(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No.

4, July 2010

Image Retrieval with Texture Features Extracted using Kekre’s Median Codebook Generation of Vector Quantization
Dr. H.B.Kekre
Sr. Professor, MPSTME, NMIMS Vileparle(W), Mumbai 400056, India hbkekre@yahoo.com

Sudeep D. Thepade
Ph.D. Scholar & Assistant Professor, MPSTME, NMIMS Vileparle(W), Mumbai 400-056, India
sudeepthepade@gamil.com

Tanuja K. Sarode
Ph.D. Scholar MPSTME, NMIMS Assistant Professor, TSEC, Mumbai 400-050, India tanuja_0123@yahoo.com

Vaishali Suryavanshi.
Lecturer, Thadomal Shahani Engg. College, Bandra (w), Mumbai 400-050, India
Vaishali.surya@gmail.com

Abstract—In this paper novel methods for image retrieval based on texture feature extraction using Vector Quantization (VQ) are proposed. We have used Linde-Buzo-Gray (LBG), and Kekre’s Median Codebook Generation (KMCG) algorithms for texture feature extraction. The image is first divided into blocks of size 2x2 pixels (each pixel with red, green and blue component). A training vector of dimensions 12 is created using this block. Collection of all such training vectors is a training set. To generate the texture feature vector of the image, LBG and KMCG algorithms are applied on the initial training set to obtain codebooks of size 16, 32, 64, 128, 256 and 512. These codebooks are considered as feature vectors for CBIR. Thus the codebook generation algorithms and five different codebook sizes per algorithm result in 12 proposed image retrieval techniques. The proposed image retrieval techniques are tested on generic image database respectively having 1000 images. Results are also compared with the Gray Level Co-occurance Matrix (GLCM) method. The proposed CBIR methods outperform GLCM with higher precision and recall values. KMCG based CBIR give performance improvement over LBG based CBIR. The performance of KMCG CBIR improves with increasing codebook size. Overall in all KMCG CBIR with codebook size 512 gives best results with higher precision and recall values for both databases. Keywords— CBIR, Vector Quantization, GLCM, LBG, KMCG

I.

INTRODUCTION (HEADING 1)

Technological advances in digital imaging, broadband networking, and data storage have motivated people to communicate and express by sharing images, video, and other forms of media online [1,3]. Although the problems of acquiring, storing and transmitting the images are well addressed, capabilities to manipulate, index, sort, filter, summarize, or search through image database lack maturity [31]. Modern image search engines [31, 37] retrieve the images based on their visual contents, commonly referred to as Content Based Image Retrieval (CBIR) systems [40]. CBIR systems have found applications in various fields like fabric and fashion design, interior design as panoramic views [17,18,32-35], art galleries [32], museums, architecture/engineering design [32], weather forecast, geographical information systems, remote sensing and

management of earth resources [38,39], scientific database management, medical imaging, trademark and copyright database management, the military, law enforcement and criminal investigations [25], intellectual property, picture archiving and communication systems, retailing and image search on the Internet. Typical CBIR systems can organize and retrieve images automatically by extracting some features such as color, texture, shape from images and looking for similar images which have similar feature [36, 37]. CBIR systems operate in two phases. In the first phase, feature extraction (FE), a set of features, called feature vector, is generated to accurately represent the content of each image in the database. A feature vector is much smaller in size than the original image [29, 30]. In the second phase, similarity measurement (SM), searching distance between the query image and each image in the database using their signatures is computed so that the most similar images can be retrieved [24,28]. A variety of feature extraction techniques have been developed. Color based feature extraction techniques include color histogram, color coherence vector, color moments,, circular ring histogram [4], BTC extensions [25, 28, 30]. Texture based feature extraction techniques such as co-occurance matrix [6], Fractals [5], Gabor filters [5], variations of wavelet transform [1], Kekre transform [17, 27, 39] have been widely used. Effort has been made in even to extend image retrieval methodologies using combination of color and texture as the case in [23] where Walshlet Pyramids are introduced. The synergy resulting from the combination of color and texture is demonstrated to be superior than using just color and texture [37, 38]. In section II texture feature extraction using GLCM and VQ based methods viz. LBG and KMCG are discussed. In section III, technique for image retrieval using vector quantization is proposed. Results and discussion are given in section IV and conclusions are presented in section V. II. TEXTURE FEATURE E XTRACTION METHODS

Texture is important component of human visual perception and can be effectively used for identifying different image

244

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

regions [1]. Compared with color and shape features, texture features indicate the shape distribution, better suits the macrostructure and microstructure of the images [5]. Texture representation methods can be classified into three categories, namely structural, statistical and multi-resolution filtering methods. The identification of specific textures in an image is achieved primarily by modeling texture as a two-dimensional gray level variation [6,37]. This two dimensional array is called as Gray level Co-occurance Matrix (GLCM). GLCM describes the frequency of one gray tone appearing in a specified spatial linear relationship with another gray tone, within the area under investigation. A. GLCM Method Normalized probability density Pij of the co-occurance matrices can be defined as follows: # {| ( x, y ), ( x + d , y + d ) |∈ S | f ( x, y ) = i, f ( x + d , y + d ) = j} (1) P (i , ) =
δ

Correlation: (COR)

COR =

∑∑ ijP (i − j) − µ
σx σy

x

µy

(5)

Where µ x, µy, σx, σy are the means and standard deviations of Px and Py respectively. Px is the sum of each row in cooccurance matrix. Py is the sum of each column in the cooccurance matrix. Thus we obtained ASM0 ASM 45 ASM 90 ASM 135

ENT0 ENT 45 ENT 90 ENT 135

COR0 COR45 COR90 COR135

CON0 CON45 CON90 CON135

j

#S

where x, y = 0,1,…..L-1 are the gray levels. S is set of pixel pairs which have certain relationship in the image. #S is the number of elements in S. Pδ(i,j) is the probability density that the first pixel has intensity value i and the second j, which are seperated by distance δ=(dx, dy). The GLCM is computed in four directions for δ=00, δ=450, δ=900, δ=1350. Based on the GLCM four statistical parameters energy, contrast, entropy and correlation are computed. Finally a feature vector is computed using the means and variances of all the parameters [8, 9]. The steps for texture feature extraction using GLCM are as given below 1. Separate the R,G, B planes of image. 2. Repeat steps 3-6 for each plane. 3. Compute four GLCM matrices (directions for δ=00, δ=450, δ=900, δ= 1350 ) as given by eq. (1) 4. For each GLCM matrix compute the statistical features Energy(Angular second moment), Entropy(ENT), Correlation(COR), Contrast(CON) [8,9] using the equations mentioned below: Energy: measures textural uniformity (i.e. pixel pairs repetitions).and can be given as Angular Second Moment (ASM) (2) ASM = P 2 (i, j)

Compute the feature vector using the means and variances of all the parameters. Thus, the feature vector f={µASM , µENT , µCOR , µCON , σASM ,σENT , σCOR , σCON } Where µ is mean and σ is variance of the parameters. B. VQ based methods Vector Quantization (VQ) [7-15] is an efficient technique for data compression [23]. VQ has been very popular in variety of research fields such as video-based event detection [26], image segmentation [19-22], speech data compression [23], CBIR [26,37,38] and face recognition [25]. VQ can be defined as the mapping function that maps kdimensional vector space to the finite set CB = { C1, C2, C3, . . .., CN}. The set CB is called codebook consisting of N number of codevectors and each codevector Ci = {ci1, ci2, ci3, ……, cik} is of dimension k. The key to VQ is the good codebook. This codebook is the signature/feature vector of the entire image and can be generated by employing various clustering techniques. The method most commonly used to generate codebook is the Linde-Buzo-Gray (LBG) algorithm [8]. The drawback of LBG algorithm is that the cluster elongation is -450 to 1350 horizontal axis in two dimensional cases. This results in inefficient clustering. Kekre’s Proportionate algorithm (KPE) removes the disadvantage of LBG [36]. However, LBG and KPE algorithms require heavy computations. Kekre’s Fast Codebook Generation algorithm (KFCG) [12,24,36] requires less errors and least time to generate codebook as compared to other algorithms, as it does not require computation of Euclidian distance [2,33]. To generate the codebook, the image is first divided into fixed size blocks, each forming a training vector Xi = (xi1, xi2, ……., xik ).The set of training vectors is a training set. This training set is initial cluster. The clustering algorithms like LBG, KPE, and KFCG etc are then applied on this initial cluster to generate the codebook of desired size. Below, LBG, KPE and KFCG algorithms for codebook generation are discussed.

∑∑

Contrast (CON): Contrast indicates the variance of the gray level . 2 (3)

CON= ∑∑(i − j) P(i, j)

Entropy (ENT) : This parameter measures the disorder of the image. For texturally uniform image, entropy is small.

ENT = − ∑∑ P(i, j) log[P(i, j)]

(4)

245

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

C. LBG Algorithm In this algorithm centroid is computed as the first codevector for the training set. Two vectors v1 & v2 are then generated by adding constant error to the codevector. Euclidean distances [2,33] as presented in equation 6, of all the training vectors are computed with vectors v1 & v2 and two clusters are formed based on nearest of v1 or v2. This procedure is repeated for every cluster. (6) n

ED=

∑(X
i=1

pi

− vqi )

2

where, Xpi and vqi are the training vector and codevectors respectively with size n. D. Kekre’s Median Codebook Generation algorithm (KMCG) The steps of KMCG algorithm can be explained as follows. • Image is divided into the windows of size 2x2 pixels (each pixel consisting of red, green and blue components). • These are put in a row to get 12 values per vector. Collection of these vectors is a training set. • The training set is sorted with respect to first column. The Median of the first column is used to divide the training set in two parts and the median vector is put in the codebook. Set the codebook size equal to 1. • Further each part is then separately sorted with respect to second column to get two median values and these two median vectors are put into the codebook. Set the codebook size equal to 2. • The process of sorting is repeated till codebook of desire size is obtained. Here quick sort algorithm is used. This algorithm takes least time to generate codebook, since Euclidean distance computation is not required. III. IMAGE RETRIEVAL USING VQ BASED TECHNIQUES

B. Query Execution For a given query image compute the feature vector using the proposed feature extraction technique. To retrieve the most similar images, compare the query feature vector with the feature vectors in database. This is done by computing the distance between the query feature vectors with those in feature vector database. Euclidian distance as given in equation (6) and correlation coefficient are most commonly used as similarity measure in CBIR [2, 36]. Here Euclidian distance is used as a similarity measure. As compared to GLCM method, this proposed method saves tremendous number of computations. Also the accuracy of the proposed VQ technique is much better than that of GLCM. IV. RESULTS AND DISCUSSIONS

The proposed CBIR techniques are implemented in Matlab 7.0 on Intel Core 2 Duo Processor T8100, 2.1 GHz, 2 GB RAM machine to obtain results. The sample image database is shown in Figure 1. The results are obtained on the general database consisting of 1000 images from 11 different categories (some of these are taken from [41]). To test the proposed method, from every class five query images are selected randomly. So in all 55 query images are used from general database. To check the performance of proposed technique we have used precision and recall. The standard definitions of these two measures are given by following equations.
Pr ecision =
Re call =

Number _ of _ relevant _ images _ retrieved Total _ number _ of _ images _ retrieved

(7) (8)

Number _ of _ relevant _ images _ retrieved Total _ number _ of _ relevent _ images _ in _ database

The crossover point of precision and recall acts as performance measure of CBIR technique. Higher value of precision-recall at crossover point indicates better performance of image retrieval method. For the image database, results are obtained using LBG and KMCG for the codebook of sizes 16x12, 32x12, 64x12, 128x12, 256x12 and 512x12.

Image retrieval based on content requires extraction of features of the image, matching these features with the features of the images in the database and retrieving the images with the most similar features. Here, paper discusses the feature extraction technique based on vector quantization. A. Proposed Feature Extraction Technique 1. Repeat steps 2-6 for each image in the image database. 2. Divide the image into blocks of size 2x2 (Each pixel having red, blue and green component, thus resulting in a vector of 12components per block) 3. Form the training set/ initial cluster from these vectors. 4. Compute the initial centroid of the cluster. 5. Obtain the codebook of desired size using LBG/KMCG algorithm. This codebook represents the feature vector/signature of the image. 6. Store the feature vector obtained in step 5 in the feature vector database.

Figure 1 sample database of 11 images by randomly selecting one image from each category from general image database

Figure 2 shows average precision and recall plotted against number of retrieved images for General image database with precision-recall crossover point value 0.273.

246

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

Figure 5 to figure 10 gives the comparison of crossover points of average precision and average recall values using LBGCBIR and KMCG-CBIR for codebook sizes 16 to 512 respectively. In all codebook sizes KMCG-CBIR outperforms the LBG-CBIR with higher precision and recall values.

Figure 2. Average Precision and Recall plotted against number of retrieved images for GLCM-CBIR of General image database

Figure 3 gives crossover points of average precision and average recall values of the LBG based CBIR techniques for all codebook sizes tested on generic image database. Here the codebook sizes 32 and 64 are better with highest crossover point value. The precision and recall curves of codebook size 32 are higher than other codebook sizes indicating better performance for LBG-CBIR. The crossover points of average precision and average recall values for KMCG based CBIR techniques with considered codebook sizes are shown in figure 4. Here codebook size 512 is giving best performance.

Figure 5. Comparison of Cross-over points of average precision and recall using LBG-CBIR and KMCG-CBIR for codebook size 16 of Generalimage database

Figure 6. Comparison of Cross-over points of average precision and recall using LBG-CBIR and KMCG-CBIR for codebook size 32 of Generalimage database Figure 3. Average Precision and Recall plotted against number of retrieved images for LBG-CBIR of General image database

Figure 7. Comparison of Cross-over points of average precision and recall using LBG-CBIR and KMCG-CBIR for codebook size 64 of Generalimage database Figure 4. Cross-over points of average precision and recall using KMCGCBIR for all considered codebook sizes of General image database

247

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

performs better than LBG-CBIR is reflected in the figure with higher precision nad recall values.

Figure 8. Comparison of Cross-over points of average precision and recall using LBG-CBIR and KMCG-CBIR for codebook size 128 of Generalimage database Figure 11. Comparison of average precision and recall using GLCM-CBIR, LBG-CBIR and KMCG-CBIR for codebook size 512 of Generalimage database

V Conclusion
The use of vector quantization codebooks as feature vectors for image retrieval is revisited in the paper. The paper used various codebook generation techniques such as of LindeBuzo-Gray (LBG) and newly proposed Kekre’s Median Codebook Generation (KMCG) algorithms for texture feature extraction. These codebooks extracted in sizes 16,32,64,128, 256 and 512 are used in proposed CBIR techniques. Thus two codebook generation algorithms and six different codebook sizes per algorithm result in 12 proposed image retrieval techniques. Results of the proposed CBIR techniques are also compared with the Gray Level Co-occurance Matrix (GLCM) method. The proposed CBIR methods outperform GLCM with higher precision and recall values, indicating better image retrieval. KMCG based CBIR give immense improvement over LBG based CBIR. In KMCG based CBIR the higher codebook size give better performance, proving the codebook size 512 to be the best. Overall in all codebook sizes KMCG gives best results with higher precision and recall values for both generic image database and COIL image database. The KMCG takes least time to form codebook (texture feature set) as compared to LBG. This proves that KMCG-CBIR gives not only better but also faster image retrieval.

Figure 9. Comparison of Cross-over points of average precision and recall using LBG-CBIR and KMCG-CBIR for codebook size 128 of Generalimage database

Figure 10. Comparison of Cross-over points of average precision and recall using LBG-CBIR and KMCG-CBIR for codebook size 512 of Generalimage database

Figure 11 gives comparison of average precision and average recall values of GLCM-CBIR with codebook generation based CBIR techniques with codebook size 512x12. Here the codebook generation based CBIR techniques are performing far better than GLCM-CBIR as indicated by higher average precision and recall values. Also the fact that KMCG-CBIR

REFERENCES [1] Sanjoy Kumar Saha, Amit Kumar Das, Bhabatosh Chanda, “ CBIR using Perception based Texture and Color Measures”, in Proc. of 17th International Conference on Pattern Recognition(ICPR’04), Vol. 2, Aug 2004. [2] H.B.Kekre, Sudeep D. Thepade, “Image Retrieval using Augmented Block Truncation Coding Techniques”, ACM International Conference on Advances in Computing, Communication and Control (ICAC3-2009), pp. 384-390, 23-24 Jan 2009, Fr. Conceicao Rodrigous COE, Mumbai. Is uploaded on online ACM portal.

248

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

[3] H.B.Kekre, Sudeep D. Thepade, “Appraise of SPIT Problem” , SPIT-IEEE Colloquium and International Conference, 04-05 Feb 2008 , Sardar Patel Institute of Technology, Andheri, Mumbai [4] Wang Xiaoling, “ A Novel Cicular Ring Histogram for Content-based Image Retrieval”, First International Workshop on Education Technology and Computer Science, 2009. [5] Xiaoyi Song, Yongjie Li, Wufan Chen,”A Textural Feature Based Image Retrieval Algorithm”, in Proc. of 4th Int. Conf. on Natural Computation, Oct. 2008. [6] Jing Zhang, Gui-li Li, Seok-wum He, “Texture-Based Image Retrieval By Edge Detection Matching GLCM ”, in Proc. of 10th International conference on High Performance Computing and Comm., Sept. 2008. [7] R. M. Gray, “Vector quantization”, IEEE ASSP Mag., pp.: 4-29, Apr. 1984. [8] Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Trans.Commun., vol. COM-28, no. 1, pp.: 84-95, 1980. [9] H.B.Kekre, Tanuja K. Sarode, “New Fast Improved Clustering Algorithm for Codebook Generation for Vector Quantization”, International Conference on Engineering Technologies and Applications in Engineering, Technology and Sciences, Computer Science Department, Saurashtra University, Rajkot, Gujarat. (India), Amoghsiddhi Education Society, Sangli, Maharashtra (India) , 13th – 14th January 2008. [10] H. B. Kekre, Tanuja K. Sarode, “New Fast Improved Codebook Generation Algorithm for Color Images using Vector Quantization,” International Journal of Engineering and Technology, vol.1, No.1, pp.: 67-77, September 2008. [11] H. B. Kekre, Tanuja K. Sarode, “Fast Codebook Generation Algorithm for Color Images using Vector Quantization,” International Journal of Computer Science and Information Technology, Vol. 1, No. 1, pp.: 7-12, Jan 2009. [12] H. B. Kekre, Tanuja K. Sarode, “An Efficient Fast Algorithm to Generate Codebook for Vector Quantization,” First International Conference on Emerging Trends in Engineering and Technology, ICETET-2008, held at Raisoni College of Engineering, Nagpur, India, pp.: 62- 67, 16-18 July 2008. Avaliable at IEEE Xplore. [13] H. B. Kekre, Tanuja K. Sarode, “Fast Codebook Generation Algorithm for Color Images using Vector Quantization,” International Journal of Computer Science and Information Technology, Vol. 1, No. 1, pp.: 7-12, Jan 2009. [14] H. B. Kekre, Tanuja K. Sarode, “Fast Codevector Search Algorithm for 3-D Vector Quantized Codebook”, WASET International Journal of cal Computer Information Science and Engineering (IJCISE), Volume 2, No. 4, pp.: 235-239, Fall 2008. Available: http://www.waset.org/ijcise.

[15] H. B. Kekre, Tanuja K. Sarode, “Fast Codebook Search Algorithm for Vector Quantization using Sorting Technique”, ACM International Conference on Advances in Computing, Communication and Control (ICAC3-2009), pp: 317-325, 23-24 Jan 2009, Fr. Conceicao Rodrigous College of Engg., Mumbai. Available on ACM portal. [16] Jim Z.C. Lai, Yi-Ching Liaw, and Julie Liu, “A fast VQ codebook generation algorithm using codeword displacement”, Pattern Recogn. vol. 41, no. 1, pp.: 315– 319, 2008. [17] H.B.Kekre, Sudeep D. Thepade, “Panoramic View Construction using Partial Images”, IEEE sponsored International Conference on Sensors, Signal Processing, Communication, Control and Instrumentation (SSPCCIN-2008) 03-05 Jan 2008,Vishwakarma Institute of Technology, Pune. [18] H.B.Kekre, Sudeep D. Thepade, “Vista creation using Picture Parts”, International Conference on Emerging and Applications in Engineering, Technologies Technology and Sciences (ICETAETS-2008), 12-13 Jan 2008, Held at Computer Science Dept., Saurashtra University, Rajkot, Gujarat. (India). [19] H. B. Kekre, Tanuja K. Sarode, Bhakti Raul, ”Color Image Segmentation using Kekre’s Fast Codebook Generation Algorithm Based on Energy Ordering Concept”, ACM International Conference on Advances in Computing, Communication and Control (ICAC32009), pp.: 357-362, 23-24 Jan 2009, Fr. Conceicao Rodrigous College of Engg., Mumbai. Available on ACM portal. [20] H. B. Kekre, Tanuja K. Sarode, Bhakti Raul, “Color Image Segmentation using Kekre’s Algorithm for Vector Quantization”, International Journal of Computer Science (IJCS), Vol. 3, No. 4, pp.: 287-292, Fall 2008. Available: http://www.waset.org/ijcs. [21] H. B. Kekre, Tanuja K. Sarode, Bhakti Raul, “Color Image Segmentation using Vector Quantization Techniques Based on Energy Ordering Concept” International Journal of Computing Science and Communication Technologies (IJCSCT) Volume 1, Issue 2, pp: 164-171, January 2009. [22] H. B. Kekre, Tanuja K. Sarode, Bhakti Raul, “Color Image Segmentation Using Vector Quantization Techniques”, Advances in Engineering Science Sect. C (3), pp.: 35-42, July-September 2008 [23] H. B. Kekre, Tanuja K. Sarode, “Speech Data Compression using Vector Quantization”, WASET International Journal of Computer and Information Science and Engineering (IJCISE), vol. 2, No. 4, pp.: 251-254, Fall 2008. available: http://www.waset.org/ijcise. [24] H. B. Kekre, Ms. Tanuja K. Sarode, Sudeep D. Thepade, “Image Retrieval using Color-Texture Features from DCT on VQ Codevectors obtained by Kekre’s Fast Codebook Generation”, ICGST-International Journal on Graphics, Vision and Image Processing (GVIP), Volume

249

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

[25]

[26]

[27]

[28]

[29]

[30]

[31]

[32]

[33]

9, Issue 5, pp.: 1-8, September 2009. Available online at http://www.icgst.com/gvip/Volume9/Issue5/P115092175 2.html H. B. Kekre, Kamal Shah, Tanuja K. Sarode, Sudeep D. Thepade, ”Performance Comparison of Vector Quantization Technique – KFCG with LBG, Existing Transforms and PCA for Face Recognition”, International Journal of Information Retrieval (IJIR), Vol. 02, Issue 1, pp.: 64-71, 2009. H.B.Kekre, Tanuja Sarode, Sudeep D. Thepade, “ColorTexture Feature based Image Retrieval using DCT applied on Kekre’s Median Codebook”, International Journal on Imaging (IJI), Volume 2, Number A09, Autumn 2009,pp. 55-65. Available online at www.ceser.res.in/iji.html (ISSN: 0974-0627). H.B.Kekre, Sudeep D. Thepade, “Image Retrieval using Non-Involutional Orthogonal Kekre’s Transform”, International Journal of Multidisciplinary Research and Advances in Engineering (IJMRAE), Ascent Publication House, 2009, Volume 1, No.I, 2009. Abstract available online at www.ascent-journals.com H.B.Kekre, Sudeep D. Thepade, “Color Based Image Retrieval using Amendment Block Truncation Coding with YCbCr Color Space”, International Journal on Imaging (IJI), Volume 2, Number A09, Autumn 2009, pp. 2-14. Available online at www.ceser.res.in/iji.html (ISSN: 0974-0627). H.B.Kekre, Sudeep D. Thepade, “Image Retrieval using Color-Texture Features Extracted from Walshlet Pyramid”, ICGST International Journal on Graphics, Vision and Image Processing (GVIP), Volume 10, Issue I, Feb.2010, pp.9-18, Available online www.icgst.com/gvip/Volume10/Issue1/P1150938876.ht ml H.B.Kekre, Sudeep D. Thepade, “Using YUV Color Space to Hoist the Performance of Block Truncation Coding for Image Retrieval”, In Proc. of IEEE International Advanced Computing Conference 2009 (IACC’09), Thapar University, Patiala, INDIA, 6-7 March 2009. H.B.Kekre, Sudeep D. Thepade, “Rendering Futuristic Image Retrieval System”, In Proc. of National Conference on Enhancements in Computer, Communication and Information Technology, EC2IT2009, 20-21 Mar 2009, K.J. Somaiya College of Engineering, Vidyavihar, Mumbai-77. H.B.Kekre, Sudeep D. Thepade, “Creating the Color Panoramic View using Medley of Grayscale and Color Partial Images ”, WASET International Journal of Electrical, Computer and System Engineering (IJECSE), Volume 2, No. 3, Summer 2008. Available online at www.waset.org/ijecse/v2/v2-3-26.pdf H.B.Kekre, Sudeep D. Thepade, “Rotation Invariant Fusion of Partial Images in Vista Creation”, WASET International Journal of Electrical, Computer and System Engineering (IJECSE), Volume 2, No. 2, Spring 2008.

[34]

[35]

[36]

[37]

[38]

[39]

[40]

[41] [42]

Available online at www.waset.org/ijecse/v2/v2-213.pdf H.B.Kekre, Sudeep D. Thepade, “Scaling Invariant Fusion of Image Pieces in Panorama Making and Novel Image Blending Technique”, International Journal on Imaging (IJI), Autumn 2008, Volume 1, No. A08, Available online at www.ceser.res.in/iji.html (ISSN: 0974-0627). H.B.Kekre, Sudeep D. Thepade, “Image Blending In Vista Creation using Kekre’s LUV Color Space” , SPIT IEEE Colloquium and International Conference, 04-05 Feb 2008, SPIT Andheri, Mumbai H.B.Kekre, Sudeep D. Thepade, Archana Athawale, Anant Shah, Prathmesh Verlekar, Suraj Shirke, “Performance Evaluation of Image Retrieval using Energy Compaction and Image Tiling over DCT Row Mean and DCT Column Mean”, Springer-International Conference on Contours of Computing Technology (Thinkquest-2010), Babasaheb Gawde Institute of Technology, Mumbai, 13-14 March 2010, The paper will be uploaded on online Springerlink. H.B.Kekre, Tanuja K. Sarode, Sudeep D. Thepade, Vaishali Suryavanshi,“Improved Texture Feature Based Image Retrieval using Kekre’s Fast Codebook Generation Algorithm”, Springer-International Conference on Contours of Computing Technology (Thinkquest-2010), Babasaheb Gawde Institute of Technology, Mumbai, 13-14 March 2010, The paper will be uploaded on online Springerlink. H.B.Kekre, Tanuja K. Sarode, Sudeep D. Thepade, “Image Retrieval by Kekre’s Transform Applied on Each Row of Walsh Transformed VQ Codebook”, (Invited), ACM-International Conference and Workshop on Emerging Trends in Technology (ICWET 2010),Thakur College of Engg. And Tech., Mumbai, 26-27 Feb 2010, The paper is invited at ICWET 2010. Also will be uploaded on online ACM Portal. H.B.Kekre, Sudeep D. Thepade, Archana Athawale, Anant Shah, Prathmesh Verlekar, Suraj Shirke,“Energy Compaction and Image Splitting for Image Retrieval using Kekre Transform over Row and Column Feature Vectors”, International Journal of Computer Science and Network Security (IJCSNS),Volume:10, Number 1, January 2010, (ISSN: 1738-7906) Available at www.IJCSNS.org. H.B.Kekre, Sudeep D. Thepade, Archana Athawale, Anant Shah, Prathmesh Verlekar, Suraj Shirke, “Walsh Transform over Row Mean and Column Mean using Image Fragmentation and Energy Compaction for Image Retrieval”, International Journal on Computer Science and Engineering (IJCSE),Volume 2S, Issue1, January 2010, (ISSN: 0975–3397). Available online at www.enggjournals.com/ijcse. (Last http://wang.ist.psu.edu/docs/related/Image.orig referred on 23 Sept 2008) S. Nene, S.Nayar, & H. Murase. Columbia object image library (COIL-100). Technical report, CUCS-006-96,

250

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

(IJCSIS) International Journal of Computer Science and Information Security, Vol. 8, No. 4, July 2010

Feb-1996-http://www1.cs.columbia.edu/CAVE/software /softlib/coil-100.php. Author Biographies
Dr. H. B. Kekre has received B.E. (Hons.) in Telecomm. Engineering. from Jabalpur University in 1958, M.Tech (Industrial Electronics) from IIT Bombay in 1960, M.S.Engg. (Electrical Engg.) from University of Ottawa in 1965 and Ph.D. (System Identification) from IIT Bombay in 1970 He has worked as Faculty of Electrical Engg. and then HOD Computer Science and Engg. at IIT Bombay. For 13 years he was working as a professor and head in the Department of Computer Engg. at Thadomal Shahani Engineering. College, Mumbai. Now he is Senior Professor at MPSTME, SVKM’s NMIMS. He has guided 17 Ph.Ds, more than 100 M.E./M.Tech and several B.E./ B.Tech projects. His areas of interest are Digital Signal processing, Image Processing and Computer Networking. He has more than 270 papers in National / International Conferences and Journals to his credit. He was Senior Member of IEEE. Presently He is Fellow of IETE and Life Member of ISTE Recently seven students working under his guidance have received best paper awards. Currently 10 research scholars are pursuing Ph.D. program under his guidance. Sudeep D. Thepade has Received B.E.(Computer) degree from North Maharashtra University with Distinction in 2003. M.E. in Computer Engineering from University of Mumbai in 2008 with Distinction, currently pursuing Ph.D. from SVKM’s NMIMS, Mumbai. He has more than 06 years of experience in teaching and industry. He was Lecturer in Dept. of Information Technology at Thadomal Shahani Engineering College, Bandra(w), Mumbai for nearly 04 years. Currently working as Assistant Professor in Computer Engineering at Mukesh Patel School of Technology Management and Engineering, SVKM’s NMIMS, Vile Parle(w), Mumbai, INDIA. He is member of International Association of Engineers (IAENG) and International Association of Computer Science and Information Technology (IACSIT), Singapore. His areas of interest are Image Processing and Computer Networks. He has about 69 papers in National/International Conferences/Journals to his credit with a Best Paper Award at International Conference SSPCCIN-2008 and Second Best Paper Award at ThinkQuest-2009 National Level paper presentation competition for faculty. Tanuja K. Sarode has Received M.E.(Computer Engineering) degree from Mumbai University in 2004, currently Pursuing Ph.D. from Mukesh Patel School of Technology, Management and Engg., SVKM’s NMIMS, Vile-Parle (W), Mumbai, INDIA. She has more than 10 years of experience in teaching. Currently working as Assistant Professor in Dept. of Computer Engineering at Thadomal Shahani Engineering College, Mumbai. She is life member of IETE, member of International Association of Engineers (IAENG) and International Association of Computer Science and Information Technology (IACSIT), Singapore. Her areas of interest are Image Processing, Signal Processing and Computer Graphics. She has 60 papers in National /International Conferences/journal to her credit. Vaishali Suryawanshi has received B.E (Computer Engineering) degree from North Maharashtra University in 2000. Currently she is pursuing her M.E. (Computer Engineering) from Thadomal Shahani Engineering College Mumbai. She is working as a lecturer in Thodomal Shahani Enginnering college and has 7 years of teaching experience.

251

http://sites.google.com/site/ijcsis/ ISSN 1947-5500

Sign up to vote on this title
UsefulNot useful