Implementation of a color content based image retrieval system

Dissertant

Mahmud, Iman Shakir

University

University of Technology

Faculty

-

Department

Computer Sciences Department

University Country

Iraq

Degree

Master

Degree Date

2006

English Abstract

In recent times the availability of images resources on the World Wide Web has increased tremendously.

This has created a demand for effective and flexible techniques for automatic image retrieval.

The traditional technique that still in use to date is Text-Based Image Retrieval.

In this technique images are annotated and indexed using (Texts, Keywords) which the retrieval process based on it.

This technique suffer from some problems that made it inefficient and inaccurate in retrieving images , therefore; one needs to develop techniques in order to increase efficiency and effectiveness of image retrieval by analyzing images and extracting the visual content of these images .

One of these techniques is the Content-Based Image Retrieval which is an efficient way for retrieving images from the image database automatically based on their visual contents such as color, texture, and shape.

In this thesis, an analysis of the Text-based image retrieval method with its disadvantages; and a software system are designed and implemented to retrieve images by extracting features from the query image and database images by applying two methods of content-based image retrieval.

These two methods are: (l)-Contour retrieval method which retrieve images using (The Prominent Edge Point) of the images that extracted using (Global Edge Detections) and (Local Edge detection) operations.

(2)- Histogram retrieval method which retrieve images using a color histogram that extracted by performing (color space selection), (color space quantization), (histogram generation) operations.

A comparison is carried out between the two methods in order to characterize and measure their effectiveness which depend on the time of retrieval and retrieval precision as important factors.

Although the first method (contour retrieval) has more accuracy than the second method, but it takes a long time in retrieving.

Main Subjects

Information Technology and Computer Science

Topics

• Data processing
• Digital electronics

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-305867