You are on page 1of 6

A

Seminar Report

on

Texture Based Image Retrieval


Submitted for the partial fulfilment of BE CSE Final Year

Submitted By: Guide :


VIJAY KUMAR JOSHI Dr. Alok Singh Gahlot
B.E. Final Year (CSE) (Assistant Professor)
Roll No.: 15CSE53036
Enroll. No: 14R/00030
Department of Computer Science and Engineering
MBM Engineering College, Faculty of Engineering & Architecture,
Jai Narain Vyas University
Jodhpur (Rajasthan)
Session 2017-18
CERTIFICATE

This is to certify that report entitled “Texture Based Image Retrieval” submitted to Department
of Computer Science and Engineering, MBM Engineering College, JNV University in partial
fulfilment of the requirements for the award of the degree of Bachelors of Engineering in Computer
Science is the work done by Mr. Vijay Kumar Joshi under my supervision and guidance.

Dr. Alok Singh Gahlot


(Assistant Professor)

III
DECLARATION
I, Vijay Kumar Joshi hereby declare that this seminar report titled “Texture Based Image
Retrieval” is a record of original work done by me under the supervision and guidance of Dr. Alok
Singh Gahlot. I further declare that this seminar work has not formed the basis for the award of
the Degree/Diploma/Associateship/Fellowship or similar work to any candidate of any university
and no part of this report is reproduced as it is from any other source without seeking permission.

Vijay Kumar Joshi


Roll no - 15CSE53036
Enroll. No – 14R/00030

II
Table of Contents

Acknowledgement v
Abstract vi

1. INTRODUCTION 1
1.1 Definition
1.2 History

2. Image Retrieval Techniques 3


2.1 Text Based
2.2 Content Based
2.3 Multimodal Fusion
2.4 Semantic Based
2.5 Relevance Feedback
3. Applications 6
3.1 Medical
3.2 Biodiversity Information System
3.3 Digital Libraries
4. Image Retrieval Feature Extraction 8
4.1 Color
4.2 Texture
4.3 Shape
4.4 Segmentation
5. Texture Based Image Retrieval using Local Binary Edge Pattern 15
5.1 Brief Review
5.2 Feature Extraction Process
5.3 Edge Detection
5.4 LBEP Calculation
6. Texture Based Image Retrieval for Computerized 19
Tomography Databases
6.1 Background
6.2 Methodology
6.3 Experimental Results
6.4 Texture Features
6.5 Similarity measures
6.6 Evaluation of results
6.7 Conclusion on future works

REFERENCE 26
IV
ACKNOWLEDGEMENT

The satisfaction that accompanies with the successful completion of this seminar would be
incomplete without the mention of people whose ceaseless cooperation made it possible, whose
constant guidance and encouragement crown all efforts with success. I am grateful to my
seminar guide Dr. Alok Singh Gahlot for the guidance, inspiration and constructive suggestions
that was helpful in the preparation of this project. Last but not the least I wish to avail myself of
this opportunity to express a sense of gratitude and love to my friends and my beloved parents
for their strength and support. I have tried my level best to make this seminar report error free,
but I regret for errors, if any.

V
ABSTRACT
This report presents a brief analysis of the main techniques used for image retrieval, while pointing
out the importance of this emerging technology. Due to the alarming growth of the Internet and
the high volume of data, we emphasize the technique of Texture based image retrieval, CBIR -
Content-Based Image Retrieval. For the case study, we developed one application of this technique
over an image database using the Euclidean Distance metric. Image segmentation is not only hard
and unnecessary for texture-based image retrieval, but can even be harmful. Images of either
individual or multiple textures are best described by distributions of spatial frequency descriptors,
rather than single descriptor vectors over pre-segmented regions. A retrieval method based on the
Earth Movers Distance with an appropriate ground distance is shown to handle both complete and
partial multi-textured queries. As an illustration, different images of the same type of animal are
easily retrieved together. At the same time, animals with subtly different coats, like cheetahs and
leopards, are properly distinguished.

VI

You might also like