Image Database Modeling

Size: px
Start display at page:

Download "Image Database Modeling"

Transcription

1 Image Database Modeling Aibing Rao, Rohini Srihari Center of Excellence for Document Analysis and Recognition, State University of New York At Buffalo, Amherst, NY14228 arao, Abstract The performance of an indexing technique, namely, a system of feature extraction and similarity measure, is strongly related to the test bed in content-based image retrieval. A theoretical framework is proposed for image database modeling. The goal is to investigate the relationship between a given indexing technique and a given image database. As an analogy to the concept of perplexity of a text corpus, the complexity of an image database is introduced. This is a quantitative measure of the quality of an image database for the task of content access to the database. The complexity of an image database is an internal property of the database and can be used to distinguish the difficulty of different databases on which content access is to be performed. On the other hand, the measure can be used to compare the effectiveness of different indexing techniques with which content access is to be performed. Keywords: Content-Based Image Retrieval, Image Database Modeling, Complexity of Image Databases 1. Introduction There are a tremendous number of techniques for image retrieval nowadays[9, 11, 3, 10, 1, 12]. Lower-level feature extraction of images is extensively explored from the perspective of color, spatial layout, texture, shape, etc. The current state of image retrieval is chaotic in terms of evaluation: different researchers design different algorithms and then test the performance on their own databases. There is no test bed, and there is no theory about how to build such a benchmark. One of the main difficulties is to answer the fundamental question: What is an image database? What is an image database? People tend to call a collection of images an image database. Is it a database? According to Elmasri and Navathe [5], a database is a collection of related data. What is the relationship reflected in a collection of images? Without any indexing and classification being performed, there is no relationship among the images in the collection; hence, it is not a database. In order to make a collection of images look more like a database, the relationships of the images in the collection have to be explored. There are tremendous number of choices to define such relationships. For example, all of the existing content-based image retrieval techniques belong to such choices. In this paper, a much more naive way of exploring the relationship is adopted. In other words, the collection of images is considered as a whole and some properties of the collection ( the database ) are proposed in favor of image retrieval. The properties of the image database is assumed to be internal to the database and can be regarded as a characteristic of the database. This characteristic is a measure of the difficulty of the task of image retrieval to be performed on the database. Here, the difficulty of image retrieval is not with respect to a particular query example but with respect to general queries on average. In other words, the difficulty of image retrieval on the database is the average difficulty of answering all possible reasonable queries on the database. Therefore, it is independent of the selection of queries and is an internal property of the database. Srihari et al. [13] gave an experimental example of the different difficulty of applying the traditional color histogram matching on a database of images of scenery against a database of images with human activities. In the experiment, the technique is the same, but the performance greatly differs with each database. Obviously, some internal difference between those two databases gave rise to the different difficulties of the retrieval task. What are the constituents of a quantitative measure of the difficulty performing the retrieval task on a given database? The following aspects are the major considerations: Homogeneity Images from different clusters of the database are very similar. For example, a rose image database is more homogeneous than a flower image database. Heterogeneity Number of clusters of similar images in the database. Content Variety A description of different levels of the

2 complexity of the semantics of images in the database. For example, a human activity image database is more complex than a purely scenery image database. Cardinality Number of images in the database. A quantitative measure of the difficulty should encompass all these aspects. Such a measure is not a simple summation of these constituents because they are not orthogonal. For example, a database of 1000 copies of an image should bring the same difficulty to the retrieval task as should the database only consisting of the single image. Moreover, the properties of homogeneity and heterogeneity bring the inevitable difficulty in defining such a measure because they are paradoxical. The idea of the quest of a quantitative measure, called the content complexity of an image database, is partially motivated from the concept of perplexity of a test corpus in language modeling[6, 8]. The perplexity of a statistical model M, such as bigram, trigram, etc., on the actual probability distribution P of a text corpus is defined as 2 H(P;M) where H(P; M ) is the cross-entropy of M on P. This concept has two important implications: For a given text corpus, it measures how accurate the model M is in approximating the actual probability distribution P ; For a given language model M, it measures an internal property of different text corpus. In speech recognition, for a given model, the perplexity defined by the model is a crude measure of the average size of the set of words from which a recognizer would choose the next spoken word. Hence it is a measure of the degree of the difficulty of performing speech recognition with the text corpus using the given model. 2. Image Database Modeling: Properties of the Complexity of Image Databases The purpose of image database modeling is to provide a quantitative measure of the difficulties of performing image retrieval task on image databases. Let I be the universal image database which is the set of all images being considered. A model ' of I is a pair consisting of a feature extraction algorithm and an associated similarity measure: ' = (f; d) where f : I?! R n maps an image to a feature vector and d : R n R n?! R + is a distance measure of a pair of feature vectors, here R n is the vector space of dimension n consisting of all n-tuples of reals and R + is the set of all non-negative reals. Let F be the set of all models of I. A measure of the complexity of image databases (CID) is a mapping cid : 2 I F?! R + such that it satisfies (1). For 8' 2 F; 8D 1 ; D I, cid(d 1 [ D 2 ; ') cid(d 1 ; ') + cid(d 2 ; ') if D 1 \ D 2 = ;; (2). cid(d; ') cid(d; ) iff ' is more suitable in describing the semantic content of image database D than is. Condition (1) states that the complexity after merging two disjoint databases together is lower-bounded by the sum of each individual complexities. This assumption is reasonable because the union of two disjoint databases brings new spatial relationship between the components, in addition to the original complexity of each database. Moreover, this assumption implies that a larger image database should be more complex, corresponding to the fact that it is usually more difficult to find the right information from a larger pool of images, no matter what kind of model is used. In fact, suppose D 1 D 2, then D 1 = D 2 [ (D 1? D 2 ) so that cid(d 1 ; ') = cid(d 2 [ (D 1? D 2 ); ') cid(d 2 ; ') + cid(d 1? D 2 ; ') cid(d 2 ; ') Condition (2) states that an less effective algorithm imposes higher complexity on the same database than a more effective one does. Notice that these conditions are ideal and may not be achievable in reality. Since the mapping has two parameters, similar to the properties of the concept of perplexity as stated above, it implies two important aspects: When the model is pre-selected, the mapping is a function of database D and can be regarded as a property of the database. Therefore it can be used to compare two image databases in term of using the chosen model for image retrieval. Moreover, an optimal model can be defined by optimizing the complexity value as follows, cid(d) = min cid(d; ') '2F which suggests that the optimal model is the perfect one used for image retrieval on D. This optimized quantity is independent of the model and is a property of the database. It measures the difficulty of performing image retrieval on D. In reality, due to the limitation of the technology of content access to image data, it is impossible to solve this optimization problem. An approximation is made possible via cid(d) = min cid(d; ' k) 1kK

3 by carefully selecting a list of models f' 1 ; ' 2 ; :::; ' K g as a benchmark for the purpose of measuring the difficulty. On the other hand, for a given image database D, the mapping is a function of model ' and can used as guide to find the optimal model for the given database D. Moreover, it can be used as a measure for comparing the performance of different models. For example, in order to evaluate the performance of a group of algorithms designed for color histograms, assuming there is a benchmark consisting of K color image databases D 1 ; D 2 ; :::; D K, the performance of a color histogram model ' is measured by cid(') = 1 K KX k=1 cid(d k ; ') Next some ideas for implementing the quantitative measure are presented. 3. Query-Based and Clustering-Based Approaches If an image database is regarded as a black box where only query by example is allowed and the output of a list of similar images is guaranteed, then querying the database is extremely important for the outside world to comprehend the content inside the black box. This gives rise to the possibility of computing the content complexity of the black box based on queries. This is called a query-based approach. Second, if the image database is regarded as a database on which clustering can be performed, then the content complexity of the database can be computed by analyzing each of the clusters as well as the relationship among them. This is called a clustering-based approach. Third, if an image is regarded as a list of labels of pre-defined keyword subimages, then the content complexity of the database can be computed in a similar manner as in text domain[6]. This is called a template-based approach. 3.1 Query-Based Approach Given image database D and a model '. The feature extraction algorithm of the model maps each image in D to a feature vector. The structure of D can be understood by carefully designing a set of queries. Suppose Q = fq 1 ; q 2 ; :::; q N g be such a set of queries. For each query q i, using model ' to calculate the feature vector of q i and then calculating the similarity distance between this vector and the feature vector of each image in D. Sort D with respect to the distance values to get a permutation of D which represents the ranking list based on the similarity to the query. The evaluation value of the permutation is Pcalculated by the average precision which is defined as R 1 R i N i where R is the total number of similar images to q i in D and N i is the number of images retrieved at the point while the i th similar image is retrieved, or by the performance area[13] of the precision-recall graph, or by any of the measures discussed in Baeza-Yates and Ribiero-Neto[2]. Denote the value as p i, it represents how good the model performs for the query. In addition, a mapping u : I?! R + is needed to define the difficulty of the question itself. It assigns each image a value representing the content variety of the image. Now the relationship between the content complexity of the database D and the query q i is: if the question is difficult which means u(q i ) is high and the answer is good, then the complexity of the database is relatively lower because hard questions yet gives easy answers. Mathematically, a possible relation is 1? performance difficulty. By a technical modification to avoid nil denominator, take average over all of the queries to define cid(d; ') = 1? 1 N NX p i 1 + u(q i ) This formula somehow catches the properties presented in section 2, at least it is obvious true for condition (2) in the definition of section 2. Currently, the mapping u is defined to map an image to its entropy. The entropy of an image somehow represents the content variety of the image because it is the uncertainty of interpreting the image. In general, the mapping should also take the database on which the query is applied into account because the same image query could be an easy question on one database while it could be a hard question on another database. The great disadvantage of query-based approach is the difficulty of designing the set of queries. To compensate this disadvantage, the database itself is usually used as the required set of queries for the computation. In this case, the mapping u is nil because the measure now is queryindependent. However, this case requires the relevance judgements of the database. 3.2 Clustering-Based Approach Assume the image database D is clustered into M clusters under the model ', namely, D = M[ where D i is a cluster of similar images of D with respect to '. Obviously, the content complexity of D is related to each of D i as well as the relationship of the clusters. Therefore, cid(d; ') = MX D i cid(d i ; ') + ('; D 1 ; D 2 ; :::; D M ) (1)

4 where the second summand ('; D 1 ; D 2 ; :::; D M ) is a non-negative function describing the relationship of the clusters. Now the problem becomes two sub-problems: (1). How to define the content complexity of a similarity cluster; (2). How to define the function ('; D 1 ; D 2 ; :::; D M ), i.e. how to represent the relationship of M clusters. The complexity of one cluster For a given cluster D i, with the simplest model, it can be represented by the centroid C i and the radius. However, this is not enough. We introduce an important concept called the density distribution vector of D i, in a similar manner as in [7] by regarding D i as a pure geometric subset in the feature space. We quantize the enveloping disc of D i into T annular, or angular, or sectoral blocks and then count the number of points in each of the blocks in a specified order to get a vector = ( 1 ; 2 ; :::; T ) of dimension T. For more detail, please refer to [7]. This density distribution vector roughly describes the distribution state of the points of D i. Now the entropy H() of the density distribution [4] can be used to define the complexity of D i. Explicitly, set cid(d i ; ') = H() log 2 T + u(c i) (2) where the entropy H() is given by H() =? TX t=1 t jd i j log t 2 jd i j and u(c i ) is defined in above section. Here jd i j is the cardinality of set D i. Notice that a normalization is performed on the entropy summand because H() achieves maximal value log 2 T at the uniform distribution. The relationship of M clusters: ('; D 1 ; D 2 ; :::; D M ) At first, there is no relationship for only one cluster, hence ('; D) = 0 where D is a database consisting of only one cluster of similar images. Second, the relationship function should be symmetric, namely, for any permutation of f1; 2; :::; M g, ('; D 1 ; D 2 ; :::; D M ) = ('; D (1) ; D (2) ; :::; D (M) ) Third, the relationship among M clusters should be more complex than the relationship among any subset of these clusters, in other words, for any subset fi; j; :::; mg f1; 2; :::; Mg, ('; D 1 ; D 2 ; :::; D M ) ('; D i ; D j ; :::; D m ) The simplest candidate satisfying these two conditions is the average distance of the centroids of the clusters, i.e. P 1i<jM ('; D 1 ; D 2 ; :::; D d(c i; C j ) M ) = = P CM 2 2 1i<jM d(c i; C j ) M (M? 1) (3) where d(c i ; C j ) is the distance between the centroid C i of D i and the centroid C j of D j. Equations (1), (2) and (3) give the complete computation of the complexity of D under model ' by the clusteringbased approach. 3.3 Template-Based Approach A set of keyword subimages (templates) is pre-selected. Suppose all templates are designed as 4 4 subimages. Then there are possible templates if the color images have 24 bits per pixel. Obviously, directly using such a huge templates is not feasible because of the computer power. However, a reasonable set of templates can be selected. Suppose N (usually less than 10000) templates are selected in advance and are labeled with numbers from 1 to N. Now, given an image, compare each 4 subimage with the templates and find the most similar template whose label is recorded. By doing so, the image is now a list of labels of length S where S is the number of pixels of the image. 16 Hence, an image is a document which can be regarded as a list of keywords, just as a text document is a list of words. Then every concept regarding language modeling [6, 8] can be implanted to the image case. For each of the approaches described above, experimental results are to be provided later. 4. Application One important application of the concept introduced above is in the benchmarking of image retrieval systems. The concept of complexity of image database can be used to build a list of image databases on which the difficulty of the image retrieval task goes from the easiest to the most complex. It can also be used as a measure for the evaluation of a particular image retrieval algorithm. In the near future, it is predicted to play an similar role in image retrieval and image understanding as the role the language modeling plays in text retrieval and speech recognition. Furthermore, image database modeling itself has theoretical interest because it proposes a new point of view to manipulate an image database. In a more general sense, the problem itself may not be only restricted in image domain, it may be generalized to the general database. The methodology of regarding a database as an integrity on which some properties are to be derived is itself not nonsense. 5. Conclusion and Future Work We have introduced the important problem of image database modeling in content-based image retrieval and presented a theoretical framework, in parallel to the exist-

5 ing theory for language modeling. We have also investigated Some general properties of a measure of the content complexity of an image database. Two possible approach for the implementation such as query-based approach and clustering-based approach have been analyzed. It is still early to propose a satifiable necessary and sufficient condition for the measure of the complexity of an image database under a given model. In addition, we focused on the mathematical representation of our idea and paid less attention to the mathematical proof of these formulas. Our future work will focus on the modification of the theoretical framework and provide more concrete mathematical proof of the formulation. Moreover, extensive experiments are to be performed for the purpose of verification. [13] R. K. Srihari, Z. Zhang, and A. Rao. Image background search: Combining object detection techniques with content-based image retrieval(cbir) systems. Proceeding of IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL 99), in conjunction with IEEE CVPR 99, pages , June References [1] J. R. Bach, C. Fuller, A. Gupta, A. Hampapur, B. Horowitz, R. Humphrey, R. Jain, and C. Shu. The virage image search engine: An open framework for image management. Symposium on Electronic Imaging: Science and Technology Storage & Retrieval for Image and Video Databases IV, 2670:76 87, [2] R. Baeza-Yates and B. Ribiero-Neto. Modern Information Retrieval. Addison-Wesley, [3] R. Barber, M. Flickner, J. Hafner, W. Niblack, and D. Petkovic. Efficient and effective querying by image content. Journal of Intelligent Information Systems, 3: , [4] T. M. Cover and J. A. Thomas. Elements of Information Theory. John Wiley & Sons, Inc., New York, [5] R. Elmasri and S. Navathe. Fundamentals of Database Systems, Second Edition. Addison-Wesley, [6] F. Jelinek. Statistical Methods for Speech Recognition. The MIT Press, [7] A. Rao, R. K. Srihari, and Z. Zhang. Spatial color histograms for content-based image retrieval. Proceeding of IEEE International Conference on Tools with Artificial Intelligence, pages , November [8] R. Rosenfeld. Adaptive Statistical Language Modeling: A Maximum Entropy Approach. PhD thesis, Carnegie Mellon University, [9] Y. Rui, T. S. Huang, and S.-F. Chang. Image retrieval: Past, present and future. Journal of Visual Communication and Image Representation, 10:1 23, [10] J. Smith and S.-F. Chang. Visualseek: A fully automated content-based image query system. Proceeding ACM International Conference of Multimedia, pages 87 98, November [11] J. R. Smith. Integrated Spatial and Feature Image Systems: Retrieval, Analysis and Compression. PhD thesis, Columbia Univ., [12] R. K. Srihari and Z. Zhang. Finding pictures in context. Proc. of IAPR International Workshop on Multimedia Information Analysis & Retrieval, Springer-Verlag Press, pages , 1998.

Textural Features for Image Database Retrieval

Textural Features for Image Database Retrieval Textural Features for Image Database Retrieval Selim Aksoy and Robert M. Haralick Intelligent Systems Laboratory Department of Electrical Engineering University of Washington Seattle, WA 98195-2500 {aksoy,haralick}@@isl.ee.washington.edu

More information

Content Based Image Retrieval: Survey and Comparison between RGB and HSV model

Content Based Image Retrieval: Survey and Comparison between RGB and HSV model Content Based Image Retrieval: Survey and Comparison between RGB and HSV model Simardeep Kaur 1 and Dr. Vijay Kumar Banga 2 AMRITSAR COLLEGE OF ENGG & TECHNOLOGY, Amritsar, India Abstract Content based

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

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

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

Symbolic Evaluation of Sums for Parallelising Compilers

Symbolic Evaluation of Sums for Parallelising Compilers Symbolic Evaluation of Sums for Parallelising Compilers Rizos Sakellariou Department of Computer Science University of Manchester Oxford Road Manchester M13 9PL United Kingdom e-mail: rizos@csmanacuk Keywords:

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

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

Query-Sensitive Similarity Measure for Content-Based Image Retrieval

Query-Sensitive Similarity Measure for Content-Based Image Retrieval Query-Sensitive Similarity Measure for Content-Based Image Retrieval Zhi-Hua Zhou Hong-Bin Dai National Laboratory for Novel Software Technology Nanjing University, Nanjing 2193, China {zhouzh, daihb}@lamda.nju.edu.cn

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

A METHOD FOR CONTENT-BASED SEARCHING OF 3D MODEL DATABASES

A METHOD FOR CONTENT-BASED SEARCHING OF 3D MODEL DATABASES A METHOD FOR CONTENT-BASED SEARCHING OF 3D MODEL DATABASES Jiale Wang *, Hongming Cai 2 and Yuanjun He * Department of Computer Science & Technology, Shanghai Jiaotong University, China Email: wjl8026@yahoo.com.cn

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 Model of Machine Learning Based on User Preference of Attributes

A Model of Machine Learning Based on User Preference of Attributes 1 A Model of Machine Learning Based on User Preference of Attributes Yiyu Yao 1, Yan Zhao 1, Jue Wang 2 and Suqing Han 2 1 Department of Computer Science, University of Regina, Regina, Saskatchewan, Canada

More information

Holistic Correlation of Color Models, Color Features and Distance Metrics on Content-Based Image Retrieval

Holistic Correlation of Color Models, Color Features and Distance Metrics on Content-Based Image Retrieval Holistic Correlation of Color Models, Color Features and Distance Metrics on Content-Based Image Retrieval Swapnil Saurav 1, Prajakta Belsare 2, Siddhartha Sarkar 3 1Researcher, Abhidheya Labs and Knowledge

More information

Querying by Color Regions using the VisualSEEk Content-Based Visual Query System

Querying by Color Regions using the VisualSEEk Content-Based Visual Query System Querying by Color Regions using the VisualSEEk Content-Based Visual Query System John R. Smith and Shih-Fu Chang Center for Image Technology for New Media and Department of Electrical Engineering Columbia

More information

Frequent Inner-Class Approach: A Semi-supervised Learning Technique for One-shot Learning

Frequent Inner-Class Approach: A Semi-supervised Learning Technique for One-shot Learning Frequent Inner-Class Approach: A Semi-supervised Learning Technique for One-shot Learning Izumi Suzuki, Koich Yamada, Muneyuki Unehara Nagaoka University of Technology, 1603-1, Kamitomioka Nagaoka, Niigata

More information

Semantic Visual Templates: Linking Visual Features to Semantics

Semantic Visual Templates: Linking Visual Features to Semantics Semantic Visual Templates: Linking Visual Features to Semantics Shih-Fu Chang William Chen Hari Sundaram Dept. of Electrical Engineering Columbia University New York New York 10027. E-mail: fsfchang,bchen,sundaramg@ctr.columbia.edu

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

Color Image Segmentation

Color Image Segmentation Color Image Segmentation Yining Deng, B. S. Manjunath and Hyundoo Shin* Department of Electrical and Computer Engineering University of California, Santa Barbara, CA 93106-9560 *Samsung Electronics Inc.

More information

AN APPROXIMATION APPROACH FOR RANKING FUZZY NUMBERS BASED ON WEIGHTED INTERVAL - VALUE 1.INTRODUCTION

AN APPROXIMATION APPROACH FOR RANKING FUZZY NUMBERS BASED ON WEIGHTED INTERVAL - VALUE 1.INTRODUCTION Mathematical and Computational Applications, Vol. 16, No. 3, pp. 588-597, 2011. Association for Scientific Research AN APPROXIMATION APPROACH FOR RANKING FUZZY NUMBERS BASED ON WEIGHTED INTERVAL - VALUE

More information

A Combined Encryption Compression Scheme Using Chaotic Maps

A Combined Encryption Compression Scheme Using Chaotic Maps BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 13, No 2 Sofia 2013 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.2478/cait-2013-0016 A Combined Encryption Compression

More information

Exploring Similarity Measures for Biometric Databases

Exploring Similarity Measures for Biometric Databases Exploring Similarity Measures for Biometric Databases Praveer Mansukhani, Venu Govindaraju Center for Unified Biometrics and Sensors (CUBS) University at Buffalo {pdm5, govind}@buffalo.edu Abstract. Currently

More information

Texture Image Segmentation using FCM

Texture Image Segmentation using FCM Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Texture Image Segmentation using FCM Kanchan S. Deshmukh + M.G.M

More information

Image retrieval based on region shape similarity

Image retrieval based on region shape similarity Image retrieval based on region shape similarity Cheng Chang Liu Wenyin Hongjiang Zhang Microsoft Research China, 49 Zhichun Road, Beijing 8, China {wyliu, hjzhang}@microsoft.com ABSTRACT This paper presents

More information

TEVI: Text Extraction for Video Indexing

TEVI: Text Extraction for Video Indexing TEVI: Text Extraction for Video Indexing Hichem KARRAY, Mohamed SALAH, Adel M. ALIMI REGIM: Research Group on Intelligent Machines, EIS, University of Sfax, Tunisia hichem.karray@ieee.org mohamed_salah@laposte.net

More information

Spatial Color Indexing Using Data Clustering Technique

Spatial Color Indexing Using Data Clustering Technique Spatial Color Indexing Using Data Clustering Techniue P J Dutta, D K Bhattacharyya, M Dutta Department of Comp Sc & IT, Tezpur University, Napaam, India {pjd,dkb,malay}@tezu.ernet.in and J K Kalita Dept

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

Constructing Control Flow Graph for Java by Decoupling Exception Flow from Normal Flow

Constructing Control Flow Graph for Java by Decoupling Exception Flow from Normal Flow Constructing Control Flow Graph for Java by Decoupling Exception Flow from Normal Flow Jang-Wu Jo 1 and Byeong-Mo Chang 2 1 Department of Computer Engineering Pusan University of Foreign Studies Pusan

More information

A Novel Image Retrieval Method Using Segmentation and Color Moments

A Novel Image Retrieval Method Using Segmentation and Color Moments A Novel Image Retrieval Method Using Segmentation and Color Moments T.V. Saikrishna 1, Dr.A.Yesubabu 2, Dr.A.Anandarao 3, T.Sudha Rani 4 1 Assoc. Professor, Computer Science Department, QIS College of

More information

Identifying Layout Classes for Mathematical Symbols Using Layout Context

Identifying Layout Classes for Mathematical Symbols Using Layout Context Rochester Institute of Technology RIT Scholar Works Articles 2009 Identifying Layout Classes for Mathematical Symbols Using Layout Context Ling Ouyang Rochester Institute of Technology Richard Zanibbi

More information

Content Based Image Retrieval with Semantic Features using Object Ontology

Content Based Image Retrieval with Semantic Features using Object Ontology Content Based Image Retrieval with Semantic Features using Object Ontology Anuja Khodaskar Research Scholar College of Engineering & Technology, Amravati, India Dr. S.A. Ladke Principal Sipna s College

More information

Equivalence Detection Using Parse-tree Normalization for Math Search

Equivalence Detection Using Parse-tree Normalization for Math Search Equivalence Detection Using Parse-tree Normalization for Math Search Mohammed Shatnawi Department of Computer Info. Systems Jordan University of Science and Tech. Jordan-Irbid (22110)-P.O.Box (3030) mshatnawi@just.edu.jo

More information

Figure 1. Overview of a semantic-based classification-driven image retrieval framework. image comparison; and (3) Adaptive image retrieval captures us

Figure 1. Overview of a semantic-based classification-driven image retrieval framework. image comparison; and (3) Adaptive image retrieval captures us Semantic-based Biomedical Image Indexing and Retrieval Y. Liu a, N. A. Lazar b, and W. E. Rothfus c a The Robotics Institute Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA 15213, USA b Statistics

More information

TRANSFORM FEATURES FOR TEXTURE CLASSIFICATION AND DISCRIMINATION IN LARGE IMAGE DATABASES

TRANSFORM FEATURES FOR TEXTURE CLASSIFICATION AND DISCRIMINATION IN LARGE IMAGE DATABASES TRANSFORM FEATURES FOR TEXTURE CLASSIFICATION AND DISCRIMINATION IN LARGE IMAGE DATABASES John R. Smith and Shih-Fu Chang Center for Telecommunications Research and Electrical Engineering Department Columbia

More information

Indexing by Shape of Image Databases Based on Extended Grid Files

Indexing by Shape of Image Databases Based on Extended Grid Files Indexing by Shape of Image Databases Based on Extended Grid Files Carlo Combi, Gian Luca Foresti, Massimo Franceschet, Angelo Montanari Department of Mathematics and ComputerScience, University of Udine

More information

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM 1 PHYO THET KHIN, 2 LAI LAI WIN KYI 1,2 Department of Information Technology, Mandalay Technological University The Republic of the Union of Myanmar

More information

6. Concluding Remarks

6. Concluding Remarks [8] K. J. Supowit, The relative neighborhood graph with an application to minimum spanning trees, Tech. Rept., Department of Computer Science, University of Illinois, Urbana-Champaign, August 1980, also

More information

One-Point Geometric Crossover

One-Point Geometric Crossover One-Point Geometric Crossover Alberto Moraglio School of Computing and Center for Reasoning, University of Kent, Canterbury, UK A.Moraglio@kent.ac.uk Abstract. Uniform crossover for binary strings has

More information

then assume that we are given the image of one of these textures captured by a camera at a different (longer) distance and with unknown direction of i

then assume that we are given the image of one of these textures captured by a camera at a different (longer) distance and with unknown direction of i Image Texture Prediction using Colour Photometric Stereo Xavier Lladó 1, Joan Mart 1, and Maria Petrou 2 1 Institute of Informatics and Applications, University of Girona, 1771, Girona, Spain fllado,joanmg@eia.udg.es

More information

Improving the Efficiency of Fast Using Semantic Similarity Algorithm

Improving the Efficiency of Fast Using Semantic Similarity Algorithm International Journal of Scientific and Research Publications, Volume 4, Issue 1, January 2014 1 Improving the Efficiency of Fast Using Semantic Similarity Algorithm D.KARTHIKA 1, S. DIVAKAR 2 Final year

More information

Efficient, Scalable, and Provenance-Aware Management of Linked Data

Efficient, Scalable, and Provenance-Aware Management of Linked Data Efficient, Scalable, and Provenance-Aware Management of Linked Data Marcin Wylot 1 Motivation and objectives of the research The proliferation of heterogeneous Linked Data on the Web requires data management

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

Triangle Graphs and Simple Trapezoid Graphs

Triangle Graphs and Simple Trapezoid Graphs JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 18, 467-473 (2002) Short Paper Triangle Graphs and Simple Trapezoid Graphs Department of Computer Science and Information Management Providence University

More information

IMPROVING THE PERFORMANCE OF CONTENT-BASED IMAGE RETRIEVAL SYSTEMS WITH COLOR IMAGE PROCESSING TOOLS

IMPROVING THE PERFORMANCE OF CONTENT-BASED IMAGE RETRIEVAL SYSTEMS WITH COLOR IMAGE PROCESSING TOOLS IMPROVING THE PERFORMANCE OF CONTENT-BASED IMAGE RETRIEVAL SYSTEMS WITH COLOR IMAGE PROCESSING TOOLS Fabio Costa Advanced Technology & Strategy (CGISS) Motorola 8000 West Sunrise Blvd. Plantation, FL 33322

More information

Toward Part-based Document Image Decoding

Toward Part-based Document Image Decoding 2012 10th IAPR International Workshop on Document Analysis Systems Toward Part-based Document Image Decoding Wang Song, Seiichi Uchida Kyushu University, Fukuoka, Japan wangsong@human.ait.kyushu-u.ac.jp,

More information

IMPROVING THE RELEVANCY OF DOCUMENT SEARCH USING THE MULTI-TERM ADJACENCY KEYWORD-ORDER MODEL

IMPROVING THE RELEVANCY OF DOCUMENT SEARCH USING THE MULTI-TERM ADJACENCY KEYWORD-ORDER MODEL IMPROVING THE RELEVANCY OF DOCUMENT SEARCH USING THE MULTI-TERM ADJACENCY KEYWORD-ORDER MODEL Lim Bee Huang 1, Vimala Balakrishnan 2, Ram Gopal Raj 3 1,2 Department of Information System, 3 Department

More information

Texture Segmentation by Windowed Projection

Texture Segmentation by Windowed Projection Texture Segmentation by Windowed Projection 1, 2 Fan-Chen Tseng, 2 Ching-Chi Hsu, 2 Chiou-Shann Fuh 1 Department of Electronic Engineering National I-Lan Institute of Technology e-mail : fctseng@ccmail.ilantech.edu.tw

More information

ROUGH MEMBERSHIP FUNCTIONS: A TOOL FOR REASONING WITH UNCERTAINTY

ROUGH MEMBERSHIP FUNCTIONS: A TOOL FOR REASONING WITH UNCERTAINTY ALGEBRAIC METHODS IN LOGIC AND IN COMPUTER SCIENCE BANACH CENTER PUBLICATIONS, VOLUME 28 INSTITUTE OF MATHEMATICS POLISH ACADEMY OF SCIENCES WARSZAWA 1993 ROUGH MEMBERSHIP FUNCTIONS: A TOOL FOR REASONING

More information

Flexible Coloring. Xiaozhou Li a, Atri Rudra b, Ram Swaminathan a. Abstract

Flexible Coloring. Xiaozhou Li a, Atri Rudra b, Ram Swaminathan a. Abstract Flexible Coloring Xiaozhou Li a, Atri Rudra b, Ram Swaminathan a a firstname.lastname@hp.com, HP Labs, 1501 Page Mill Road, Palo Alto, CA 94304 b atri@buffalo.edu, Computer Sc. & Engg. dept., SUNY Buffalo,

More information

Time Stamp Detection and Recognition in Video Frames

Time Stamp Detection and Recognition in Video Frames Time Stamp Detection and Recognition in Video Frames Nongluk Covavisaruch and Chetsada Saengpanit Department of Computer Engineering, Chulalongkorn University, Bangkok 10330, Thailand E-mail: nongluk.c@chula.ac.th

More information

Semantic Website Clustering

Semantic Website Clustering Semantic Website Clustering I-Hsuan Yang, Yu-tsun Huang, Yen-Ling Huang 1. Abstract We propose a new approach to cluster the web pages. Utilizing an iterative reinforced algorithm, the model extracts semantic

More information

A Simplified Correctness Proof for a Well-Known Algorithm Computing Strongly Connected Components

A Simplified Correctness Proof for a Well-Known Algorithm Computing Strongly Connected Components A Simplified Correctness Proof for a Well-Known Algorithm Computing Strongly Connected Components Ingo Wegener FB Informatik, LS2, Univ. Dortmund, 44221 Dortmund, Germany wegener@ls2.cs.uni-dortmund.de

More information

CHAPTER 8 Multimedia Information Retrieval

CHAPTER 8 Multimedia Information Retrieval CHAPTER 8 Multimedia Information Retrieval Introduction Text has been the predominant medium for the communication of information. With the availability of better computing capabilities such as availability

More information

LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES

LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES LARGE-VOCABULARY CHINESE TEXT/SPEECH INFORMATION RETRIEVAL USING MANDARIN SPEECH QUERIES Bo-ren Bai 1, Berlin Chen 2, Hsin-min Wang 2, Lee-feng Chien 2, and Lin-shan Lee 1,2 1 Department of Electrical

More information

2D image segmentation based on spatial coherence

2D image segmentation based on spatial coherence 2D image segmentation based on spatial coherence Václav Hlaváč Czech Technical University in Prague Center for Machine Perception (bridging groups of the) Czech Institute of Informatics, Robotics and Cybernetics

More information

IMAGE SEGMENTATION. Václav Hlaváč

IMAGE SEGMENTATION. Václav Hlaváč IMAGE SEGMENTATION Václav Hlaváč Czech Technical University in Prague Faculty of Electrical Engineering, Department of Cybernetics Center for Machine Perception http://cmp.felk.cvut.cz/ hlavac, hlavac@fel.cvut.cz

More information

K-Means Clustering Using Localized Histogram Analysis

K-Means Clustering Using Localized Histogram Analysis K-Means Clustering Using Localized Histogram Analysis Michael Bryson University of South Carolina, Department of Computer Science Columbia, SC brysonm@cse.sc.edu Abstract. The first step required for many

More information

A Novel PAT-Tree Approach to Chinese Document Clustering

A Novel PAT-Tree Approach to Chinese Document Clustering A Novel PAT-Tree Approach to Chinese Document Clustering Kenny Kwok, Michael R. Lyu, Irwin King Department of Computer Science and Engineering The Chinese University of Hong Kong Shatin, N.T., Hong Kong

More information

Chapter S:II. II. Search Space Representation

Chapter S:II. II. Search Space Representation Chapter S:II II. Search Space Representation Systematic Search Encoding of Problems State-Space Representation Problem-Reduction Representation Choosing a Representation S:II-1 Search Space Representation

More information

International Journal of Advance Foundation and Research in Science & Engineering (IJAFRSE) Volume 1, Issue 2, July 2014.

International Journal of Advance Foundation and Research in Science & Engineering (IJAFRSE) Volume 1, Issue 2, July 2014. A B S T R A C T International Journal of Advance Foundation and Research in Science & Engineering (IJAFRSE) Information Retrieval Models and Searching Methodologies: Survey Balwinder Saini*,Vikram Singh,Satish

More information

Intelligent management of on-line video learning resources supported by Web-mining technology based on the practical application of VOD

Intelligent management of on-line video learning resources supported by Web-mining technology based on the practical application of VOD World Transactions on Engineering and Technology Education Vol.13, No.3, 2015 2015 WIETE Intelligent management of on-line video learning resources supported by Web-mining technology based on the practical

More information

A Random Number Based Method for Monte Carlo Integration

A Random Number Based Method for Monte Carlo Integration A Random Number Based Method for Monte Carlo Integration J Wang and G Harrell Department Math and CS, Valdosta State University, Valdosta, Georgia, USA Abstract - A new method is proposed for Monte Carlo

More information

Image Mining Using Image Feature

Image Mining Using Image Feature Image Mining Using Image Feature Varsha Kundlikar 1, Meghana Nagori 2. Abstract In this paper, features of image used for mining images from database. Basic features of images such as colour of pixel in

More information

Title A Content-Based Search Engine on Medical Images for Telemedicine Author(s) Cheung, DWL; Lee, CH; Ng, V Citation The 21st Annual International Computer Software and Applications Conference Proceedings,

More information

Graph Sampling Approach for Reducing. Computational Complexity of. Large-Scale Social Network

Graph Sampling Approach for Reducing. Computational Complexity of. Large-Scale Social Network Journal of Innovative Technology and Education, Vol. 3, 216, no. 1, 131-137 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/1.12988/jite.216.6828 Graph Sampling Approach for Reducing Computational Complexity

More information

CE4031 and CZ4031 Database System Principles

CE4031 and CZ4031 Database System Principles CE431 and CZ431 Database System Principles Course CE/CZ431 Course Database System Principles CE/CZ21 Algorithms; CZ27 Introduction to Databases CZ433 Advanced Data Management (not offered currently) Lectures

More information

Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques

Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques 24 Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques Enhancing Forecasting Performance of Naïve-Bayes Classifiers with Discretization Techniques Ruxandra PETRE

More information

Consistent Line Clusters for Building Recognition in CBIR

Consistent Line Clusters for Building Recognition in CBIR Consistent Line Clusters for Building Recognition in CBIR Yi Li and Linda G. Shapiro Department of Computer Science and Engineering University of Washington Seattle, WA 98195-250 shapiro,yi @cs.washington.edu

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

Advanced Operations Research Techniques IE316. Quiz 1 Review. Dr. Ted Ralphs

Advanced Operations Research Techniques IE316. Quiz 1 Review. Dr. Ted Ralphs Advanced Operations Research Techniques IE316 Quiz 1 Review Dr. Ted Ralphs IE316 Quiz 1 Review 1 Reading for The Quiz Material covered in detail in lecture. 1.1, 1.4, 2.1-2.6, 3.1-3.3, 3.5 Background material

More information

Semantics-based Image Retrieval by Region Saliency

Semantics-based Image Retrieval by Region Saliency Semantics-based Image Retrieval by Region Saliency Wei Wang, Yuqing Song and Aidong Zhang Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY 14260, USA

More information

EE 701 ROBOT VISION. Segmentation

EE 701 ROBOT VISION. Segmentation EE 701 ROBOT VISION Regions and Image Segmentation Histogram-based Segmentation Automatic Thresholding K-means Clustering Spatial Coherence Merging and Splitting Graph Theoretic Segmentation Region Growing

More information

Decision Making. final results. Input. Update Utility

Decision Making. final results. Input. Update Utility Active Handwritten Word Recognition Jaehwa Park and Venu Govindaraju Center of Excellence for Document Analysis and Recognition Department of Computer Science and Engineering State University of New York

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

Bloom filters and their applications

Bloom filters and their applications Bloom filters and their applications Fedor Nikitin June 11, 2006 1 Introduction The bloom filters, as a new approach to hashing, were firstly presented by Burton Bloom [Blo70]. He considered the task of

More information

EFFICIENT ATTRIBUTE REDUCTION ALGORITHM

EFFICIENT ATTRIBUTE REDUCTION ALGORITHM EFFICIENT ATTRIBUTE REDUCTION ALGORITHM Zhongzhi Shi, Shaohui Liu, Zheng Zheng Institute Of Computing Technology,Chinese Academy of Sciences, Beijing, China Abstract: Key words: Efficiency of algorithms

More information

Shape Retrieval with Flat Contour Segments

Shape Retrieval with Flat Contour Segments Shape Retrieval with Flat Contour Segments Dalong Li 1, Steven Simske Intelligent Enterprise Technologies Laboratory HP Laboratories Palo Alto HPL-2002-250 September 9 th, 2002* image database, image retrieval,

More information

Dynamic Thresholding for Image Analysis

Dynamic Thresholding for Image Analysis Dynamic Thresholding for Image Analysis Statistical Consulting Report for Edward Chan Clean Energy Research Center University of British Columbia by Libo Lu Department of Statistics University of British

More information

An Improved Upper Bound for the Sum-free Subset Constant

An Improved Upper Bound for the Sum-free Subset Constant 1 2 3 47 6 23 11 Journal of Integer Sequences, Vol. 13 (2010), Article 10.8.3 An Improved Upper Bound for the Sum-free Subset Constant Mark Lewko Department of Mathematics University of Texas at Austin

More information

Power-Mode-Aware Buffer Synthesis for Low-Power Clock Skew Minimization

Power-Mode-Aware Buffer Synthesis for Low-Power Clock Skew Minimization This article has been accepted and published on J-STAGE in advance of copyediting. Content is final as presented. IEICE Electronics Express, Vol.* No.*,*-* Power-Mode-Aware Buffer Synthesis for Low-Power

More information

Two Algorithms of Image Segmentation and Measurement Method of Particle s Parameters

Two Algorithms of Image Segmentation and Measurement Method of Particle s Parameters Appl. Math. Inf. Sci. 6 No. 1S pp. 105S-109S (2012) Applied Mathematics & Information Sciences An International Journal @ 2012 NSP Natural Sciences Publishing Cor. Two Algorithms of Image Segmentation

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

Eye Detection by Haar wavelets and cascaded Support Vector Machine

Eye Detection by Haar wavelets and cascaded Support Vector Machine Eye Detection by Haar wavelets and cascaded Support Vector Machine Vishal Agrawal B.Tech 4th Year Guide: Simant Dubey / Amitabha Mukherjee Dept of Computer Science and Engineering IIT Kanpur - 208 016

More information

arxiv:cs/ v1 [cs.dl] 11 Feb 1999

arxiv:cs/ v1 [cs.dl] 11 Feb 1999 arxiv:cs/9902023v1 [cs.dl] 11 Feb 1999 A New Ranking Principle for Multimedia Information Retrieval Martin Wechsler, Peter Schäuble Eurospider Information Technology AG, Zürich www.eurospider.com Abstract

More information

XETA: extensible metadata System

XETA: extensible metadata System XETA: extensible metadata System Abstract: This paper presents an extensible metadata system (XETA System) which makes it possible for the user to organize and extend the structure of metadata. We discuss

More information

KBSVM: KMeans-based SVM for Business Intelligence

KBSVM: KMeans-based SVM for Business Intelligence Association for Information Systems AIS Electronic Library (AISeL) AMCIS 2004 Proceedings Americas Conference on Information Systems (AMCIS) December 2004 KBSVM: KMeans-based SVM for Business Intelligence

More information

Tracking of Human Body using Multiple Predictors

Tracking of Human Body using Multiple Predictors Tracking of Human Body using Multiple Predictors Rui M Jesus 1, Arnaldo J Abrantes 1, and Jorge S Marques 2 1 Instituto Superior de Engenharia de Lisboa, Postfach 351-218317001, Rua Conselheiro Emído Navarro,

More information

Representing Symbolic Reasoning

Representing Symbolic Reasoning Representing Symbolic Reasoning Brian Mastenbrook and Eric Berkowitz 1400 N. Roosevelt Blvd. Schaumburg, IL 60173 chandler@acm.roosevelt.edu eric@cs.roosevelt.edu Abstract Introspection is a fundamental

More information

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai

COMPUTER VISION. Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai COMPUTER VISION Dr. Sukhendu Das Deptt. of Computer Science and Engg., IIT Madras, Chennai 600036. Email: sdas@iitm.ac.in URL: //www.cs.iitm.ernet.in/~sdas 1 INTRODUCTION 2 Human Vision System (HVS) Vs.

More information

LANGUAGE MODEL SIZE REDUCTION BY PRUNING AND CLUSTERING

LANGUAGE MODEL SIZE REDUCTION BY PRUNING AND CLUSTERING LANGUAGE MODEL SIZE REDUCTION BY PRUNING AND CLUSTERING Joshua Goodman Speech Technology Group Microsoft Research Redmond, Washington 98052, USA joshuago@microsoft.com http://research.microsoft.com/~joshuago

More information

PERFORMANCE EVALUATION OF ONTOLOGY AND FUZZYBASE CBIR

PERFORMANCE EVALUATION OF ONTOLOGY AND FUZZYBASE CBIR PERFORMANCE EVALUATION OF ONTOLOGY AND FUZZYBASE CBIR ABSTRACT Tajman sandhu (Research scholar) Department of Information Technology Chandigarh Engineering College, Landran, Punjab, India yuvi_taj@yahoo.com

More information

Provably Efficient Non-Preemptive Task Scheduling with Cilk

Provably Efficient Non-Preemptive Task Scheduling with Cilk Provably Efficient Non-Preemptive Task Scheduling with Cilk V. -Y. Vee and W.-J. Hsu School of Applied Science, Nanyang Technological University Nanyang Avenue, Singapore 639798. Abstract We consider the

More information

The Fibonacci hypercube

The Fibonacci hypercube AUSTRALASIAN JOURNAL OF COMBINATORICS Volume 40 (2008), Pages 187 196 The Fibonacci hypercube Fred J. Rispoli Department of Mathematics and Computer Science Dowling College, Oakdale, NY 11769 U.S.A. Steven

More information

A Fast Algorithm for Finding k-nearest Neighbors with Non-metric Dissimilarity

A Fast Algorithm for Finding k-nearest Neighbors with Non-metric Dissimilarity A Fast Algorithm for Finding k-nearest Neighbors with Non-metric Dissimilarity Bin Zhang and Sargur N. Srihari CEDAR, Department of Computer Science and Engineering State University of New York at Buffalo

More information

AUTOMATIC EXTRACTION OF BUILDING FEATURES FROM TERRESTRIAL LASER SCANNING

AUTOMATIC EXTRACTION OF BUILDING FEATURES FROM TERRESTRIAL LASER SCANNING AUTOMATIC EXTRACTION OF BUILDING FEATURES FROM TERRESTRIAL LASER SCANNING Shi Pu and George Vosselman International Institute for Geo-information Science and Earth Observation (ITC) spu@itc.nl, vosselman@itc.nl

More information

How to Conduct a Heuristic Evaluation

How to Conduct a Heuristic Evaluation Page 1 of 9 useit.com Papers and Essays Heuristic Evaluation How to conduct a heuristic evaluation How to Conduct a Heuristic Evaluation by Jakob Nielsen Heuristic evaluation (Nielsen and Molich, 1990;

More information

Algorithm That Mimics Human Perceptual Grouping of Dot Patterns

Algorithm That Mimics Human Perceptual Grouping of Dot Patterns Algorithm That Mimics Human Perceptual Grouping of Dot Patterns G. Papari and N. Petkov Institute of Mathematics and Computing Science, University of Groningen, P.O.Box 800, 9700 AV Groningen, The Netherlands

More information

Spotting Words in Latin, Devanagari and Arabic Scripts

Spotting Words in Latin, Devanagari and Arabic Scripts Spotting Words in Latin, Devanagari and Arabic Scripts Sargur N. Srihari, Harish Srinivasan, Chen Huang and Shravya Shetty {srihari,hs32,chuang5,sshetty}@cedar.buffalo.edu Center of Excellence for Document

More information

Indexing in Search Engines based on Pipelining Architecture using Single Link HAC

Indexing in Search Engines based on Pipelining Architecture using Single Link HAC Indexing in Search Engines based on Pipelining Architecture using Single Link HAC Anuradha Tyagi S. V. Subharti University Haridwar Bypass Road NH-58, Meerut, India ABSTRACT Search on the web is a daily

More information

Efficient Acquisition of Human Existence Priors from Motion Trajectories

Efficient Acquisition of Human Existence Priors from Motion Trajectories Efficient Acquisition of Human Existence Priors from Motion Trajectories Hitoshi Habe Hidehito Nakagawa Masatsugu Kidode Graduate School of Information Science, Nara Institute of Science and Technology

More information