arts & Science College (Autonomous), Erode, Tamil Nadu, India.

Email: pannirselvam08@gmail.com Abstract-- In this paper, the rectangular features of an and widely used to find the step edges rather than the roof image are considered for generation of feature set and edges. All these operators are first order derivatives.

Hueckel [7] proposed a method for edge-fitting and compared with the existing techniques. The orientation features are extracted for the establishment of feature set edge detection and later it has been simplified by Rosenfeld for image indexing and retrieval. The identification and the [17]. Though the gradient based operators are computationally representation of textures present in the image under simple and amenable to the hardware implementation, the analysis are performed with auto-correlation coefficients Laplacian operator, which is a second order derivative is by estimating the model parameters for small image mostly used to establish the location of edges present in the regions. The feature is generated and matching is done by measuring distance between two images using Euclidean image. This operator cannot be used in its natural form for distance classification. The experiments are carried out on edge detection.

Instead, it is applied with the Gaussian function the standard images using MATLAB. The result shows that proposed method provides better retrieval rate when which is known as Laplacian of Gaussian (LoG) function [11]. compared with the existing methods such as Local Tetra Goshtasby et al., [5] proposed a curve-fitting Patterna and Local Ternary Pattern Method. approach for edge detection in which the parametric curves are being used to represent the edge contours and fitted to the Keywords— LBP,CBIR,LTP,ACF, high-gradient image pixels with its weight proportional to the 1. INTRODUCTION gradient magnitude of the pixels.

Edge based image retrieval is one of the best Krishnamoorthi et al., [8] used the curve fitting approaches for image retrieval system. The extraction of edges model based on zero-crossing in the second order derivatives in 2D monochrome images based on the proposed Full Range and claimed that the technique is superior to the vector order Auto Regressive Model is first presented in this chapter and is statistics and entropy schemes in color images. Sarkar et al., extended for subsequent effective image retrieval.

[18] reported that the edge detectors are based on optimality Generally, an edge is defined as a boundary point or criterion. outermost area of an object. In image retrieval, edge plays a Canny’s [1] operator is very much popular among all major role. The retrieval process is done by detecting the the edge detectors and it uses Gaussian filter for smoothing edges, computing their values and performing the low-level the image before extracting the edges. tasks such as identification, classification, matching, Ding et al., [Ding01] have proved that the Canny’s segmentation, compression and boundary detection. In algorithm cannot capture the branching edges and edge general, edges are characterized by an abrupt change in the junctions, but it captures the spurious edges. gray value of an image and they are classified as roof edges Grimson et al., [6] introduced a residual analysis and step edges. approach for computer vision applications and suggested the zero-crossings of the residual results in locating the edges.

2. LITERATURE SURVEY Subsequently, [9] have analysed and reported the In the literature, many reviews on edge detection are differences between the original and the smoothed version, reported and various algorithms are proposed for edge which are the important feature detectors to extract edges in extraction in gray level images. Edge detection methods are gray scale images [10]. classified into enhancement /threshold type, gradient based Chen et al., [2] considered the distribution of operators, edge-fitting, edge detection, zero-crossings in residuals and found auto correlation for the residual by which second order derivatives, curve fitting approach, optimally they could extract the edge features. criterion approach and residual based techniques.

Zheng et al., [24] proposed a hybrid edge detector The enhancement/threshold type is well-known for with the combination of gradient and zero-crossing based on its simplicity and low computational complexity. The gradient Least Square Support Vector Machine (LS-SVM) with the values of different orders are calculated by convolving the Gaussian filter. It is reported that it takes lesser time than the various gradient operators. The gradient based operators such Canny’s detector with similar performance on edge extraction. as Roberts [16], Prewitt [13] and Sobel [21] are well known In the earlier works, the threshold is chosen on heuristic basis 259

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 for edge detection. Even in the Canny’s edge detector the default value of the upper limit is suggested to be 75th percentile of the gradient strength.

Rakesh et al., [15] reported that this problem has been overcome in their work, but their algorithm needs initial threshold value and parameters as an input. Several methods have been proposed for edge detection with marking points in a digital image. Most of the algorithms typically convolute a filter operator, and then map overlapping input image regions to output signals which lead to a considerable loss in edge detection. Even Gaussian filter suffers with some problems such as edge displacement, vanishing edges and false edges.

Shashank Mathur et. al., [19] have proposed an application model based on fuzzy logic that helps to deal with problems with imprecise and vague information.

Dong-Su Kim et al. [4] proposed a procedure to determine the edge magnitude and direction which are found in the (3 × 3) ideal binary pattern for a block. The average value is calculated for the pixels in a (3 × 3) block, and compared with each pixel in the block. If the pixel is greater than the average value then it is marked as 1, otherwise it is marked as 0. Then, they proposed fixed weight such as (1, 2, 4, 8, 16, 32, 64 and 128) for the 8-neigbouring pixels depending on their zonal position related to the centre pixel and formulated an 8-bit code by adding the weight of the pixels which are marked as 1. This is not justifiable because the pixel values in a (3 × 3) block generally influence the centre pixel more or less equally. In this approach, they used the weight 1 to the pixel in the location (1, 1) and 128 to the pixel in the location (3, 3).

3. EXISTING METHODOLOGY 3.1 LOCAL TETRA PATTERNS Local Tetra Patterns for the application of contentbased image retrieval. This method encodes the spatial relationship between the referenced pixel and its neighbors, which is based on the first order derivatives, along vertical and horizontal directions. The 8 bit tetra pattern for each center pixel is formulated, then separate all patterns into four parts based on the direction of center pixel. Finally, the tetra patterns for each direction are converted into three binary patterns. Similarly, the other tetra patterns for remaining three directions (2, 3 and 4) are converted to 12 binary patterns.

3.2 LOCAL TERNARY PATTERNS Conventional LBP is extended to a three – valued code called as LTP. It preserves more textural information than LBP. This descriptor perceives the number of transitions or discontinuities in the circular presentation of the patterns.

When such transitions are found to follow a rhythmic pattern, they are recorded as uniform LTP. 3.3 PROPOSED METHODOLOGY The feature extraction is an important process to make efficient image indexing and retrieval. Hence an enhanced technique is used to extract the feature and represent image as a template for image recognition and retrieval.

3.3.1 ORIENTATIONAL FEATURE There are various models and methods are available for image indexing and retrieval but not sufficient for providing accuracy in recognition process. To develop an image indexing and retrieval system features extracted based on orientation and autocorrelation features of an image. In order to improve the efficiency of the image retrieval system using low-level salient features embedded in the edges are extracted.

Input Image

Models Local Tetra Patterns Local Ternary Patterns Orientation Feature Autocorrelation

Feature Extraction

Target Image

Euclidean Distance

Output Image

Fig.1 Process flow In general, matching of texture based image is carried out with the similarity between the areas of the images with similar texture. The technique that has been used for measuring texture similarity is done by calculating the relative brightness of selected pairs of pixels from each image. From these it is possible to measure texture features of the image such as the degree of contrast, coarseness, directionality and regularity, or periodicity, directionality and randomness.

Texture queries can be formulated in a similar manner to color queries, by selecting examples of desired textures from a palette or by supplying a query image. The system then retrieves images with texture measures which are most similar to the query.

If the primitives are large, the function decreases slowly with increasing distance where as it decreases rapidly if texture consists of small primitives. The auto-correlation function is defined as: M − r −1 N − c −1

A (r , c ) =

1 ( M − r )( M − c )

∑

i=0

∑

---(3.1)

M −1 N −1

∑∑ i=0

0

g 0 (i , j ) g 0 (i + r , j + c )

j=0 0

0

g (i, j ) g (i, j )

j=0

Here g represents the zero-mean image of the gray level image g(r,c) of size M X N and computed by the equation [g0=g(r,c)-mean of g]. Nature of function value reveals the presence of texture pattern and its periodicity of representation. However, if the primitives are periodic, then the autocorrelation increases and decreases periodically with distance. The set of autocorrelation coefficients [Gcff] are modeled to extract the texture features as below:

260

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 M − P N −q

MN G

cff

∑ ∑ i=1

=

g (i, j) g (i + p , j + q ) M

(M

… (3.2)

j =1

− p )( N − q ) ∑ i=1

N

∑

g

2

(i, j)

j =1

Here the position difference in the i, j direction is denoted by p and q respectively and their value ranges from (0,0) to (r-1,s-1) such that 1 ≤ r ≤ M/2 and 1 ≤ s ≤ N/2.The gray scale image with M X N dimension is considered for computation.

When the positional difference (p,q) varies from (0,0) to (r-1,s-1) the extracted texture feature is represented as a matrix as shown below:

Fcff ( p , q ) = ( G ff ( r , s )) rm=, n0 .. m − 1

definition is often used without the normalization without subtracting the Mean and dividing by the variance. When the autocorrelation function is normalized by mean and variance, it is sometimes referred to as the autocorrelation coefficient.

Multi-dimensional autocorrelation is defined similarly.

3.3.3 HORIZONTAL DIRECTIONALITY In the proposed model, the texture horizontal directionality of each block of size (n x n) is computed by applying q = 0 in the equation (3.2). The auto correlation coefficients on horizontal directionality is modeled and converted into autonums and are represented as

F hff ( p , 0 ) = ( G ff ( r , 0 )) mr = 0 .. m − 1

........ (3.3)

s = 0 .. n − 1

In order to represent the identified micro textured regions, the autocorrelation coefficients are calculated using the equation 3.2 and are stored in an array for various subimages. The computed autocorrelation values range from 0 to 1. A simple transformation (P*100) is applied on the autocorrelation values to obtain decimal number that range from 0 to 100, where P is the autocorrelation coefficient.

3.3.2 AUTOCORRELATION FUNCTION In statistics, the autocorrelation function of a random process describes the correlation between the processes at different points in time. Let Xt be the value of the process at time t (where t may be an integer for a discrete time process or a real number for a continuous-time process). If Xt has Mean µ and variance σ2 then the definition of the ACF is E [( X t − µ ) ( X s − µ )] R (t , s ) = 2 σ …(3.4) The expression is not well-defined for all time series.

Since the variance σ2 may be zero (for a constant process) or infinite. If the function R is well defined its value must lie in the range [-1,1], with 1 indicating perfect correlation and -1 indicating perfect anti-correlation.

If Xt is second-order stationary then the ACF depends only on the difference between t and s can be expressed as a function of a single variable. This gives E [( X i − µ ) ( X i + k − µ )] R (k ) = σ2 … (3.5) Where k is the tag |(t-s)|. It is common practice in many disciplines to drop the normalization by σ2 and use the term autocorrelation interchangeably with auto-covariance.

For a discrete time series of length n{X1, X2, ...... Xn} with known Mean and Variance, an estimate of the autocorrelation may be obtained as n −k 1 Rˆ (k ) = X − µ][ Xt +k − µ] 2 ∑[ t (n − k ) σ t=1 … (3.6) for any positive integer k<n. When the true Mean µ is known, this estimate is unbiased. However, if the true Mean and variance of the process are not known and µ and σ2 replaced by the standard formulae. For sample mean and sample variance, then this estimate is biased. An alternative way a period gram based estimate replaces n-k in the above formula with n. This estimate is always biased it usually has a smaller Mean square error. In image processing, the above

…(3.7)

3.3.4 VERTICAL DIRECTIONALITY In the proposed model, the texture vertical directionality of each block of size (n x n) is computed by applying p = 0 in the equation (3.2). The auto correlation coefficients on horizontal directionality is modeled and converted into autonums and are represented as

Fvff ( 0 , q ) = ( G ff ( 0 , s )) ns = 0 .. n − 1

--- (3.8)

3.3.5 RECTANGULAR FEATURES The rectangular grid of each sub-image is represented in a matrix of size (mxn) as shown in the equation 1, if thepresenceof shapeareawithinthegrid f ( x,y) = … (3.9) 0, otherwise

G m , n = ( g ( m , n )) mm ,=n0 .. m − 1

… (3.10)

n = 0 .. n − 1

The general features such as area, perimeter, centroid and mass are computed for rectangular grid in which it satisfies ¼ of presence of shape and represented by fri where i=1..k.

3.3.6 GENERATION OF FEATURE SET The feature set is generated with the orientation image based feature vectors for all the sub images. The features of each blocks of the sub image and are represented as below, Fori = {Fcff , Fhcff , Fvcff , f r1 ,..., f rk } … (3.11) Hence, the obtained orientation features values of each block are represented. Then the feature vectors are obtained with the values as mentioned in equation 3.11. Here, the orientation feature set generation is considered for the recognition and retrieval. The extracted feature set of the block of the target image is obtained.

3.4 PROPOSED ALGORITHM The entire retrieval procedure with the orientation features is presented as simple algorithms hereunder using MATLAB. In two phases the orientation feature, of the images from the databases, are used. In the algorithm-I, procedure to establish feature set is established for each of the images. In algorithm-II, the image retrieval procedure that retrieves top ‘m’ images from the IDB corresponding to the target image is presented.

261

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 3.4.1 Algorithm – I // Procedure Orientation Feature//

// generating feature sets // Input: Input image size from IDB Output: Feature database Begin Step 1: Read an image from the image database (IDB) of size M×N. Step 2: Divide the input image into non-overlapping blocks of size.

Step 3: Perform procedure ori _ feature ( ) Step 3: Perform procedure auto_ corr ( ) Step 4: Repeat Step1 through Step4 for all the images in IDB. Step 5: Establish feature database set End

Procedure ori_ feature ( ) Begin Step 1 : Identify the closed edges of the input image with rectangular grid.

Step 2: Fill the grid values either “1” for presence of rectangular (or) “0” for other.

Step 3: Eliminate the shape present in the rectangular grid if the area less than ¼ of the bounded rectangular grid area and count no. of shape (n) for feature extraction.

Step 4: Establish the horizontal feature matrix with the auto correlation features of the input image as discussed in section 3.3.2.

Step 5: Establish the vertical feature matrix with the auto correlation features of the input image as discussed in section 3.3.4.

Step 6: Calculate rectangular based general features such as centroid area, perimeter and mass of selected Kth rectangular grid area as discussed in the sub section for 3.3.5.

Step 7: Establish the rectangular based general feature set are computed as mentioned in equation 3.10 Step 8: Calculate the features set of the input image as mentioned in equation 3.11.

Step 9: Repeat Step2 through Step6 for all the input images and find the feature vectors of each rectangular features.

Step 10: Return End

3.4.2 Algorithm-II //Retrieving top m relevant images corresponding to the target image// Input : Target Image Output : Resultant Image Begin Step 1: Select the target image of size M×N and divide into blocks.

Step2: Repeat Step3 and Step 4 in algorithm I. Step3:Compute the Euclidean distance between the target image and the image set for matching using the equation 3.13.

Step 4: Compute the Precision and Recall using the equation 3.14 and equation 3.15.

Step 5: Stop End // procedure auto correlation // Procedure auto_Corr () { Step 1: Read an input image from the image database.

Step 2: Compute the positional difference by using equation 5.16 Step3: Establish feature Matrix with the auto correlation features for all the K sub regions of the input image as discussed in equ.3.2 Step 4: Return }

4. EXPERIMENTATION & RESULTS The experimentation is carried out by MATLAB. To validate the effectiveness of the proposed orientation feature based image retrieval system, experimentation is performed with the images in the CORAL image database that contains five hundred 2-D monochrome images of same size. The total images are grouped into 40 classes with 10 images in each class.

262

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015

Fig 2.Images Considered for Experimentation 5. SIMILARITY AND PERFORMANCE MEASURES To find the similarity measures between the images, various metrics are used to measure the distance between features of the images. Some of the well known distance metrics used in for image retrieval is presented below. The Euclidean Distance is calculated as below

d E ( x1 , x 2 ) =

i= n

( x1 (i ) − x2 (i )) ∑ i =1

2

… (3.12) Where x1(i) is the feature vector of input image i and x2(i) is the feature vector of the target image i in the image database.

In the texture based image retrieval system Euclidean distance is used to find the distance between the features vectors of the target image It and each of the image in the image database (Ii). The difference between two images Ii and It can be expressed as the distance ‘d’ between the respective feature vectors Fs(Ii) and Fs(It).

From the given input image Ii and the target image It the Euclidean Distance is calculated as,

(

( )

)

dE Fs Ii , Fs( It ) =

i=n

∑ Fs( Ii ) − Fs( It ) i=1

(

)

2

… (3.13) Where Fs(Ii) is the feature set of the input image Ii, Fs(It) is the n-dimensional feature vector of the target image It respectively.

Precision Precision measures the fraction of retrieved documents that are relevant to a specific query and is analogous to positive predictive value.

No. of relevant images retrieved P (%) = × 100 -- (3.14) Total no. of images Retrieved

6. PERFORMANCE EVALUATION The proposed feature extraction is experimented with the images collected from the standard database CORAL consisting of 1000 images are of the size ( m x n) as shown in fig.2. From the below Table 1.1 shows that recognition percentage of query images with Proposed Model gives the higher retrieval accuracy of 65.13%. The performance was evaluated using the Euclidean Distance classification by analysis of the values in the table the Proposed model is better for image retrieval.

Table 1.1 Comparison Values Methods Recognition Local Binary Pattern(LBP) [24] 43.62 Local Tetra Patterns (LTP) [24]

49.05

Local Ternary Patterns(LTrPs) [24]

48.79

Proposed Orientation Model 65.13 From the below figure shows the pictorial representation of the performance evaluated. By analyzing the obtained results the Proposed Model produced the best results.

Fig.3 Comparison Graph with Existing Model Hence, the retrieval rate is estimated in terms of precision and recall. The precision and recall of the proposed method is presented in the following table. The performance of the existing schemes with precision and recall are also obtained. For every comparison, they are also incorporated in the same Table 4.2.

Table 1.2 Comparison Result Method Precision Recall GLCM [23] 0.72 0.54 Law’s Method [23] 0.81 0.68 Proposed 1.06 0.13 Orientation Model The above Table 1.2 shows the precision and recall of the proposed model in which the proposed model provides the precision 1.06 and recall 0.13 which is better than GLCM and Laws method respectively. Hence, the proposed model is also efficient for image retrieval.

Recall Recall measures the fraction of all the relevant documents in a collection that are retrieved by a specific query and similar to the concept of sensitivity. Here, recall is the number of figure captions that were indexed by a concept divided by the number of captions in which the concept was actually present.

No. of relevant images retrieved R (%) = × 100 -- (3.15) Total no. of relevant images in DB

263

Fig.4 Comparison Graph with Existing Model

INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.5 NO.2 FEBRUARY 2015 The fig.4 shows the pictorial representation of the evaluated performance of the image retrieval. By analyzing the obtained results the Proposed Model produces better results.

7. CONCLUSION In this paper, integrated model is extended for the edge based image retrieval. The feature sets of the nontextured images are generated with Distance edge orientation histogram sequences of the edge map and are stored in the feature database. The images are then retrieved from the image database with the edge orientation features. In order to achieve the proposed edge based image retrieval are been tested with different image databases. The results are compared with the existing methods.

[1]

[2]

[3]

[4]

[5]

[6]

[7]

[8]

[9]

[10]

[11]

[12]

8. REFERENCES Canny. J., (1986). “A computational approach to edge detection”. IEEE Trans. On Pattern Analysis and Machine Intelligence, vol. 8(6), pp. 679-698.

Chen. M.H., Lee. D., and Pavlidis. T., (1991).

“Residual analysis for feature detection”, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 13, pp. 30-40.

Ding. L., and Goshtasby. A., (2001). “On the Canny edge detector”. Pattern Recognition, vol. 34, pp. 721725.

Dong-Su Kim., Wang-Heon Lee., and In-So Kweon., (2004). “Automatic edge detection using (3 × 3) ideal binary pixel patterns and fuzzy-based edge thresholding”. Pattern Recogntion Letters, vol. 25, pp. 101-106.

Goshtasby. A., and Shyu. H-L., (1995). “Edge detection by curve fitting”, Image Vision Comput. vol. 13(3), pp. 169-177.

Grimson. W.E.L., and Pavlidis. T., (1985).

“Discontinuity detection for visual surface reconstruction”, Computer Vision, Graphics, Image Processing, vol. 30, pp. 316-330.

Hueckel. M., (1971). “An edge operator which locates edge in digital pictures”. Journal of ACM. vol. 18, pp. 113-125.

Krishnamoorthi. R., and Bhattacharya. P., (1998).

“Color edge extraction using orthogonal polynomials based zero crossing scheme”. Information Sciences, vol. 112, pp. 51-65.

Lee. D., Pavlidis T., and Huang. K., (1988). “Edge detection through residual analysis”. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 215-222.

Li. S.Z., (2000). “Roof-Edge Preserving Image Smoothing Based on MRFs”. Proceedings of IEEE Transactions on Image Processing, vol. 9(6), pp.

1134-1138.

Marr. D., and Hildreth. E. C., (1980). “Theory of edge detection”. Proceedings of Royal Society, vol.

207, pp. 187-217.

Pavlidis. T., and Lee. D., (1988). “Residual analysis for feature extraction”, in From Pixel to Features, J.C. Simon, Ed. Amsterdam, Proceedings of Workshop (COST13), pp. 219-227.

[13]

[14]

[15]

[16]

[17]

[18]

[19]

[20]

[21] [22]

[23]

[24]

264

Prewitt. J.M.S., (1970). “Object enhancement and extraction”. In: B.S. Lipkin and A. Rosenfield, eds., Picture Processing and Psychopictorics, Academic Press.

Qie. P., and Bhandarkar. and S.M., (1996). “An edge detection Technique using local smoothing and statistical hypothesis testing”. Pattern Recognition Letters, vol. 17(8), pp. 849-872.

Rakesh. R.R., Probal Chaudhuri., and Murthy. C.A., (2004). “Thresholding in Edge Detection: A Statistical Approach”. IEEE Transactions on Image Processing, vol. 13(7), pp. 927-936.

Roberts. L.G.,(1965). “Machine Perception of three dimensional solids”. J.T.Tipper Ed., Optical and Electro optical Information Processing.

Rosenfeld. A., (1981). “The Max Roberts operator is Hueckel-type of edge detectors”. IEEE Transactions on Pattern Analysis and Machine Intelligence. vol.

3(1), pp. 101-103.

Sarkar. S.Y., and Boyer. K.L., (1991). “Optimal infinite impulse response zero-crossing based edge detectors”, Computer Vision Graphics Image Processing: Image Understanding, vol. 54(9), pp.

224-243.

Shashank Mathur., and Anil Ahlawat., (2008).

“Application of Fuzzy Logic on Image Edge Detection”, Intelligent Technologies and Applications, pp. 24-28.

Shen. J., and Castan. S., (1992). “An optimal linear operator for step edge detection”, Graph Models Image Processing, vol. 54(1), pp. 112-133.

Sobel. I.E., (1970). “Camera models and machine perception”. Ph.D. Thesis, Stanford University.

Stern. D., and Kurz, L., (1988). “Edge detection in correlated noise using Latin squares models”. Pattern Recognition, vol. 21, pp. 119-129.

S. Pannirselvam and R. Krishnamoorthi(2009), “A New Texture Image Retrieval Scheme with Full Range Auto-Regressive (FRAR) Model”, International Journal of Soft Computing,pp. 229-235.

Santosh Kumar Vipparthi and Shyam Krishna Nagar (2014),"Color Directional Local Quinary Patterns for Content Based Indexing and Retrieval", Humancentric Computing and Information Sciences,pp.2-13.

@IJITCE Publication