Fast Query Point Movement Techniques for Large CBIR Systems

Abstract—Target search in content-based image retrieval (CBIR) systems refers to finding a specific (target) image such as a particular registered logo or a specific historical photograph. Existing techniques, designed around query refinement based on relevance feedback (RF), suffer from slow convergence, and do not guarantee to find intended targets. To address these limitations, we propose several efficient query point movement methods. We prove that our approach is able to reach any given target image with fewer iterations in the worst and average cases. We propose a new index structure and query processing technique to improve retrieval effectiveness and efficiency. We also consider strategies to minimize the effects of users’ inaccurate RF. Extensive experiments in simulated and realistic environments show that our approach significantly reduces the number of required iterations and improves overall retrieval performance. The experimental results also confirm that our approach can always retrieve intended targets even with poor selection of initial query points.

Existing System

CONTENT-BASED image retrieval (CBIR) has received much attention in the last decade, which is motivated by the need to efficiently handle the immensely growing amount of multimedia data. In a typical CBIR system, low-level visual image features (e.g., color, texture, and shape) are automatically extracted for image descriptions and indexing purposes. To search for desirable images, a user presents an image as an example of similarity, and the system returns a set of similar

images based on the extracted features.

Disadvantages

Ø  No guarantee that the target can be found

Ø  Slow convergence.

Proposed system

CBIR(Content Based Image retrieval) System modern image databases are queried by image content. Relevance feedback is an interactive process, which fulfills the requirements of the query formulation.

• The user initializes a query session by submitting an image.
• The system then compares the query image to each image in the database and returns the r images that are the nearest neighbors to the query.

• If the user is not satisfied with the retrieved result, the user can activate an RF process by identifying which retrieved images are relevant and which are non relevant.
• Based on the retrieved result users can give notification to the system which is relevant and which is non relevant this will store in virtual feature
• Virtual feature can adapt that reference with that image category for future effective retrievals
• With indexing technique we can retrieve images with different concept

Advantages of Proposed System:

1. User Feedback is included

2. Reduces the unrelated searches

3. The images are searched using the image properties

4. Single Image can have multiple concepts

SYSTEM REQUIREMENT

Hardware Requirements

       Processor                     :           Pentium III / IV

            Hard Disk                   :           40 GB

            Ram                             :           256 MB

Monitor                       :           15VGA Color

            Mouse                         :           Ball / Optical

            Keyboard                    :           102 Keys

Software Requirements

Operating System       :           Windows XP professional

Front End                    :           Microsoft Visual Studio .Net 2005

Language                    :           Visual C#.Net

Back End                    :           SQL Server 2000