Scribd
Upload
60 views26 pages

A Study of Color Histogram Based Image Retrieval System: Under The Esteemed Guidance of

This document summarizes a study on developing a color histogram-based image retrieval system. The study aims to create a content-based image retrieval system that can automatically extract image features like color histograms to classify and retrieve similar images. It proposes using color histograms to classify images, which would be efficient, quick and robust. The study tests the technique on a database of images and finds it is effective at retrieving similar images but has some weaknesses that would need addressing for practical use.

Uploaded by

Anil Kumar Dudla
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
60 views26 pages

A Study of Color Histogram Based Image Retrieval System: Under The Esteemed Guidance of

This document summarizes a study on developing a color histogram-based image retrieval system. The study aims to create a content-based image retrieval system that can automatically extract image features like color histograms to classify and retrieve similar images. It proposes using color histograms to classify images, which would be efficient, quick and robust. The study tests the technique on a database of images and finds it is effective at retrieving similar images but has some weaknesses that would need addressing for practical use.

Uploaded by

Anil Kumar Dudla
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 26

A Study of Color Histogram Based

Image Retrieval System


Under the Esteemed guidance of V.KUMAR
M.Tech

HOD of CSE Dept.

D.VIKRAM LAKSHMI KANTH Regd No: 08811D4018

ABSTRACT

Currently the most popular search engines for images rely on the comparison of metadata or textual tags associated with the images. This methodology relies on human intervention to provide an interpretation of the image content so as to produce tags associated with the image. Content-based image retrieval systems (CBIR) is very useful and efficient if the images are classified on the score of particular aspects. The aim of this paper to develop such a color histogram based classification approach, which is efficient, quick and enough robust .

Synopsis

In this paper one of the preprocessing algorithms, the image classification is analized. In CBIR image classification has to be computationally fast and efficient. We implemented the algorithm in Java Language.
The study finds the technique to be effective as shown by analysis using the RankPower measurement. The testing also highlights the weaknesses and strengths of the model, concluding that the technique would have to be augmented and modified in order for practical use.

Existing System

Early image retrieval methods locate the desired images by matching keywords that are assigned to each image manually. Disadvantage of Existing system: we cant foresee all the query keywords that will be used in a retrieval process, it is impractical to assign keywords to every image, so the effectiveness of classic image retrieval is very limited.

Proposed System

Automatically extract metadata containing primitive features of images.

Methods to compare the similarities (or differences) between images. Techniques to efficiently index and store metadata.

Software Requirements

For front end JDK1.5 Swings For back end MS Access

Hardware Requirements:

Processor: Pentium III or Later Hard Disk: 20 GB minimum RAM: 128 MB minimum Operating System: Windows 2000 or Later

SYSTEM ARCHITECTURE

UML Diagrams
usecase diagram

A use case diagram is a diagram that shows a set of use


cases and actors and their relationships

Class Diagram

A class diagram is a diagram that shows a set of classes, interfaces, and collaborations and their relationships

Sequence diagram

State diagram

Test Case Design for GUI


Test Case Variable Expected Value

Main User Interface Menu

File Histogram

Main User Interface Body

Text Area to show upload image

Main User Interface Body

Text Area to show resulting image


Should contains two buttons to move forward & backward

Buttons

Test Case Design for Action Performed

Test Case 1 2 5 Click on file

Variable

Expected Value Should show sub menu Should show sub menu Should display dialog box Text area should display the images and two text fields are for the file name and its format Displays the file name in text field when image is selected

Click on histogram Click on open sub menu

Check text area and two text fields

Check on the file name in text field when image is selected Click on open for selecting the image

Displays the image in the user interface

Click on Global Histogram sub menu

Displays the image in the user interface with related images. Displays the dialog box for selecting image from source which has three text fields for name, source for which there is browse, and description. Text area should display the images and two text fields are for the file name and its format The image should be displayed in user interface and the prompt box is displayed with the message.

10

Click on add new image submenu

11

Click on Browse button

12

Click on insert button

Screen shots

Screen Shot for dialog box for Choose an image

Screen Shot for image displaying the image in interface

Screen Shot for Global Histogram

Calculating global histogram

Adding new image to database

dialog box when image is to be loaded in an image

Browsing the image

insertion successful for image into database

conclusion

Since most of the techniques involve the color, shape or texture for the image retrieval. The color based gives similar images for results. For the shape, there may be confusing results because two different types of images may have same shapes. Even for the texture, the resulting images may have the database has a dominant texture. Therefore it can be concluded that this project A Study on Color Histogram based Image Retrieval aims for increased usage such techniques for image retrieval. This has user friendly front end. It is designed and tested efficiently for a created database.

references

AIRS - Advanced Image Retrieval Service. http://www.imageclick.com/airs/sub/aboutAIRs.html (accessedOctober 2008). Content-based image retrieval - Wikipedia. 5 November 2008. http://en.wikipedia.org/wiki/CBIR (accessed November 8,2008). Iqbal, Qasim. CIRES: Content Based Image Retrieval System. August 2007. http://amazon.ece.utexas.edu/~qasim/research.htm (accessed November 2008). Jain, Anil K., and Aditya Vailaya. Image Retrieval UsingColor And Shape. Great Britain: Elsevier Science Ltd, 1995. Jeong, Sangoh. Histogram-Based Color Image Retrieval.Psych221/EE362 Project Report, Stanford University, 2001. Jeong, Sangoh, Chee Sun Won, and Robert M Gray. ImageRetrieval using color histograms generated by Gauss mixturevector quantization. Standford University and DonggukUniversity, Seoul: El Sevier, 2003. Meng, Xiannong. A Comparative Study of Performance Measures for Information Retrieval Systems. Third International Conference on Information Technology: New Generations (ITNG'06). 2006. 578-579. QBIC - IBM's Query By Image Content .http://wwwqbic.almaden.ibm.com/ (accessed November 2008 ).

You might also like