Content-Based Image Retrieval of Web Surface Defects with PicSOM

Size: px
Start display at page:

Download "Content-Based Image Retrieval of Web Surface Defects with PicSOM"

Transcription

1 Content-Based Image Retrieval of Web Surface Defects with PicSOM Rami Rautkorpi and Jukka Iivarinen Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 54, FIN-25 HUT, Finland {rami.rautkorpi, Abstract This paper describes the application of PicSOM, a content-based image retrieval (CBIR) system based on selforganizing maps, on a defect image database containing 24 images from a web inspection system. Six feature descriptors from the MPEG-7 standard and an additional shape descriptor developed for surface defect images are used in the experiments. The classification performance of the descriptors is evaluated using K-Nearest Neighbor (KNN) leave-one-out cross-validation and PicSOM s built-in CBIR analysis system. The KNN results show good performance from three MPEG-7 descriptors and our shape descriptor. The CBIR results using these descriptors show that PicSOM s SOM-based indexing engine yields efficient and accurate retrieval of similar defect images from our database. I. INTRODUCTION The development of technology required to produce high quality digital images and the increasing capacity of digital data storage devices have made possible the creation of huge digital image databases. This in turn has necessitated the development of a system to efficiently manage and search such databases. Traditional text-based search methods can be applied to image databases, if the images in a database have been annotated by a human with keywords describing the content and nature of the images. However, this approach becomes unpractical as the size of the database increases. Also the annotations are subjective judgments by the annotator, which means that if several people are involved in annotating a single database, the annotations, and thus any search results, may be inconsistent, and thus the annotations may not reflect the needs of a particular end user of the database. A more efficient approach is content-based image retrieval (CBIR), where low level visual features are extracted from the images, stored and indexed in order to speed up searching [], [2]. The problem is to develop descriptors that capture the essential features of an image, and a system that makes it possible to match these features with the semantic concepts of content and significance that a human user sees in the images. One way to implement such capabilities in a system is the use of relevance feedback provided by the user, enabling the system to refine the search criteria according to the user s preferences. Web surface inspection systems produce large quantities of defect image data, and the classification of such defect images is a significant challenge for CBIR systems. Manual checking of all these defect images is too time-consuming, so some automatic tool is necessarily needed. In this paper we propose to use PicSOM[3], [4], a SOM-based CBIR system, to handle this task. In our previous work we have been dealing with defect images from a paper web inspection system[5], [6] but in this paper we deal with a new kind of defect images, namely metal defect images. So, experiments are conducted with a defect image database containing 24 images from a metal web inspection system. Six feature descriptors from the MPEG-7 standard [7], [8] and the additional shape descriptor developed for surface defect images [9] are first evaluated with a simple K-Nearest Neighbor (KNN) classifier. The best features are then implemented in PicSOM, and finally the retrieval performance of PicSOM is evaluated with these defect images. II. PICSOM RETRIEVAL SYSTEM PicSOM is a content-based image retrieval system for large, unannotated databases, developed at the Laboratory of Computer and Information Science at Helsinki University of Technology [3], [4]. It uses the self-organizing map (SOM) [] as a means of indexing feature data from images. The SOM provides not only an efficient indexing engine, but it also provides an automatic clustering of defect images that is very important in our case. This clustering can be used to reveal the main defect types and also to help to detect more rare defects. The retrieval process is implemented using relevance feedback. When training PicSOM, the first step is to calculate a number of features from the images in a database. These feature vectors are then used to train tree-structured SOMs (TS-SOM) []. The TS-SOM is a hierarchical structure that has a SOM at each level, with the map sizes increasing towards the bottom. The tree-structure speeds up the training and searching of the SOMs. After the training is complete, the distribution of the map units in the feature space reflects the distribution of the feature data. The feature vectors can then be associated with the nearest map unit in the feature space, i.e. the best matching unit (BMU). The maps in the TS-SOMs now serve as two-dimensional indexes to the feature data. The feature vectors that have the same BMU are very similar, and the map units surrounding the BMU represent less similar feature vectors. The division of the

2 map units into clusters in the feature space can be interpreted as a reflection of natural class divisions in the original image data. Searching in a database is iterative, beginning with the system presenting an initial set of images to the user, who can then select the images that best match the type of image that is being searched for. The system then assigns a positive relevance score to each map unit according to the number of selected images that have the unit as their BMU. A negative score is assigned to map units for all the images that were not selected by the user. The relevance values are then spread into the surrounding map units with low-pass filtering. Previously unseen images from the highest scoring map units are selected as candidates for the next phase. The scores of these images from each TS-SOM are summed, and the highest scoring images are shown on the next iteration. The selection process is repeated on each iteration, allowing the system to learn the search criteria based on the user s feedback. Since each TS-SOM is trained with a different feature, the relevance patterns on the maps are different. If the images selected by the user form a cluster in a certain map, the scores for the images in the associated units cumulate, resulting in the map unit, and thus the associated images, having a higher score than any unit in a map where the selections are spread out. This way the relative importance of each feature in the search is automatically weighted. The PicSOM user interface is depicted in Figure. On the top are the bottom levels of the four TS-SOMs (one for each feature set) and then the images selected by the user. Below these are the 2 best-matching images returned by PicSOM. III. FEATURE DESCRIPTORS A. The MPEG-7 standard descriptors The MPEG-7 standard, ISO/IEC 5938, formally named Multimedia Content Description Interface [2], [7], [8], provides standardized descriptions of streamed or stored images or video, to be used in searching, identifying, filtering and browsing images or video in various applications. The standard defines several still image descriptors. The descriptors used in this paper are: Color Layout (CL) specifies a spatial distribution of colors. The image is divided into 8 8blocks and the dominant colors are solved for each block in the YCbCr color system. Discrete Cosine Transform is applied to the dominant colors in each channel and the DCT coefficients are used as a descriptor. Color Structure (CS) slides a structuring element over the image. The numbers of positions where the element contains each particular color are stored and used as a descriptor. Scalable Color (SC) is a 256-color histogram in HSV color space, which is encoded by a Haar transform. Edge Histogram (EH) calculates the amount of vertical, horizontal, 45 degree, 35 degree and non-directional Fig.. The PicSOM user interface. edges in 6 sub-images of the picture, resulting in a total of 8 histogram bins. Homogeneous Texture (HT) filters the image with a bank of orientation and scale tuned filters that are modeled using Gabor functions. The first and second moments of the energy in the frequency domain in the corresponding sub-bands are then used as the components of the texture descriptor. Region-based Shape (RS) utilizes a set of 35 Angular Radial Transform (ART) coefficients that are calculated within a disk centered at the center of the image s Y channel. The descriptors were calculated using the MPEG-7 Experimentation Model (XM) software versions 5.5 and 5.6. B. The Simple Shape Descriptor The Simple Shape Descriptor (SSD) was developed for surface defect description in our earlier project [9]. It consists of several simple descriptors calculated from an object s contour. The descriptors are convexity, principal axis ratio, compactness, circular variance, elliptic variance, and angle. The descriptors are not very efficient individually, but the combination of them has been shown to produce good results with low computational costs [3].

3 Fig. 2. Example images from the metal database classes. A. The image database IV. EXPERIMENTS The image database contained 24 defect images from an online metal web inspection system. The database was preclassified into 4 different classes, with each class containing from up to 65 images. Example images from each class are shown in Figure 2. All images were gray-scale with 256 gray levels, dimensions ranging from less than pixels up to over pixels. Each image was supplied with a segmentation mask, indicating the defect areas to be distinguished from the surface background. The images and the segmentation masks were provided by ABB Oy. Some example images and their segmentation masks are shown in Figure 3. B. KNN leave-one-out cross-validation The performance of the descriptors was first evaluated with the K-Nearest Neighbor leave-one-out cross-validation. All calculations used Euclidean distances and a value of 5 for K. The results in Table I show that the best descriptor is Color Structure, at an overall success rate of 63%, taken as an average weighted with the number of images in each class. The next best descriptors are Edge Histogram (49%), Homogeneous Texture (57%) and the Simple Shape Descriptor (42%). The remaining features performed considerably more poorly, with success rates less than 32%. The effects of using several descriptors in the classification were evaluated by determining the classes of the 5 nearest neighbors for each descriptor and choosing the classification according to the class with the largest total number of occurrences. Using all seven descriptors in the classification increased the performance considerably, with the overall success rate being 76%, which is 3% more than with the best individual descriptor, Color Structure. Using only the four best descriptors achieved the same overall classification rate, so the remaining descriptors were excluded from further experiments. C. CBIR performance The image retrieval performance of PicSOM was evaluated using a built-in testing system, which emulates a human user making queries and giving feedback on the retrieved images in order to find images belonging to a specific class. The results are recall and precision values for each iteration of image retrieval. is the percentage of images belonging to the desired class that have been retrieved so far. A recall of % means that all desired images have been found. Precision is the percentage of desired images from all the images retrieved so far. Precision should be higher than the a priori probability of the desired class, otherwise the system s

4 Fig. 3. Example images and their segmentation masks from the metal database. The numbers are corresponding class labels. TABLE I KNN CLASSIFICATION RESULTS Classification success rates (%) of classes avg CS HT EH SSD SC CL RS All best best retrieval performance is worse than random selection. Figure 4 shows precision/recall graphs for the metal defect database, illustrating the retrieval performance as the query progresses. The average graph shown is a result of calculating for each iteration the weighted average of the precision and recall values over all classes. All three graphs show an increase in precision at the beginning of the query, which reflects the system s ability to refine the search based on relevance feedback from the user. After this, the precision stays relatively stable, until a significant portion of the desired images has been retrieved. The easy class exhibits this behavior very clearly. Precision stays above 8% until almost % of the desired images have been retrieved, and then slopes down very abruptly. Typically the phases of the process are not so clearly defined, as is seen in the smoothly curving graphs for the difficult class and the average over all classes. Figure 5 shows recall/iteration graphs for the metal defect database. The graphs show how the system is able to retrieve the most relevant results very efficiently in the first few iterations. The last few remaining images in the desired class are typically very hard to retrieve. Since 2 images are retrieved on each iteration, and nearly all classes have between 4 and 6 images, an ideal system would achieve % recall after 8 iterations. Thus examining the system s recall values at 8 iterations gives a good idea of the system s retrieval performance. Using more iterations will improve the results, but not in proportion to the number of additional iterations. Figure 6 shows the recall values at 8 and 6 iterations for each class and as a weighted average over all classes. On the average 62% recall is achieved after 8 iterations. The differences in performance among the classes are consistent with the results of the KNN crossvalidation tests. Using the additional 8 iterations increases recall approximately 25%. V. CONCLUSIONS A content-based image retrieval system called PicSOM was applied to a database consisting of defect images obtained from a real metal web inspection system. The MPEG-7 descriptors Color Structure, Edge Histogram, and Homogeneous Texture, and our own Simple Shape Descriptor were used as features. Their goodness was determined with the KNN classifications. These four feature sets were then implemented in PicSOM. The CBIR experiments showed that the SOMbased indexing engine of PicSOM was able to retrieve similar defect images accurately and efficiently from our database. The obtained recall and precision values show good performance that is also comparable to the ones obtained with a simple KNN classifier.

5 Easy class (4) Difficult class (8) Average Precision.. Fig. 4. Precision/recall graphs using the four best features.. Fig iterations 6 iterations avg Classes s at 8 and 6 iterations using the four best features.. Easy class (4) Difficult class (8) Average Iterations Fig. 5. /iteration graphs using the four best features. ACKNOWLEDGMENTS The authors wish to thank Mr J. Pakkanen and the Pic- SOM group (J. Laaksonen, M. Koskela, E. Oja) at Helsinki University of Technology, and our industrial partner ABB Oy (J. Rauhamaa). The financial support of the Technology Development Centre of Finland (TEKES s grant 42/3) is gratefully acknowledged. REFERENCES [] Y. Rui, T. S. Huang, and S.-F. Chang, Image retrieval: Current techniques, promising directions, and open issues, J. of Visual Communication and Image Representation, vol., no., pp , 999. [2] A. Del Bimbo, Visual Information Retrieval. Morgan Kaufmann Publishers, Inc., 999. [3] J. Laaksonen, M. Koskela, S. Laakso, and E. Oja, PicSOM - contentbased image retrieval with self-organizing maps, Pattern Recognition Letters, vol. 2, no. 3-4, pp , 2. [4], Self-organising maps as a relevance feedback technique in content-based image retrieval, Pattern Analysis and Applications, vol. 4, no. 2+3, pp. 4 52, 2. [5] J. Iivarinen, J. Pakkanen, and J. Rauhamaa, Content-based image retrieval in surface inspection, in Proceedings of 7th International Conference on Control, Automation, Robotics and Vision, Singapore, Dec , pp [6] J. Pakkanen, A. Ilvesmäki, and J. Iivarinen, Defect image classification and retrieval with MPEG-7 descriptors, in Proceedings of the 3th Scandinavian Conference on Image Analysis, ser. LNCS 2749, J. Bigun and T. Gustavsson, Eds. Göteborg, Sweden: Springer-Verlag, June 29 July 2 23, pp [7] MPEG-7, MPEG-7 visual part of the experimentation model (version 9.), ISO/IEC JTC/SC29/WG N394, 2. [8], MPEG-7 multimedia content description interface part 3 visual, ISO/IEC JTC/SC29/WG W373, 2. [9] J. Iivarinen and A. Visa, An adaptive texture and shape based defect classification, in Proceedings of the 4th International Conference on Pattern Recognition, vol. I, Brisbane, Australia, Aug , pp [] T. Kohonen, Self-Organizing Maps. Berlin: Springer-Verlag, 995. [] P. Koikkalainen and E. Oja, Self-organizing hierarchical feature maps, in Proceedings of 99 International Joint Conference on Neural Networks, vol. II, San Diego, CA, 99, pp [2] B. S. Manjunath, J.-R. Ohm, V. V. Vasudevan, and A. Yamada, Color and texture descriptors, IEEE Transactions on Circuits and Systems for Video Technology, vol., no. 6, June 2. [3] J. Iivarinen, M. Peura, J. Särelä, and A. Visa, Comparison of combined shape descriptors for irregular objects, in Proceedings of the 8th British Machine Vision Conference, vol. 2, University of Essex, UK, Sept , pp

By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Jussi Pakkanen and Jukka Iivarinen, A Novel Self Organizing Neural Network for Defect Image Classification. In Proceedings of the International Joint Conference on Neural Networks, pages 2553 2558, Budapest,

More information

Evaluation of Features for Defect Image Retrieval

Evaluation of Features for Defect Image Retrieval Evaluation of Features for Defect Image Retrieval Jukka Iivarinen, Antti Ilvesmäki, and Jussi Pakkanen Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400, FIN-02015

More information

DEFECT IMAGE CLASSIFICATION WITH MPEG-7 DESCRIPTORS. Antti Ilvesmäki and Jukka Iivarinen

DEFECT IMAGE CLASSIFICATION WITH MPEG-7 DESCRIPTORS. Antti Ilvesmäki and Jukka Iivarinen DEFECT IMAGE CLASSIFICATION WITH MPEG-7 DESCRIPTORS Antti Ilvesmäki and Jukka Iivarinen Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400, FIN-02015 HUT, Finland

More information

Self-Organizing Maps of Web Link Information

Self-Organizing Maps of Web Link Information Self-Organizing Maps of Web Link Information Sami Laakso, Jorma Laaksonen, Markus Koskela, and Erkki Oja Laboratory of Computer and Information Science Helsinki University of Technology P.O. Box 5400,

More information

An efficiency comparison of two content-based image retrieval systems, GIFT and PicSOM

An efficiency comparison of two content-based image retrieval systems, GIFT and PicSOM An efficiency comparison of two content-based image retrieval systems, GIFT and Mika Rummukainen, Jorma Laaksonen, and Markus Koskela Laboratory of Computer and Information Science, Helsinki University

More information

Image Theft Detection with Self-Organising Maps

Image Theft Detection with Self-Organising Maps Image Theft Detection with Self-Organising Maps Philip Prentis, Mats Sjöberg, Markus Koskela, and Jorma Laaksonen Czech Technical University in Prague, Helsinki University of Technology prentphi@fjfi.cvut.cz,

More information

VC 11/12 T14 Visual Feature Extraction

VC 11/12 T14 Visual Feature Extraction VC 11/12 T14 Visual Feature Extraction Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos Miguel Tavares Coimbra Outline Feature Vectors Colour Texture

More information

CONTENT-BASED RETRIEVAL OF DEFECT IMAGES. Jukka Iivarinen and Jussi Pakkanen

CONTENT-BASED RETRIEVAL OF DEFECT IMAGES. Jukka Iivarinen and Jussi Pakkanen Proceeings of ACIVS 2002 (Avance Concepts for Intelligent Vision Systems), Ghent, Belgium, September 9-11, 2002 CONTENT-BASED RETRIEVAL OF DEFECT IMAGES Jukka Iivarinen an Jussi Pakkanen jukka.iivarinen@hut.fi,

More information

PicSOM Self-Organizing Image Retrieval With MPEG-7 Content Descriptors

PicSOM Self-Organizing Image Retrieval With MPEG-7 Content Descriptors IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 13, NO. 4, JULY 2002 841 PicSOM Self-Organizing Image Retrieval With MPEG-7 Content Descriptors Jorma Laaksonen, Associate Member, IEEE, Markus Koskela, and Erkki

More information

Analysis of Semantic Information Available in an Image Collection Augmented with Auxiliary Data

Analysis of Semantic Information Available in an Image Collection Augmented with Auxiliary Data Analysis of Semantic Information Available in an Image Collection Augmented with Auxiliary Data Mats Sjöberg, Ville Viitaniemi, Jorma Laaksonen, and Timo Honkela Adaptive Informatics Research Centre, Helsinki

More information

APPLYING TEXTURE AND COLOR FEATURES TO NATURAL IMAGE RETRIEVAL

APPLYING TEXTURE AND COLOR FEATURES TO NATURAL IMAGE RETRIEVAL APPLYING TEXTURE AND COLOR FEATURES TO NATURAL IMAGE RETRIEVAL Mari Partio, Esin Guldogan, Olcay Guldogan, and Moncef Gabbouj Institute of Signal Processing, Tampere University of Technology, P.O.BOX 553,

More information

Binary Histogram in Image Classification for Retrieval Purposes

Binary Histogram in Image Classification for Retrieval Purposes Binary Histogram in Image Classification for Retrieval Purposes Iivari Kunttu 1, Leena Lepistö 1, Juhani Rauhamaa 2, and Ari Visa 1 1 Tampere University of Technology Institute of Signal Processing P.

More information

A Miniature-Based Image Retrieval System

A Miniature-Based Image Retrieval System A Miniature-Based Image Retrieval System Md. Saiful Islam 1 and Md. Haider Ali 2 Institute of Information Technology 1, Dept. of Computer Science and Engineering 2, University of Dhaka 1, 2, Dhaka-1000,

More information

ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN

ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN THE SEVENTH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV 2002), DEC. 2-5, 2002, SINGAPORE. ADAPTIVE TEXTURE IMAGE RETRIEVAL IN TRANSFORM DOMAIN Bin Zhang, Catalin I Tomai,

More information

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map

Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map Texture Classification by Combining Local Binary Pattern Features and a Self-Organizing Map Markus Turtinen, Topi Mäenpää, and Matti Pietikäinen Machine Vision Group, P.O.Box 4500, FIN-90014 University

More information

Automatic Image Annotation by Classification Using Mpeg-7 Features

Automatic Image Annotation by Classification Using Mpeg-7 Features International Journal of Scientific and Research Publications, Volume 2, Issue 9, September 2012 1 Automatic Image Annotation by Classification Using Mpeg-7 Features Manjary P.Gangan *, Dr. R. Karthi **

More information

COMPARISON OF SOME CONTENT-BASED IMAGE RETRIEVAL SYSTEMS WITH ROCK TEXTURE IMAGES

COMPARISON OF SOME CONTENT-BASED IMAGE RETRIEVAL SYSTEMS WITH ROCK TEXTURE IMAGES COMPARISON OF SOME CONTENT-BASED IMAGE RETRIEVAL SYSTEMS WITH ROCK TEXTURE IMAGES Leena Lepistö 1, Iivari Kunttu 1, Jorma Autio 2, and Ari Visa 1 1 Tampere University of Technology, Institute of Signal

More information

Image retrieval based on bag of images

Image retrieval based on bag of images University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2009 Image retrieval based on bag of images Jun Zhang University of Wollongong

More information

Efficient Image Retrieval Using Indexing Technique

Efficient Image Retrieval Using Indexing Technique Vol.3, Issue.1, Jan-Feb. 2013 pp-472-476 ISSN: 2249-6645 Efficient Image Retrieval Using Indexing Technique Mr.T.Saravanan, 1 S.Dhivya, 2 C.Selvi 3 Asst Professor/Dept of Computer Science Engineering,

More information

Locating 1-D Bar Codes in DCT-Domain

Locating 1-D Bar Codes in DCT-Domain Edith Cowan University Research Online ECU Publications Pre. 2011 2006 Locating 1-D Bar Codes in DCT-Domain Alexander Tropf Edith Cowan University Douglas Chai Edith Cowan University 10.1109/ICASSP.2006.1660449

More information

animals apes (1) NEW OR CONTINUED QUERY (2) CALLS (3) RETURNS THE CONTROL FILE (4) (7) RETURNS IMAGES BROWSER (6) REQUESTS IMAGES (5) HTML PAGE

animals apes (1) NEW OR CONTINUED QUERY (2) CALLS (3) RETURNS THE CONTROL FILE (4) (7) RETURNS IMAGES BROWSER (6) REQUESTS IMAGES (5) HTML PAGE published in the Proceedings of SCIA 99, Kangerlussuaq, Greenland, June 1999 available at PicSOM A Framework for Content-Based Image Database Retrieval

More information

Content-based Image Retrieval (CBIR)

Content-based Image Retrieval (CBIR) Content-based Image Retrieval (CBIR) Content-based Image Retrieval (CBIR) Searching a large database for images that match a query: What kinds of databases? What kinds of queries? What constitutes a match?

More information

Color-Based Classification of Natural Rock Images Using Classifier Combinations

Color-Based Classification of Natural Rock Images Using Classifier Combinations Color-Based Classification of Natural Rock Images Using Classifier Combinations Leena Lepistö, Iivari Kunttu, and Ari Visa Tampere University of Technology, Institute of Signal Processing, P.O. Box 553,

More information

Color Content Based Image Classification

Color Content Based Image Classification Color Content Based Image Classification Szabolcs Sergyán Budapest Tech sergyan.szabolcs@nik.bmf.hu Abstract: In content based image retrieval systems the most efficient and simple searches are the color

More information

Sketch Based Image Retrieval Approach Using Gray Level Co-Occurrence Matrix

Sketch Based Image Retrieval Approach Using Gray Level Co-Occurrence Matrix Sketch Based Image Retrieval Approach Using Gray Level Co-Occurrence Matrix K... Nagarjuna Reddy P. Prasanna Kumari JNT University, JNT University, LIET, Himayatsagar, Hyderabad-8, LIET, Himayatsagar,

More information

Image Retrieval Based on its Contents Using Features Extraction

Image Retrieval Based on its Contents Using Features Extraction Image Retrieval Based on its Contents Using Features Extraction Priyanka Shinde 1, Anushka Sinkar 2, Mugdha Toro 3, Prof.Shrinivas Halhalli 4 123Student, Computer Science, GSMCOE,Maharashtra, Pune, India

More information

MPEG-7 Visual shape descriptors

MPEG-7 Visual shape descriptors MPEG-7 Visual shape descriptors Miroslaw Bober presented by Peter Tylka Seminar on scientific soft skills 22.3.2012 Presentation Outline Presentation Outline Introduction to problem Shape spectrum - 3D

More information

Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval

Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval Pattern Analysis & Applications (2001)4:140 152 2001 Springer-Verlag London Limited Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval Jorma Laaksonen, Markus Koskela,

More information

2. LITERATURE REVIEW

2. LITERATURE REVIEW 2. LITERATURE REVIEW CBIR has come long way before 1990 and very little papers have been published at that time, however the number of papers published since 1997 is increasing. There are many CBIR algorithms

More information

Differential Compression and Optimal Caching Methods for Content-Based Image Search Systems

Differential Compression and Optimal Caching Methods for Content-Based Image Search Systems Differential Compression and Optimal Caching Methods for Content-Based Image Search Systems Di Zhong a, Shih-Fu Chang a, John R. Smith b a Department of Electrical Engineering, Columbia University, NY,

More information

Analyzing Low-Level Visual Features Using Content-Based Image Retrieval

Analyzing Low-Level Visual Features Using Content-Based Image Retrieval published in the Proceedings of ICONIP 2000, Taejon, Korea, November 2000 available at nalyzing Low-Level Visual Features Using Content-Based Image

More information

Content Based Image Retrieval Using Curvelet Transform

Content Based Image Retrieval Using Curvelet Transform Content Based Image Retrieval Using Curvelet Transform Ishrat Jahan Sumana, Md. Monirul Islam, Dengsheng Zhang and Guojun Lu Gippsland School of Information Technology, Monash University Churchill, Victoria

More information

COLOR AND SHAPE BASED IMAGE RETRIEVAL

COLOR AND SHAPE BASED IMAGE RETRIEVAL International Journal of Computer Science Engineering and Information Technology Research (IJCSEITR) ISSN 2249-6831 Vol.2, Issue 4, Dec 2012 39-44 TJPRC Pvt. Ltd. COLOR AND SHAPE BASED IMAGE RETRIEVAL

More information

Texture. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors

Texture. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors. Frequency Descriptors Texture The most fundamental question is: How can we measure texture, i.e., how can we quantitatively distinguish between different textures? Of course it is not enough to look at the intensity of individual

More information

Autoregressive and Random Field Texture Models

Autoregressive and Random Field Texture Models 1 Autoregressive and Random Field Texture Models Wei-Ta Chu 2008/11/6 Random Field 2 Think of a textured image as a 2D array of random numbers. The pixel intensity at each location is a random variable.

More information

Statistical Shape Features for Content-Based Image Retrieval

Statistical Shape Features for Content-Based Image Retrieval Journal of Mathematical Imaging and Vision 17: 187 198, 2002 c 2002 Kluwer Academic Publishers. Manufactured in The Netherlands. Statistical Shape Features for Content-Based Image Retrieval SAMI BRANDT

More information

Fusing MPEG-7 visual descriptors for image classification

Fusing MPEG-7 visual descriptors for image classification Fusing MPEG-7 visual descriptors for image classification Evaggelos Spyrou 1, Hervé Le Borgne 2, Theofilos Mailis 1, Eddie Cooke 2, Yannis Avrithis 1, and Noel O Connor 2 1 Image, Video and Multimedia

More information

Content Based Image Retrieval

Content Based Image Retrieval Content Based Image Retrieval R. Venkatesh Babu Outline What is CBIR Approaches Features for content based image retrieval Global Local Hybrid Similarity measure Trtaditional Image Retrieval Traditional

More information

Multiresolution Texture Analysis of Surface Reflection Images

Multiresolution Texture Analysis of Surface Reflection Images Multiresolution Texture Analysis of Surface Reflection Images Leena Lepistö, Iivari Kunttu, Jorma Autio, and Ari Visa Tampere University of Technology, Institute of Signal Processing P.O. Box 553, FIN-330

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

Improved Image Retrieval Using Visual Sorting and Semi-Automatic Semantic Categorization of Images

Improved Image Retrieval Using Visual Sorting and Semi-Automatic Semantic Categorization of Images Improved Image Retrieval Using Visual Sorting and Semi-Automatic Semantic Categorization of Images Kai Uwe Barthel, Sebastian Richter, Anuj Goyal and Andreas Follmann FHTW Berlin, Treskowallee 8, 10313

More information

A Graph Theoretic Approach to Image Database Retrieval

A Graph Theoretic Approach to Image Database Retrieval A Graph Theoretic Approach to Image Database Retrieval Selim Aksoy and Robert M. Haralick Intelligent Systems Laboratory Department of Electrical Engineering University of Washington, Seattle, WA 98195-2500

More information

AN EFFICIENT BATIK IMAGE RETRIEVAL SYSTEM BASED ON COLOR AND TEXTURE FEATURES

AN EFFICIENT BATIK IMAGE RETRIEVAL SYSTEM BASED ON COLOR AND TEXTURE FEATURES AN EFFICIENT BATIK IMAGE RETRIEVAL SYSTEM BASED ON COLOR AND TEXTURE FEATURES 1 RIMA TRI WAHYUNINGRUM, 2 INDAH AGUSTIEN SIRADJUDDIN 1, 2 Department of Informatics Engineering, University of Trunojoyo Madura,

More information

Similarity Image Retrieval System Using Hierarchical Classification

Similarity Image Retrieval System Using Hierarchical Classification Similarity Image Retrieval System Using Hierarchical Classification Experimental System on Mobile Internet with Cellular Phone Masahiro Tada 1, Toshikazu Kato 1, and Isao Shinohara 2 1 Department of Industrial

More information

Color Local Texture Features Based Face Recognition

Color Local Texture Features Based Face Recognition Color Local Texture Features Based Face Recognition Priyanka V. Bankar Department of Electronics and Communication Engineering SKN Sinhgad College of Engineering, Korti, Pandharpur, Maharashtra, India

More information

Texture Analysis of Painted Strokes 1) Martin Lettner, Paul Kammerer, Robert Sablatnig

Texture Analysis of Painted Strokes 1) Martin Lettner, Paul Kammerer, Robert Sablatnig Texture Analysis of Painted Strokes 1) Martin Lettner, Paul Kammerer, Robert Sablatnig Vienna University of Technology, Institute of Computer Aided Automation, Pattern Recognition and Image Processing

More information

An Efficient Semantic Image Retrieval based on Color and Texture Features and Data Mining Techniques

An Efficient Semantic Image Retrieval based on Color and Texture Features and Data Mining Techniques An Efficient Semantic Image Retrieval based on Color and Texture Features and Data Mining Techniques Doaa M. Alebiary Department of computer Science, Faculty of computers and informatics Benha University

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK REVIEW ON CONTENT BASED IMAGE RETRIEVAL BY USING VISUAL SEARCH RANKING MS. PRAGATI

More information

Practical Image and Video Processing Using MATLAB

Practical Image and Video Processing Using MATLAB Practical Image and Video Processing Using MATLAB Chapter 18 Feature extraction and representation What will we learn? What is feature extraction and why is it a critical step in most computer vision and

More information

An Introduction to Content Based Image Retrieval

An Introduction to Content Based Image Retrieval CHAPTER -1 An Introduction to Content Based Image Retrieval 1.1 Introduction With the advancement in internet and multimedia technologies, a huge amount of multimedia data in the form of audio, video and

More information

Evaluation of Different Metrics for Shape Based Image Retrieval Using a New Contour Points Descriptor

Evaluation of Different Metrics for Shape Based Image Retrieval Using a New Contour Points Descriptor Evaluation of Different Metrics for Shape Based Image Retrieval Using a New Contour Points Descriptor María-Teresa García Ordás, Enrique Alegre, Oscar García-Olalla, Diego García-Ordás University of León.

More information

Perimeter and Area Estimations of Digitized Objects with Fuzzy Borders

Perimeter and Area Estimations of Digitized Objects with Fuzzy Borders Perimeter and Area Estimations of Digitized Objects with Fuzzy Borders Nataša Sladoje,, Ingela Nyström, and Punam K. Saha 2 Centre for Image Analysis, Uppsala, Sweden {natasa,ingela}@cb.uu.se 2 MIPG, Dept.

More information

Contextual priming for artificial visual perception

Contextual priming for artificial visual perception Contextual priming for artificial visual perception Hervé Guillaume 1, Nathalie Denquive 1, Philippe Tarroux 1,2 1 LIMSI-CNRS BP 133 F-91403 Orsay cedex France 2 ENS 45 rue d Ulm F-75230 Paris cedex 05

More information

A Content Based Image Retrieval System Based on Color Features

A Content Based Image Retrieval System Based on Color Features A Content Based Image Retrieval System Based on Features Irena Valova, University of Rousse Angel Kanchev, Department of Computer Systems and Technologies, Rousse, Bulgaria, Irena@ecs.ru.acad.bg Boris

More information

IJESRT. Scientific Journal Impact Factor: (ISRA), Impact Factor: [82] [Thakur, 4(2): February, 2015] ISSN:

IJESRT. Scientific Journal Impact Factor: (ISRA), Impact Factor: [82] [Thakur, 4(2): February, 2015] ISSN: IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY A PSEUDO RELEVANCE BASED IMAGE RETRIEVAL MODEL Kamini Thakur*, Ms. Preetika Saxena M.Tech, Computer Science &Engineering, Acropolis

More information

Evaluation of MPEG7 Color Descriptors for Visual Surveillance Retrieval

Evaluation of MPEG7 Color Descriptors for Visual Surveillance Retrieval Evaluation of MPEG7 Descriptors for Visual Surveillance Retrieval James Annesley, James Orwell, John-Paul Renno Digital Imaging Research Center, Kingston University, Kingston-upon-Thames, Surrey, UK. {james.annesley,

More information

Automatic annotation of digital photos

Automatic annotation of digital photos University of Wollongong Research Online University of Wollongong Thesis Collection 1954-2016 University of Wollongong Thesis Collections 2007 Automatic annotation of digital photos Wenbin Shao University

More information

Content-Based Image Retrieval Readings: Chapter 8:

Content-Based Image Retrieval Readings: Chapter 8: Content-Based Image Retrieval Readings: Chapter 8: 8.1-8.4 Queries Commercial Systems Retrieval Features Indexing in the FIDS System Lead-in to Object Recognition 1 Content-based Image Retrieval (CBIR)

More information

CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS

CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS CIRCULAR MOIRÉ PATTERNS IN 3D COMPUTER VISION APPLICATIONS Setiawan Hadi Mathematics Department, Universitas Padjadjaran e-mail : shadi@unpad.ac.id Abstract Geometric patterns generated by superimposing

More information

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR)

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 63 CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 4.1 INTRODUCTION The Semantic Region Based Image Retrieval (SRBIR) system automatically segments the dominant foreground region and retrieves

More information

Get High Precision in Content-Based Image Retrieval using Combination of Color, Texture and Shape Features

Get High Precision in Content-Based Image Retrieval using Combination of Color, Texture and Shape Features Get High Precision in Content-Based Image Retrieval using Combination of Color, Texture and Shape Features 1 Mr. Rikin Thakkar, 2 Ms. Ompriya Kale 1 Department of Computer engineering, 1 LJ Institute of

More information

Dominant colour extraction in DCT domain

Dominant colour extraction in DCT domain Image and Vision Computing 24 (2006) 1269 1277 www.elsevier.com/locate/imavis Dominant colour extraction in DCT domain Jianmin Jiang a,b, *, Ying Weng b, PengJie Li c a Southwest University, China b University

More information

An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback

An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback An Improved CBIR Method Using Color and Texture Properties with Relevance Feedback MS. R. Janani 1, Sebhakumar.P 2 Assistant Professor, Department of CSE, Park College of Engineering and Technology, Coimbatore-

More information

Latest development in image feature representation and extraction

Latest development in image feature representation and extraction International Journal of Advanced Research and Development ISSN: 2455-4030, Impact Factor: RJIF 5.24 www.advancedjournal.com Volume 2; Issue 1; January 2017; Page No. 05-09 Latest development in image

More information

Classification Method for Colored Natural Textures Using Gabor Filtering

Classification Method for Colored Natural Textures Using Gabor Filtering Classiication Method or Colored Natural Textures Using Gabor Filtering Leena Lepistö 1, Iivari Kunttu 1, Jorma Autio 2, and Ari Visa 1, 1 Tampere University o Technology Institute o Signal Processing P.

More information

Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features

Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features 1 Kum Sharanamma, 2 Krishnapriya Sharma 1,2 SIR MVIT Abstract- To describe the image features the Local binary pattern (LBP)

More information

An Efficient Approach for Color Pattern Matching Using Image Mining

An Efficient Approach for Color Pattern Matching Using Image Mining An Efficient Approach for Color Pattern Matching Using Image Mining * Manjot Kaur Navjot Kaur Master of Technology in Computer Science & Engineering, Sri Guru Granth Sahib World University, Fatehgarh Sahib,

More information

Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang

Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang Lecture 6: Multimedia Information Retrieval Dr. Jian Zhang NICTA & CSE UNSW COMP9314 Advanced Database S1 2007 jzhang@cse.unsw.edu.au Reference Papers and Resources Papers: Colour spaces-perceptual, historical

More information

ANovel Approach to Collect Training Images from WWW for Image Thesaurus Building

ANovel Approach to Collect Training Images from WWW for Image Thesaurus Building ANovel Approach to Collect Training Images from WWW for Image Thesaurus Building Joohyoun Park and Jongho Nang Dept. of Computer Science and Engineering Sogang University Seoul, Korea {parkjh, jhnang}@sogang.ac.kr

More information

Fusing MPEG-7 visual descriptors for image classification

Fusing MPEG-7 visual descriptors for image classification Fusing MPEG-7 visual descriptors for image classification Evaggelos Spyrou 1, Hervé Le Borgne 2, Theofilos Mailis 1, Eddie Cooke 2, Yannis Avrithis 1, and Noel O Connor 2 1 Image, Video and Multimedia

More information

FEATURE EXTRACTION TECHNIQUES FOR IMAGE RETRIEVAL USING HAAR AND GLCM

FEATURE EXTRACTION TECHNIQUES FOR IMAGE RETRIEVAL USING HAAR AND GLCM FEATURE EXTRACTION TECHNIQUES FOR IMAGE RETRIEVAL USING HAAR AND GLCM Neha 1, Tanvi Jain 2 1,2 Senior Research Fellow (SRF), SAM-C, Defence R & D Organization, (India) ABSTRACT Content Based Image Retrieval

More information

Content Based Image Retrieval (CBIR) Using Segmentation Process

Content Based Image Retrieval (CBIR) Using Segmentation Process Content Based Image Retrieval (CBIR) Using Segmentation Process R.Gnanaraja 1, B. Jagadishkumar 2, S.T. Premkumar 3, B. Sunil kumar 4 1, 2, 3, 4 PG Scholar, Department of Computer Science and Engineering,

More information

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Abstract Automatic linguistic indexing of pictures is an important but highly challenging problem for researchers in content-based

More information

Efficient Content Based Image Retrieval System with Metadata Processing

Efficient Content Based Image Retrieval System with Metadata Processing IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 10 March 2015 ISSN (online): 2349-6010 Efficient Content Based Image Retrieval System with Metadata Processing

More information

Journal of Asian Scientific Research FEATURES COMPOSITION FOR PROFICIENT AND REAL TIME RETRIEVAL IN CBIR SYSTEM. Tohid Sedghi

Journal of Asian Scientific Research FEATURES COMPOSITION FOR PROFICIENT AND REAL TIME RETRIEVAL IN CBIR SYSTEM. Tohid Sedghi Journal of Asian Scientific Research, 013, 3(1):68-74 Journal of Asian Scientific Research journal homepage: http://aessweb.com/journal-detail.php?id=5003 FEATURES COMPOSTON FOR PROFCENT AND REAL TME RETREVAL

More information

Efficient Indexing and Searching Framework for Unstructured Data

Efficient Indexing and Searching Framework for Unstructured Data Efficient Indexing and Searching Framework for Unstructured Data Kyar Nyo Aye, Ni Lar Thein University of Computer Studies, Yangon kyarnyoaye@gmail.com, nilarthein@gmail.com ABSTRACT The proliferation

More information

An Implementation on Histogram of Oriented Gradients for Human Detection

An Implementation on Histogram of Oriented Gradients for Human Detection An Implementation on Histogram of Oriented Gradients for Human Detection Cansın Yıldız Dept. of Computer Engineering Bilkent University Ankara,Turkey cansin@cs.bilkent.edu.tr Abstract I implemented a Histogram

More information

Content-Based Image Retrieval Readings: Chapter 8:

Content-Based Image Retrieval Readings: Chapter 8: Content-Based Image Retrieval Readings: Chapter 8: 8.1-8.4 Queries Commercial Systems Retrieval Features Indexing in the FIDS System Lead-in to Object Recognition 1 Content-based Image Retrieval (CBIR)

More information

Content based Image Retrieval Using Multichannel Feature Extraction Techniques

Content based Image Retrieval Using Multichannel Feature Extraction Techniques ISSN 2395-1621 Content based Image Retrieval Using Multichannel Feature Extraction Techniques #1 Pooja P. Patil1, #2 Prof. B.H. Thombare 1 patilpoojapandit@gmail.com #1 M.E. Student, Computer Engineering

More information

CHAPTER 6 PROPOSED HYBRID MEDICAL IMAGE RETRIEVAL SYSTEM USING SEMANTIC AND VISUAL FEATURES

CHAPTER 6 PROPOSED HYBRID MEDICAL IMAGE RETRIEVAL SYSTEM USING SEMANTIC AND VISUAL FEATURES 188 CHAPTER 6 PROPOSED HYBRID MEDICAL IMAGE RETRIEVAL SYSTEM USING SEMANTIC AND VISUAL FEATURES 6.1 INTRODUCTION Image representation schemes designed for image retrieval systems are categorized into two

More information

Fuzzy Hamming Distance in a Content-Based Image Retrieval System

Fuzzy Hamming Distance in a Content-Based Image Retrieval System Fuzzy Hamming Distance in a Content-Based Image Retrieval System Mircea Ionescu Department of ECECS, University of Cincinnati, Cincinnati, OH 51-3, USA ionescmm@ececs.uc.edu Anca Ralescu Department of

More information

Content Based Image Retrieval Using Color and Texture Feature with Distance Matrices

Content Based Image Retrieval Using Color and Texture Feature with Distance Matrices International Journal of Scientific and Research Publications, Volume 7, Issue 8, August 2017 512 Content Based Image Retrieval Using Color and Texture Feature with Distance Matrices Manisha Rajput Department

More information

Content Based Image Retrieval Using Combined Color & Texture Features

Content Based Image Retrieval Using Combined Color & Texture Features IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) e-issn: 2278-1676,p-ISSN: 2320-3331, Volume 11, Issue 6 Ver. III (Nov. Dec. 2016), PP 01-05 www.iosrjournals.org Content Based Image Retrieval

More information

International Journal of Modern Trends in Engineering and Research e-issn No.: , Date: 2-4 July, 2015

International Journal of Modern Trends in Engineering and Research   e-issn No.: , Date: 2-4 July, 2015 International Journal of Modern Trends in Engineering and Research www.ijmter.com e-issn No.:2349-9745, Date: 2-4 July, 2015 SKETCH BASED IMAGE RETRIEVAL Prof. S. B. Ambhore¹, Priyank Shah², Mahendra Desarda³,

More information

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION Panca Mudjirahardjo, Rahmadwati, Nanang Sulistiyanto and R. Arief Setyawan Department of Electrical Engineering, Faculty of

More information

ECE 176 Digital Image Processing Handout #14 Pamela Cosman 4/29/05 TEXTURE ANALYSIS

ECE 176 Digital Image Processing Handout #14 Pamela Cosman 4/29/05 TEXTURE ANALYSIS ECE 176 Digital Image Processing Handout #14 Pamela Cosman 4/29/ TEXTURE ANALYSIS Texture analysis is covered very briefly in Gonzalez and Woods, pages 66 671. This handout is intended to supplement that

More information

LECTURE 4: FEATURE EXTRACTION DR. OUIEM BCHIR

LECTURE 4: FEATURE EXTRACTION DR. OUIEM BCHIR LECTURE 4: FEATURE EXTRACTION DR. OUIEM BCHIR RGB COLOR HISTOGRAM HSV COLOR MOMENTS hsv_image = rgb2hsv(rgb_image) converts the RGB image to the equivalent HSV image. RGB is an m-by-n-by-3 image array

More information

An Accurate Method for Skew Determination in Document Images

An Accurate Method for Skew Determination in Document Images DICTA00: Digital Image Computing Techniques and Applications, 1 January 00, Melbourne, Australia. An Accurate Method for Skew Determination in Document Images S. Lowther, V. Chandran and S. Sridharan Research

More information

Image Retrieval Based on Quad Chain Code and Standard Deviation

Image Retrieval Based on Quad Chain Code and Standard Deviation Vol3 Issue12, December- 2014, pg 466-473 Available Online at wwwijcsmccom International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology

More information

COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS

COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS Toomas Kirt Supervisor: Leo Võhandu Tallinn Technical University Toomas.Kirt@mail.ee Abstract: Key words: For the visualisation

More information

Introduction to Similarity Search in Multimedia Databases

Introduction to Similarity Search in Multimedia Databases Introduction to Similarity Search in Multimedia Databases Tomáš Skopal Charles University in Prague Faculty of Mathematics and Phycics SIRET research group http://siret.ms.mff.cuni.cz March 23 rd 2011,

More information

Image Mining: frameworks and techniques

Image Mining: frameworks and techniques Image Mining: frameworks and techniques Madhumathi.k 1, Dr.Antony Selvadoss Thanamani 2 M.Phil, Department of computer science, NGM College, Pollachi, Coimbatore, India 1 HOD Department of Computer Science,

More information

Scalable Coding of Image Collections with Embedded Descriptors

Scalable Coding of Image Collections with Embedded Descriptors Scalable Coding of Image Collections with Embedded Descriptors N. Adami, A. Boschetti, R. Leonardi, P. Migliorati Department of Electronic for Automation, University of Brescia Via Branze, 38, Brescia,

More information

CONTENT BASED IMAGE RETRIEVAL SYSTEM USING IMAGE CLASSIFICATION

CONTENT BASED IMAGE RETRIEVAL SYSTEM USING IMAGE CLASSIFICATION International Journal of Research and Reviews in Applied Sciences And Engineering (IJRRASE) Vol 8. No.1 2016 Pp.58-62 gopalax Journals, Singapore available at : www.ijcns.com ISSN: 2231-0061 CONTENT BASED

More information

A FRAMEWORK FOR ANALYZING TEXTURE DESCRIPTORS

A FRAMEWORK FOR ANALYZING TEXTURE DESCRIPTORS A FRAMEWORK FOR ANALYZING TEXTURE DESCRIPTORS Timo Ahonen and Matti Pietikäinen Machine Vision Group, University of Oulu, PL 4500, FI-90014 Oulun yliopisto, Finland tahonen@ee.oulu.fi, mkp@ee.oulu.fi Keywords:

More information

Semantic Evaluation and Efficiency Comparison of the Edge Pixel Neighboring Histogram in Image retrieval

Semantic Evaluation and Efficiency Comparison of the Edge Pixel Neighboring Histogram in Image retrieval Semantic Evaluation and Efficiency Comparison of the Edge Pixel Neighboring Histogram in Image retrieval Abdolah Chalechale and Alfred Mertins School of Electrical, Computer and Telecommunications Engineering

More information

Bipartite Graph Partitioning and Content-based Image Clustering

Bipartite Graph Partitioning and Content-based Image Clustering Bipartite Graph Partitioning and Content-based Image Clustering Guoping Qiu School of Computer Science The University of Nottingham qiu @ cs.nott.ac.uk Abstract This paper presents a method to model the

More information

MULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIER

MULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIER MULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIER A.Shabbir 1, 2 and G.Verdoolaege 1, 3 1 Department of Applied Physics, Ghent University, B-9000 Ghent, Belgium 2 Max Planck Institute

More information

Automatic Segmentation of Semantic Classes in Raster Map Images

Automatic Segmentation of Semantic Classes in Raster Map Images Automatic Segmentation of Semantic Classes in Raster Map Images Thomas C. Henderson, Trevor Linton, Sergey Potupchik and Andrei Ostanin School of Computing, University of Utah, Salt Lake City, UT 84112

More information

ENHANCED GENERIC FOURIER DESCRIPTORS FOR OBJECT-BASED IMAGE RETRIEVAL

ENHANCED GENERIC FOURIER DESCRIPTORS FOR OBJECT-BASED IMAGE RETRIEVAL ENHANCED GENERIC FOURIER DESCRIPTORS FOR OBJECT-BASED IMAGE RETRIEVAL Dengsheng Zhang and Guojun Lu Gippsland School of Computing and Info Tech Monash University Churchill, Victoria 3842 dengsheng.zhang,

More information