Clustering of Text and Image for Grouping Similar Contents

Size: px
Start display at page:

Download "Clustering of Text and Image for Grouping Similar Contents"

Transcription

1 University of Aizu, Graduation Thesis. August, 2003 s Clustering of Text and Image for Grouping Similar Contents of Web Data Keigo Hirai s Supervised by Prof. Ryuichi Oka Abstract 2 System for Clustering of Text and Image The object of this paper is to design a searching system that uses relation between two vectors. The data files are random text (Hyper Text Markup Language, HTML) and image files. This paper explains how the data files were classified and retrieved. 1 Introduction This paper supports searching system that uses relation between two vectors. The Google image searching system searches images with text keywords that are near the tag< img... > and the image captions [1]. This paper s image searching system is more effective than the Google one. The system uses image vector information and text vector information. The system can search for images from input text or image as well as texts from input text or image. The position of this paper is between word analysis and image processing. Word analysis is needed to make text feature vectors from texts. This paper uses KAKASI as word analysis method. KAKASI is abbreviation of KAnji KAna Simple Inverter. Word analysis method is included the invert process of KAKASI [2]. Image processing is needed to make image feature vectors from images. The Prewitt method is adopted this research as edge analysis method [3]. This searching system needs a clustering method for retrieving object data. K-means clustering is grouping method that arranges similar data files close groups [4]. Images that are used at web sites on mostly Joint Photographic Experts Group (JPEG) image. JPEG images adopted for this research too. JPEG image data is stored 2-dimension arrays. Image processing processes the RED, GREEN, and BLUE (RGB) values of the 2- dimension array. In this research program, a dynamic link library (DLL) imgctl.dll was adopted as the JPEG image loading method [5]. Figure 1: Outline of the system for multimedia data organization and retrieval Figure 1 shows this research system. The raw data 1 of images and text is hard to process for computer. The need for feature vector extraction stems from this raw data property. Feature vectors are easy to process for computers. 2.1 Feature Vector Extraction from Image Data There are several ways to get image feature vectors, such as color feature vectors, edge feature vector, and position feature vectors. Color feature vectors and edge feature vectors were adopted for this research Color Feature Vector Extraction 1. Separate the image into 64 cells. The cell width is image width image height 8. The cell height is Compute the RGB mean value of the respective cells. The value range is from 0 to non-processed original data

2 University of Aizu, Graduation Thesis. August, 2003 s Quantized value Original value 0 (0-31) 1 (32-63) 2 (64-95) 3 (96-127) 4 ( ) 5 ( ) 6 ( ) 7 ( ) M k is a mask element value. M 0 corresponds to the first element of the mask. I k is an image intensity value under the mask. The edge direction at the pixel is the mask direction that has maximum MD value. 4. Run above process for per pixel. Table 1: Quantize table for color feature vector extraction 3. Quantize the RGB mean value (0-255) to 8 levels (0-7). The quantized value is computed at the respective cells (Table 1). 4. Prepare the 24-dimension array Vc(R 0,..., R 7, G 0,..., G 7, B 0,..., B 7 ) to store color data. 64 cells are processed with the above 2 and 3 rules. The specific process is follows: (a) If the RGB mean value is (R, G, B) = (10, 150, 255), the quantized value is (0, 4, 7) (b) Add 1 to R 0, G 4, B 7 (c) Process these quantizations and increment all 64 cells. Those processes extract the 24-dimension color feature vector Vc. 5. Apply the above method to all image files (JPEG) under a directory (include subdirectories) Edge Feature Vector Extraction The Prewitt method, a method of Template Matching, is used in the edge feature extraction process. It uses the kinds 3 x 3 pixel masks. Those masks detect where edge direction is. The method detects edge direction with the 3 x 3 pixels mask that moves a pixel at a time. 1. Change the image into gray-scale. This research considers the image intensity element. 2. Prepare eight 3 x 3 pixels masks that correspond to eight directions respectively (Figure 2). 3. Compute the matching degree (MD) for the eight masks (eight directions) as follows. (i=mask identifier (0-7) ). MD i = 7 M k I k k=0 Figure 2: Mask set for Prewitt method 5. Separate the image into 80 x 80 blocks for extracting the broad edge vectors. 6. Compute the image intensity mean value for the respective blocks. In broad edge vector extraction, the Prewitt method regards a block as a pixel. 7. Prepare the array of the number of edge directions frequency Ve(E 0, E 1,..., E 15 ). (E 0,..., E 7 ) are elements for storing the number of edge direction frequencies. (E 8,..., E 15 ) are elements for storing the number of broad edge direction frequencies. 8. Apply the above method to all image files (JPEG) under a directory (include subdirectories). The image feature vector is defined as Vi(I 0,..., I 31 )= (Vc, Ve). (Vi is 40-dimension. Color feature vector Vc is 24-dimension. Edge feature vector Ve is 16- dimension.) All image feature vectors (Vi) under a directory are recorded to an image feature data file. The data file is prepared for clustering. 2.2 Feature Vector Extraction from Text Data The text feature vector Vt(word 0,..., word n ) is an array of word frequency within the text (HTML). n is the num-

3 University of Aizu, Graduation Thesis. August, 2003 s ber of the word type. The first element of array (word 0 ) is first word frequency within the text. The KAKASI project members had researched originally the KAKASI program for transforming Japanese from kanji to hiragana, katakana, and Romaji. (Romaji is Romanized Japanese pronunciation.) The KAKASI program uses a function that divides text into words. Extract method of text feature vector is written as follows. 1. Get rid of HTML tags<... > and comments <! > from input text. 2. Insert spaces between words with a KAKASI function. 3. Prepare a linked-list of structures which has string data (word) and integer data (frequency). 4. Add a word of text to a linked-list node in occurrence order. If a word already exists within the linked-list, the occurrence number of the word is added All text files (HTML) under a directory (obtain subdirectories) are processed by above method. The text feature vector dimension becomes larger by reading new text file. This dimension number is the word kind number of whole texts. (In practice, the dimension number is 3658 for 118 text files.) This large dimension vector is hard to handle for clustering. 6. Set the appropriate high value and low value to extract useful middle word data. Words that occurs too frequently and words that occurs too infrequently are cut with the high value and the low value. The example of the word that occurs too frequently is basic verb, kakuzyosi 2, period ( ), and comma ( ). They are cut because of the meaninglessness. Words occurs too infrequently have the possibility that include many kinds of part of speech. Most of those words have meaning themselves, but they are not useful for clustering because of the small frequency. Words occurs too infrequently has weak relation to other texts. 7. Cut words that occur too frequently and words that occur too infrequently from the linked-list. Figure 3 shows the linked-list elements after cutting. 2 the Japanese part of speech that shows the relation between word. For example, (ga), (no), (wo), (ni), (he), (to), (yori), (kara), and (de). It resembles English preposition. Figure 3: The part of the linked-list elements after cutting This figure shows text feature vectors frequency of the web data under a directory. Left elements are word type. Right elements are word frequency. 8. Recount the word frequency for respective texts. The counter notes only the linked-list words. The recounted number array is the text feature vector. 9. Apply the above method to all text files (HTML) under a directory (include subdirectories). All text feature vectors (Vt) under a directory are recorded to a text feature data file. The data file is prepared for clustering. 3 Clustering of Two Types of Feature Vectors Both feature vectors, image feature vectors and text feature vectors, are classified by k-means clustering method by using the image feature data file and the text feature data file. The k-means method is defined as follows. 1. Set random K initial center points of class. 2. Classify all data to clusters. If there is a center point of class nearest for a data, this data is classified to this class. 3. Move the center point of class to the new class s center of gravity. 4. If the all new positions of center points of class equal to old ones, the process ends. If not, the process goes back to 2. The k-means method gathers resemble data to a resemble class. Those data are feature vector set written in feature data file. Image feature data file and text feature data file are classified individually.

4 University of Aizu, Graduation Thesis. August, 2003 s Retrieval Algorithm of Multimedia Data 4.2 Text Query The retrieval method in searching texts by a text is follows: 1. Extract the input text s feature vector 2. Examine the input text class 3. Texts in the class are results. The retrieval method in searching images by a text is follows: Figure 4: Outline of retrieval algorithm of multimedia data Figure 4 shows outline of retrieval. This section explains the retrieval way to get results when the keyword is entered. There are 4 retrieval routes. Classified data are prepared already in this section. When the system gets the text from image keyword, when the system gets the image from text keyword, this situation needs bridge data that explains the relation between texts and images. Bridge data are constructed the set of image file names (src=...jpg ) within img tag in the HTML. The bridge data are recorded to a bridge data file. 4.1 Image Query The retrieval method in searching images by an image is follows: 1. Extract the input image s feature vector 2. Examine the input image class 3. Images in the class are results. The retrieval method in searching texts by an image is follows: 1. Extract the input image s feature vector 2. Examine the input image class 3. Select another image of the class 4. A (Several) class (classes) of texts is (are) determined by the selected image using by text-image bridge data 5. Texts in the class (classes) are results. When several classes of texts are determined, the input image is used several HTML. 1. Extract the input text s feature vector 2. Examine the input text class 3. Select another text of the class 4. A (Several) class (classes) of images is (are) determined by the selected text using by text-image bridge data 5. Images in the class (classes) are results. When several classes of images are determined, the input text (HTML) uses several JPEG images. 5 Experimental Results This section shows results of the searching system. Web data (130 texts (HTML) and 91 images) are prepared for this searching system. The number of the image class and the text class is twelve in this paper. This number (twelve) are determined by this research experience. They are retrieved by four methods. Those web data are completely same as Mr. Yanagita s paper s web data. 5.1 Image Query Mr. Yanagita s (s ) paper shows image query results. The paper title is Extraction of Text-Image Correlation for Web Image Data with Text. 5.2 Text Query The web data have words, 5221 word types. The low value for cutting is decided 10. The high value for word types cutting is decided 30 = 174. This text feature has 215 elements, in other words, this feature dimension is 215.

5 University of Aizu, Graduation Thesis. August, 2003 s Text Query Text Results Figure 5: Example of the web page having only the image and caption (text results for the short text query) Short texts (HTML) tend to gather at the same class. Those HTML have the strong possibility of the web page having only the image and caption (Figure 5), in practice, all such web pages of this research data gather at the same class. Therefore, if the query text length is short, text results (HTML) are like such web pages. Figure 7: Example of the web page having the word kamosika (text results for the long text query with figure 6) Long texts (HTML) are classified by word frequency (Figure 6). Therefore, if the query text is long and has the word kamosika 3, text results (HTML) have the possibility of having the word kamosika (Figure 7), in practice, such web pages tend to gather at the same class Text Query Image Results The input texts is used figure 6. The image results are follows. Figure 8: Retrieved nine images by the input text query shown in figure 6 Figure 6: Example of long texts word frequency (input text) Three pictures of kamosika, (b), (f), and (h), are retrieved. Six pictures of monkey, (a), (c), (d), (e), (g), and (i), are retrieved too, because colors and edges of monkey picture resemble to kamosika one. 3 Japanese of serow

6 University of Aizu, Graduation Thesis. August, 2003 s Discussion of the Text Query Short texts tend to position the center point of vector space because of those Euclidean distances are so shorter than long texts one. Those searching system results depend on the word type and the text length too. The text length is one of text features, so this system supports the text length feature without notice. This property will contribute to this system improvement. 6 Conclusion This paper presented the searching system that uses relation between two vectors. This system realizes the retrieving system that superiors to two data types ( Images and Texts ). The old searching system supports the combination of words as keyword. This system supports images and texts as keyword. This improvement supports the fuzzy retrieving. This property helps to search wide relational informations. The additional improvements can be made to this searching system in the future. 6.1 Future work Images clustering is constructed in this research completely, but programs of the texts clustering and the retrieving system are not constructed completely. The program of texts clustering has a bug to stop reading from large-scale number of HTML. Above results are produced by the handwork. The future works for this research are follows: Acknowledgment I want to thank Prof. Oka, Mr. Suenaga, Mr. Murakami and Mr. Yanagita for their helpful comments and programs during this research. I use Mr. Yanagita s image processing program in this research. References [1] Google, Google Frequently Asked Questions: Image Search, images.html (current Jan. 2003) [2] KAKASI project, KAKASI - Kanji Kana Simple Inverter, (current Dec. 2002) [3] S. Inoue, N. Yagi, M. Hayashi, E. Nakasu, K. Mitani, M. Okui, C gengo de Manabu Jissen Gazoushori, Ohmsha, [4] H. Kasuga, Color Quantization Using Fast K- means Algorithm, kasuga/kmeans.html (current Jan. 2003) [5] Ruche, Ruche s Homepage, (current Jan. 2003) Construct the complete programs of the texts clustering and the retrieving system Prepare the user friendly GUI (Graphical User Interface) system for retrieve Expand the destination data from local data to Internet data Visualize web data by using a classification method Adopt audio data as keyword and retrieve destination. Adopt texts in images as bridge data. Adopt the position feature as the image feature vector. If above works will be researched, this searching system will be more useful for the people all around the world.

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

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

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

CSC 101: PreLab Reading for Lab #4 More HTML (some of this reading on Tables and Images are based on previous writings of Prof William Turkett)

CSC 101: PreLab Reading for Lab #4 More HTML (some of this reading on Tables and Images are based on previous writings of Prof William Turkett) CSC 101: PreLab Reading for Lab #4 More HTML (some of this reading on Tables and Images are based on previous writings of Prof William Turkett) Purpose: The purpose of this pre-lab is to provide you with

More information

CSE 3. Marking Up with HTML. Comics Updates Shortcut(s)/Tip(s) of the Day Google Earth/Google Maps ssh Anti-Spyware

CSE 3. Marking Up with HTML. Comics Updates Shortcut(s)/Tip(s) of the Day Google Earth/Google Maps ssh Anti-Spyware CSE 3 Comics Updates Shortcut(s)/Tip(s) of the Day Google Earth/Google Maps ssh Anti-Spyware 1-1 4-1 Chapter 4: Marking Up With HTML: A Hypertext Markup Language Primer Fluency with Information Technology

More information

5/17/2009. Marking Up with HTML. An HTML Web Page File. Tags for Bold, Italic, and underline. Structuring Documents

5/17/2009. Marking Up with HTML. An HTML Web Page File. Tags for Bold, Italic, and underline. Structuring Documents Chapter 4: Marking Up With HTML: A Hypertext Markup Language Primer Marking Up with HTML Fluency with Information Technology Third Edition by Lawrence Snyder Tags describe how a web page should look Formatting

More information

3 Data Storage 3.1. Foundations of Computer Science Cengage Learning

3 Data Storage 3.1. Foundations of Computer Science Cengage Learning 3 Data Storage 3.1 Foundations of Computer Science Cengage Learning Objectives After studying this chapter, the student should be able to: List five different data types used in a computer. Describe how

More information

Video Compression An Introduction

Video Compression An Introduction Video Compression An Introduction The increasing demand to incorporate video data into telecommunications services, the corporate environment, the entertainment industry, and even at home has made digital

More information

Web Design 101. What is HTML? HTML Tags. Web Browsers. <!DOCTYPE html> <html> <body> <h1>my First Heading</h1> <p>my first paragraph.

Web Design 101. What is HTML? HTML Tags. Web Browsers. <!DOCTYPE html> <html> <body> <h1>my First Heading</h1> <p>my first paragraph. What is HTML? Web Design 101 HTML is a language for describing web pages. HTML stands for Hyper Text Markup Language HTML is a markup language à A markup language is a set of markup tags The tags describe

More information

Chapter 4: Marking Up With HTML: A Hypertext tmarkup Language Primer

Chapter 4: Marking Up With HTML: A Hypertext tmarkup Language Primer Chapter 4: Marking Up With HTML: A Hypertext tmarkup Language Primer Fluency with Information Technology Third Edition by Lawrence Snyder Copyright 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley

More information

255, 255, 0 0, 255, 255 XHTML:

255, 255, 0 0, 255, 255 XHTML: Colour Concepts How Colours are Displayed FIG-5.1 Have you looked closely at your television screen recently? It's in full colour, showing every colour and shade that your eye is capable of seeing. And

More information

Marking Up with HTML. Tags for Bold, Italic, and underline. An HTML Web Page File. Chapter 4: Marking Up With HTML: A. Formatting with Tags:

Marking Up with HTML. Tags for Bold, Italic, and underline. An HTML Web Page File. Chapter 4: Marking Up With HTML: A. Formatting with Tags: Chapter 4: Marking Up With HTML: A HypertextMarkup tm Language Primer Fluency with Information Technology Third Edition by Lawrence Snyder Marking Up with HTML Tags describe how a web page should look

More information

Chapter 4 A Hypertext Markup Language Primer

Chapter 4 A Hypertext Markup Language Primer Chapter 4 A Hypertext Markup Language Primer XHTML Mark Up with Tags Extensible Hypertext Markup Language Format Word/abbreviation in < > PAIR Singleton (not surround text) />

More information

CS 103, Fall 2008 Midterm 1 Prof. Nakayama

CS 103, Fall 2008 Midterm 1 Prof. Nakayama CS 103, Fall 2008 Midterm 1 Prof. Nakayama Family (or Last) Name Given (or First) Name Student ID Instructions 1. This exam has 9 pages in total, numbered 1 to 9. Make sure your exam has all the pages.

More information

TABLE OF CONTENTS CHAPTER NO. TITLE PAGENO. LIST OF TABLES LIST OF FIGURES LIST OF ABRIVATION

TABLE OF CONTENTS CHAPTER NO. TITLE PAGENO. LIST OF TABLES LIST OF FIGURES LIST OF ABRIVATION vi TABLE OF CONTENTS ABSTRACT LIST OF TABLES LIST OF FIGURES LIST OF ABRIVATION iii xii xiii xiv 1 INTRODUCTION 1 1.1 WEB MINING 2 1.1.1 Association Rules 2 1.1.2 Association Rule Mining 3 1.1.3 Clustering

More information

Instructions for Web Content Creators and Web Editors Web Transformation design extensions

Instructions for Web Content Creators and Web Editors Web Transformation design extensions Web Services and Information Policy Instructions for Web Content Creators and Web Editors Web Transformation design extensions Version 1.2 December 2013 I:\UIWS\Projects\Web Transformation Program\Projects\Completed\2012\Web

More information

Extracting Characters From Books Based On The OCR Technology

Extracting Characters From Books Based On The OCR Technology 2016 International Conference on Engineering and Advanced Technology (ICEAT-16) Extracting Characters From Books Based On The OCR Technology Mingkai Zhang1, a, Xiaoyi Bao1, b,xin Wang1, c, Jifeng Ding1,

More information

Introduction to Computer Science (I1100) Data Storage

Introduction to Computer Science (I1100) Data Storage Data Storage 145 Data types Data comes in different forms Data Numbers Text Audio Images Video 146 Data inside the computer All data types are transformed into a uniform representation when they are stored

More information

Clustering Technique with Potter stemmer and Hypergraph Algorithms for Multi-featured Query Processing

Clustering Technique with Potter stemmer and Hypergraph Algorithms for Multi-featured Query Processing Vol.2, Issue.3, May-June 2012 pp-960-965 ISSN: 2249-6645 Clustering Technique with Potter stemmer and Hypergraph Algorithms for Multi-featured Query Processing Abstract In navigational system, it is important

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

Meta-Content framework for back index generation

Meta-Content framework for back index generation Meta-Content framework for back index generation Tripti Sharma, Assistant Professor Department of computer science Chhatrapati Shivaji Institute of Technology. Durg, India triptisharma@csitdurg.in Sarang

More information

INF5063: Programming heterogeneous multi-core processors. September 17, 2010

INF5063: Programming heterogeneous multi-core processors. September 17, 2010 INF5063: Programming heterogeneous multi-core processors September 17, 2010 High data volumes: Need for compression PAL video sequence 25 images per second 3 bytes per pixel RGB (red-green-blue values)

More information

More HTML. Graphics. Graphic Format

More HTML. Graphics. Graphic Format More HTML Graphics Graphics are probably one of the more exciting pieces to the Web. They give Web pages that fun, classy, or sophisticated look. They can also make your page look gaudy and too busy if

More information

A SURVEY OF IMAGE MINING TECHNIQUES AND APPLICATIONS

A SURVEY OF IMAGE MINING TECHNIQUES AND APPLICATIONS A SURVEY OF IMAGE MINING TECHNIQUES AND APPLICATIONS R. Vijayalatha Research Scholar, Manonmaniam Sundaranar University, Tirunelveli (India) ABSTRACT In the area of Data Mining, Image Mining technology

More information

Contents. Table of Contents. Table of Contents... iii Preface... xvii. Getting Started iii

Contents. Table of Contents. Table of Contents... iii Preface... xvii. Getting Started iii Contents Discovering the Possibilities... iii Preface... xvii Preface to the First Edition xvii Preface to the Second Edition xviii Getting Started... 1 Chapter Overview 1 Philosophy Behind this Book 1

More information

15 Data Compression 2014/9/21. Objectives After studying this chapter, the student should be able to: 15-1 LOSSLESS COMPRESSION

15 Data Compression 2014/9/21. Objectives After studying this chapter, the student should be able to: 15-1 LOSSLESS COMPRESSION 15 Data Compression Data compression implies sending or storing a smaller number of bits. Although many methods are used for this purpose, in general these methods can be divided into two broad categories:

More information

MATRIX BASED INDEXING TECHNIQUE FOR VIDEO DATA

MATRIX BASED INDEXING TECHNIQUE FOR VIDEO DATA Journal of Computer Science, 9 (5): 534-542, 2013 ISSN 1549-3636 2013 doi:10.3844/jcssp.2013.534.542 Published Online 9 (5) 2013 (http://www.thescipub.com/jcs.toc) MATRIX BASED INDEXING TECHNIQUE FOR VIDEO

More information

Vehicle Detection Method using Haar-like Feature on Real Time System

Vehicle Detection Method using Haar-like Feature on Real Time System Vehicle Detection Method using Haar-like Feature on Real Time System Sungji Han, Youngjoon Han and Hernsoo Hahn Abstract This paper presents a robust vehicle detection approach using Haar-like feature.

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

Development of E-learning Contents for Exchange Students

Development of E-learning Contents for Exchange Students Development of E-learning Contents for Exchange Students Kuniaki YAJIMA #1, Jarmo Seppälä *2, Akihiro NITTA #1 # Department of Information networks, Hirose campus, Sendai College, Institute National of

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

Keywords Binary Linked Object, Binary silhouette, Fingertip Detection, Hand Gesture Recognition, k-nn algorithm.

Keywords Binary Linked Object, Binary silhouette, Fingertip Detection, Hand Gesture Recognition, k-nn algorithm. Volume 7, Issue 5, May 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Hand Gestures Recognition

More information

Semantic Video Indexing

Semantic Video Indexing Semantic Video Indexing T-61.6030 Multimedia Retrieval Stevan Keraudy stevan.keraudy@tkk.fi Helsinki University of Technology March 14, 2008 What is it? Query by keyword or tag is common Semantic Video

More information

CHAPTER 4 DETECTION OF DISEASES IN PLANT LEAF USING IMAGE SEGMENTATION

CHAPTER 4 DETECTION OF DISEASES IN PLANT LEAF USING IMAGE SEGMENTATION CHAPTER 4 DETECTION OF DISEASES IN PLANT LEAF USING IMAGE SEGMENTATION 4.1. Introduction Indian economy is highly dependent of agricultural productivity. Therefore, in field of agriculture, detection of

More information

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Anil K Goswami 1, Swati Sharma 2, Praveen Kumar 3 1 DRDO, New Delhi, India 2 PDM College of Engineering for

More information

Chapter 1 Getting Started with HTML 5 1. Chapter 2 Introduction to New Elements in HTML 5 21

Chapter 1 Getting Started with HTML 5 1. Chapter 2 Introduction to New Elements in HTML 5 21 Table of Contents Chapter 1 Getting Started with HTML 5 1 Introduction to HTML 5... 2 New API... 2 New Structure... 3 New Markup Elements and Attributes... 3 New Form Elements and Attributes... 4 Geolocation...

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

Introduction to HTML. SSE 3200 Web-based Services. Michigan Technological University Nilufer Onder

Introduction to HTML. SSE 3200 Web-based Services. Michigan Technological University Nilufer Onder Introduction to HTML SSE 3200 Web-based Services Michigan Technological University Nilufer Onder What is HTML? Acronym for: HyperText Markup Language HyperText refers to text that can initiate jumps to

More information

Creating Web Pages. Getting Started

Creating Web Pages. Getting Started Creating Web Pages Getting Started Overview What Web Pages Are How Web Pages are Formatted Putting Graphics on Web Pages How Web Pages are Linked Linking to other Files What Web Pages Are Web Pages combine

More information

Building Web Annotation Stickies based on Bidirectional Links

Building Web Annotation Stickies based on Bidirectional Links Building Web Annotation Stickies based on Bidirectional Links Hiroyuki Sano, Taiki Ito, Tadachika Ozono and Toramatsu Shintani Dept. of Computer Science and Engineering Graduate School of Engineering,

More information

Canny Edge Based Self-localization of a RoboCup Middle-sized League Robot

Canny Edge Based Self-localization of a RoboCup Middle-sized League Robot Canny Edge Based Self-localization of a RoboCup Middle-sized League Robot Yoichi Nakaguro Sirindhorn International Institute of Technology, Thammasat University P.O. Box 22, Thammasat-Rangsit Post Office,

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

Your Own Web Page; Quick and Dirty Via Mashup Reminder: Next Quiz on 4/15

Your Own Web Page; Quick and Dirty Via Mashup Reminder: Next Quiz on 4/15 Your Own Web Page; Quick and Dirty Via Mashup Reminder: Next Quiz on 4/15 A Special Language for the Web In the early 1990 s web pages were mostly described using a special purpose language, called Hyper-Text

More information

Multimedia Integration for Cooking Video Indexing

Multimedia Integration for Cooking Video Indexing Multimedia Integration for Cooking Video Indexing Reiko Hamada 1, Koichi Miura 1, Ichiro Ide 2, Shin ichi Satoh 3, Shuichi Sakai 1, and Hidehiko Tanaka 4 1 The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku,

More information

Different File Types and their Use

Different File Types and their Use Different File Types and their Use.DOC (Microsoft Word Document) Text Files A DOC file is a Word processing document created by Microsoft Word, a word processor included with all versions of Microsoft

More information

PART I: Formatting the Appearance of the Blog

PART I: Formatting the Appearance of the Blog 1 Wordpress Basics PUR4103 Public Relations Visual Communication Tappan Contents Part I: Formatting the Appearance of the Blog Choosing a theme Header image size Choosing a background color Finding a hex

More information

1. Introduction to Microsoft Excel

1. Introduction to Microsoft Excel 1. Introduction to Microsoft Excel A spreadsheet is an online version of an accountant's worksheet, which can automatically do most of the calculating for you. You can do budgets, analyze data, or generate

More information

Compression of Stereo Images using a Huffman-Zip Scheme

Compression of Stereo Images using a Huffman-Zip Scheme Compression of Stereo Images using a Huffman-Zip Scheme John Hamann, Vickey Yeh Department of Electrical Engineering, Stanford University Stanford, CA 94304 jhamann@stanford.edu, vickey@stanford.edu Abstract

More information

IMAGE COMPRESSION. Image Compression. Why? Reducing transportation times Reducing file size. A two way event - compression and decompression

IMAGE COMPRESSION. Image Compression. Why? Reducing transportation times Reducing file size. A two way event - compression and decompression IMAGE COMPRESSION Image Compression Why? Reducing transportation times Reducing file size A two way event - compression and decompression 1 Compression categories Compression = Image coding Still-image

More information

Fonts, text, and colour on the web. Sourcing, resizing, and inserting web site images MGMT 230 LAB

Fonts, text, and colour on the web. Sourcing, resizing, and inserting web site images MGMT 230 LAB Fonts, text, and colour on the web Sourcing, resizing, and inserting web site images MGMT 230 LAB Fonts and font families Font families are used in web development rather than just the name of one font

More information

A Fuzzy ARTMAP Based Classification Technique of Natural Textures

A Fuzzy ARTMAP Based Classification Technique of Natural Textures A Fuzzy ARTMAP Based Classification Technique of Natural Textures Dimitrios Charalampidis Orlando, Florida 328 16 dcl9339@pegasus.cc.ucf.edu Michael Georgiopoulos michaelg @pegasus.cc.ucf.edu Takis Kasparis

More information

Information Retrieval

Information Retrieval Multimedia Computing: Algorithms, Systems, and Applications: Information Retrieval and Search Engine By Dr. Yu Cao Department of Computer Science The University of Massachusetts Lowell Lowell, MA 01854,

More information

Voronoi diagrams and applications

Voronoi diagrams and applications Voronoi diagrams and applications Prof. Ramin Zabih http://cs100r.cs.cornell.edu Administrivia Last quiz: Thursday 11/15 Prelim 3: Thursday 11/29 (last lecture) A6 is due Friday 11/30 (LDOC) Final projects

More information

Table of Contents Chapter Nine: Database Display Chapter two: Install and Uninstall... 2

Table of Contents Chapter Nine: Database Display Chapter two: Install and Uninstall... 2 Table of Contents Chapter One: Overview... 1 1.1 Features... 1 1.2 Operating environment... 1 Chapter two: Install and Uninstall... 2 2.1 Install... 2 2.2 Uninstall... 3 Chapter Three: Use details... 4

More information

Dreamweaver Basics Workshop

Dreamweaver Basics Workshop Dreamweaver Basics Workshop Robert Rector idesign Lab - Fall 2013 What is Dreamweaver? o Dreamweaver is a web development tool o Dreamweaver is an HTML and CSS editor o Dreamweaver features a WYSIWIG (What

More information

CHAPTER 6. 6 Huffman Coding Based Image Compression Using Complex Wavelet Transform. 6.3 Wavelet Transform based compression technique 106

CHAPTER 6. 6 Huffman Coding Based Image Compression Using Complex Wavelet Transform. 6.3 Wavelet Transform based compression technique 106 CHAPTER 6 6 Huffman Coding Based Image Compression Using Complex Wavelet Transform Page No 6.1 Introduction 103 6.2 Compression Techniques 104 103 6.2.1 Lossless compression 105 6.2.2 Lossy compression

More information

Hello, I am from the State University of Library Studies and Information Technologies, Bulgaria

Hello, I am from the State University of Library Studies and Information Technologies, Bulgaria Hello, My name is Svetla Boytcheva, I am from the State University of Library Studies and Information Technologies, Bulgaria I am goingto present you work in progress for a research project aiming development

More information

Adding CSS to your HTML

Adding CSS to your HTML Adding CSS to your HTML Lecture 3 CGS 3066 Fall 2016 September 27, 2016 Making your document pretty CSS is used to add presentation to the HTML document. We have seen 3 ways of adding CSS. In this lecture,

More information

Web Usage Mining: A Research Area in Web Mining

Web Usage Mining: A Research Area in Web Mining Web Usage Mining: A Research Area in Web Mining Rajni Pamnani, Pramila Chawan Department of computer technology, VJTI University, Mumbai Abstract Web usage mining is a main research area in Web mining

More information

Manual. HTPheno. A Novel Image Analysis Pipeline for High-Throughput Plant Phenotyping

Manual. HTPheno. A Novel Image Analysis Pipeline for High-Throughput Plant Phenotyping Manual HTPheno A Novel Image Analysis Pipeline for High-Throughput Plant Phenotyping July 14, 2010 Contents 1 Basic step-by-step setup 1 1.1 Define the image object classes................. 2 1.2 Define

More information

DICOM Conformance Statement for GALILEI. Software Version V6.0

DICOM Conformance Statement for GALILEI. Software Version V6.0 DICOM Conformance Statement for GALILEI Software Version V6.0 Version 1.0, December 6 th, 2011 Contents Revision History... 2 Purpose... 2 References... 2 Terms and Definitions... 2 Abbreviations... 3

More information

Drupal 7 Template. Page 1 of 27. Site Title. Navigation Tabs. Homepage Slide. Social Media. News article. Events. Links. Contact Information

Drupal 7 Template. Page 1 of 27. Site Title. Navigation Tabs. Homepage Slide. Social Media. News article. Events. Links. Contact Information Site Title Navigation Tabs Homepage Slide News article Social Media Events Contact Information Links Page 1 of 27 Table of Contents USER ACCOUNT... 3 Edit Profile... 3 CONTENT... 5 ADD CONTENT... 5 BASIC

More information

Features. Sequential encoding. Progressive encoding. Hierarchical encoding. Lossless encoding using a different strategy

Features. Sequential encoding. Progressive encoding. Hierarchical encoding. Lossless encoding using a different strategy JPEG JPEG Joint Photographic Expert Group Voted as international standard in 1992 Works with color and grayscale images, e.g., satellite, medical,... Motivation: The compression ratio of lossless methods

More information

Tutorial and Exercises with WordList in WordSmith Tools: Level I

Tutorial and Exercises with WordList in WordSmith Tools: Level I Tutorial and Exercises with WordList in WordSmith Tools: Level I WordSmith Tools, developed by Mike Scott, is a corpus analysis tool that integrates three text analysis tools: a monolingual concordancer

More information

Chapter 4. The Classification of Species and Colors of Finished Wooden Parts Using RBFNs

Chapter 4. The Classification of Species and Colors of Finished Wooden Parts Using RBFNs Chapter 4. The Classification of Species and Colors of Finished Wooden Parts Using RBFNs 4.1 Introduction In Chapter 1, an introduction was given to the species and color classification problem of kitchen

More information

Enhanced Hemisphere Concept for Color Pixel Classification

Enhanced Hemisphere Concept for Color Pixel Classification 2016 International Conference on Multimedia Systems and Signal Processing Enhanced Hemisphere Concept for Color Pixel Classification Van Ng Graduate School of Information Sciences Tohoku University Sendai,

More information

Create a Contact Sheet of Your Images Design a Picture Package Customize Your Picture Package Layout Resample Your Image...

Create a Contact Sheet of Your Images Design a Picture Package Customize Your Picture Package Layout Resample Your Image... 72 71 Create a Contact Sheet of Your Images................... 158 Design a Picture Package............ 160 73 Customize Your Picture Package Layout.... 162 74 Resample Your Image.................... 164

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

Extraction of Color and Texture Features of an Image

Extraction of Color and Texture Features of an Image International Journal of Engineering Research ISSN: 2348-4039 & Management Technology July-2015 Volume 2, Issue-4 Email: editor@ijermt.org www.ijermt.org Extraction of Color and Texture Features of an

More information

In the recent past, the World Wide Web has been witnessing an. explosive growth. All the leading web search engines, namely, Google,

In the recent past, the World Wide Web has been witnessing an. explosive growth. All the leading web search engines, namely, Google, 1 1.1 Introduction In the recent past, the World Wide Web has been witnessing an explosive growth. All the leading web search engines, namely, Google, Yahoo, Askjeeves, etc. are vying with each other to

More information

SCHULICH MEDICINE & DENTISTRY Website Updates August 30, Administrative Web Editor Guide v6

SCHULICH MEDICINE & DENTISTRY Website Updates August 30, Administrative Web Editor Guide v6 SCHULICH MEDICINE & DENTISTRY Website Updates August 30, 2012 Administrative Web Editor Guide v6 Table of Contents Chapter 1 Web Anatomy... 1 1.1 What You Need To Know First... 1 1.2 Anatomy of a Home

More information

CS 335 Graphics and Multimedia. Image Compression

CS 335 Graphics and Multimedia. Image Compression CS 335 Graphics and Multimedia Image Compression CCITT Image Storage and Compression Group 3: Huffman-type encoding for binary (bilevel) data: FAX Group 4: Entropy encoding without error checks of group

More information

for Q-CHECKER Text version 15-Feb-16 4:49 PM

for Q-CHECKER Text version 15-Feb-16 4:49 PM Q-MONITOR 5.4.X FOR V5 for Q-CHECKER USERS GUIDE Text version 15-Feb-16 4:49 PM Orientation Symbols used in the manual For better orientation in the manual the following symbols are used: Warning symbol

More information

animation, and what interface elements the Flash editor contains to help you create and control your animation.

animation, and what interface elements the Flash editor contains to help you create and control your animation. e r ch02.fm Page 43 Wednesday, November 15, 2000 8:52 AM c h a p t 2 Animating the Page IN THIS CHAPTER Timelines and Frames Movement Tweening Shape Tweening Fading Recap Advanced Projects You have totally

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

Elimination of Duplicate Videos in Video Sharing Sites

Elimination of Duplicate Videos in Video Sharing Sites Elimination of Duplicate Videos in Video Sharing Sites Narendra Kumar S, Murugan S, Krishnaveni R Abstract - In some social video networking sites such as YouTube, there exists large numbers of duplicate

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

EDITOR GUIDE. Button Functions:...2 Inserting Text...4 Inserting Pictures...4 Inserting Tables...8 Inserting Styles...9

EDITOR GUIDE. Button Functions:...2 Inserting Text...4 Inserting Pictures...4 Inserting Tables...8 Inserting Styles...9 EDITOR GUIDE Button Functions:...2 Inserting Text...4 Inserting Pictures...4 Inserting Tables...8 Inserting Styles...9 1 Button Functions: Button Function Display the page content as HTML. Save Preview

More information

Adaptive data hiding based on VQ compressed images

Adaptive data hiding based on VQ compressed images Adaptive data hiding based on VQ compressed images W.-C. Du and W.-J. Hsu Vision, Image and Signal Processing, IEE Proceedings 22 Aug. 2003 Volume: 150, Issue: 4 Page(s): 233-238 Presented by Benjamin

More information

Metadata-related Challenges for Realizing a Federated Searching System for Japanese Humanities Databases

Metadata-related Challenges for Realizing a Federated Searching System for Japanese Humanities Databases Metadata-related Challenges for Realizing a Federated Searching System for Japanese Humanities Databases Biligsaikhan Batjargal Ritsumeikan University, Japan biligsaikhan@gmail.com Fuminori Kimura Ritsumeikan

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

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

เพ มภาพตามเน อหาของแต ละบท. Basic of Web Design by Assoc. Prof. Churee Techawut and Dr. Ratsameetip Wita adapted into English by Dr.

เพ มภาพตามเน อหาของแต ละบท. Basic of Web Design by Assoc. Prof. Churee Techawut and Dr. Ratsameetip Wita adapted into English by Dr. เพ มภาพตามเน อหาของแต ละบท http://highlevelstudios.com/images/basic_design.jpg Basic of Web Design by Assoc. Prof. Churee Techawut and Dr. Ratsameetip Wita adapted into English by Dr. Prakarn Unachak 1.

More information

TERM BASED WEIGHT MEASURE FOR INFORMATION FILTERING IN SEARCH ENGINES

TERM BASED WEIGHT MEASURE FOR INFORMATION FILTERING IN SEARCH ENGINES TERM BASED WEIGHT MEASURE FOR INFORMATION FILTERING IN SEARCH ENGINES Mu. Annalakshmi Research Scholar, Department of Computer Science, Alagappa University, Karaikudi. annalakshmi_mu@yahoo.co.in Dr. A.

More information

APPLICATIONS OF THE SINGULAR VALUE DECOMPOSITION

APPLICATIONS OF THE SINGULAR VALUE DECOMPOSITION APPLICATIONS OF THE SINGULAR VALUE DECOMPOSITION Image Compression Let s take an image of a leader that we all know and respect: This image can be downloaded from the IAA website, after clicking on the

More information

Managing and Securing Computer Networks. Guy Leduc. Chapter 2: Software-Defined Networks (SDN) Chapter 2. Chapter goals:

Managing and Securing Computer Networks. Guy Leduc. Chapter 2: Software-Defined Networks (SDN) Chapter 2. Chapter goals: Managing and Securing Computer Networks Guy Leduc Chapter 2: Software-Defined Networks (SDN) Mainly based on: Computer Networks and Internets, 6 th Edition Douglas E. Comer Pearson Education, 2015 (Chapter

More information

Image Segmentation Based on Watershed and Edge Detection Techniques

Image Segmentation Based on Watershed and Edge Detection Techniques 0 The International Arab Journal of Information Technology, Vol., No., April 00 Image Segmentation Based on Watershed and Edge Detection Techniques Nassir Salman Computer Science Department, Zarqa Private

More information

CMPT 165 INTRODUCTION TO THE INTERNET AND THE WORLD WIDE WEB

CMPT 165 INTRODUCTION TO THE INTERNET AND THE WORLD WIDE WEB CMPT 165 INTRODUCTION TO THE INTERNET AND THE WORLD WIDE WEB Unit 3 Cascading Style Sheets (CSS) Slides based on course material SFU Icons their respective owners 1 Learning Objectives In this unit you

More information

Automatic Assessment of Japanese Text Readability Based on a Textbook Corpus

Automatic Assessment of Japanese Text Readability Based on a Textbook Corpus Automatic Assessment of Japanese Text Readability Based on a Textbook Corpus Satoshi Sato, Suguru Matsuyoshi, Yohsuke Kondoh Department of Electrical Engineering and Computer Science Graduate School of

More information

VC 17/18 TP14 Pattern Recognition

VC 17/18 TP14 Pattern Recognition VC 17/18 TP14 Pattern Recognition Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos Miguel Tavares Coimbra Outline Introduction to Pattern Recognition

More information

Manual Web Accessibility Assessment Process

Manual Web Accessibility Assessment Process STUDENT AFFAIRS & ENROLLMENT MANAGEMENT DISABILITY PROGRAMS AND RESOURCE CENTER 1600 Holloway Avenue, SSB 110 San Francisco, CA 94132 Office: 415/338-2472 Video Phone: 415/335-7210 Fax: 415/338-1041 Email:

More information

An Introduction to Pattern Recognition

An Introduction to Pattern Recognition An Introduction to Pattern Recognition Speaker : Wei lun Chao Advisor : Prof. Jian-jiun Ding DISP Lab Graduate Institute of Communication Engineering 1 Abstract Not a new research field Wide range included

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

REVIEW ON IMAGE COMPRESSION TECHNIQUES AND ADVANTAGES OF IMAGE COMPRESSION

REVIEW ON IMAGE COMPRESSION TECHNIQUES AND ADVANTAGES OF IMAGE COMPRESSION REVIEW ON IMAGE COMPRESSION TECHNIQUES AND ABSTRACT ADVANTAGES OF IMAGE COMPRESSION Amanpreet Kaur 1, Dr. Jagroop Singh 2 1 Ph. D Scholar, Deptt. of Computer Applications, IK Gujral Punjab Technical University,

More information

Home page layout in Canvas

Home page layout in Canvas Home page layout in Canvas This document describes how to change the Home page layout to a custom home page in Canvas. St e p s: 1. Click on the home tab on the left hand pane when in a course. 2. Click

More information

Interactive Video Retrieval System Integrating Visual Search with Textual Search

Interactive Video Retrieval System Integrating Visual Search with Textual Search From: AAAI Technical Report SS-03-08. Compilation copyright 2003, AAAI (www.aaai.org). All rights reserved. Interactive Video Retrieval System Integrating Visual Search with Textual Search Shuichi Shiitani,

More information

Session 3.1 Objectives Review the history and concepts of CSS Explore inline styles, embedded styles, and external style sheets Understand style

Session 3.1 Objectives Review the history and concepts of CSS Explore inline styles, embedded styles, and external style sheets Understand style Session 3.1 Objectives Review the history and concepts of CSS Explore inline styles, embedded styles, and external style sheets Understand style precedence and style inheritance Understand the CSS use

More information

An Analysis of Image Retrieval Behavior for Metadata Type and Google Image Database

An Analysis of Image Retrieval Behavior for Metadata Type and Google Image Database An Analysis of Image Retrieval Behavior for Metadata Type and Google Image Database Toru Fukumoto Canon Inc., JAPAN fukumoto.toru@canon.co.jp Abstract: A large number of digital images are stored on the

More information

Deep Web Content Mining

Deep Web Content Mining Deep Web Content Mining Shohreh Ajoudanian, and Mohammad Davarpanah Jazi Abstract The rapid expansion of the web is causing the constant growth of information, leading to several problems such as increased

More information

Contextual Information Retrieval Using Ontology-Based User Profiles

Contextual Information Retrieval Using Ontology-Based User Profiles Contextual Information Retrieval Using Ontology-Based User Profiles Vishnu Kanth Reddy Challam Master s Thesis Defense Date: Jan 22 nd, 2004. Committee Dr. Susan Gauch(Chair) Dr.David Andrews Dr. Jerzy

More information