Mining User Queries with Markov Chains: Application to Online Image Retrieval

Rs- Contact for OFFER Price

Get Project

Project Summary

Price:- Contact for OFFER Price

AvailabilityYes

Year of Project2013

SRS.NET

Project Detail

Mining User Queries with Markov Chains: Application to Online Image Retrieval IEEE Projects 2013 | Final year projects | BE Projects | Abstract: We propose a novel method for automatic annotation, indexing and annotation-based retrieval of images. The new method, that we call Markovian Semantic Indexing (MSI), is presented in the context of an online image retrieval system. Assuming such a system, the users’ queries are used to construct an Aggregate Markov Chain (AMC) through which the relevance between the keywords seen by the system is defined. The users’ queries are also used to automatically annotate the images. A stochastic distance between images, based on their annotation and the keyword relevance captured in the AMC, is then introduced. Geometric interpretations of the proposed distance are provided and its relation to a clustering in the keyword space is investigated. By means of a new measure of Markovian state similarity, the mean first cross passage time (CPT), optimality properties of the proposed distance are proved. Images are modeled as points in a vector space and their similarity is measured with MSI. The new method is shown to possess certain theoretical advantages and also to achieve better Precision versus Recall results when compared to Latent Semantic Indexing (LSI) and probabilistic Latent Semantic Indexing (pLSI) methods in Annotation-Based Image Retrieval (ABIR) tasks.

EVEN though humans tend to associate images with high level concepts, the current computer vision techniques extract from images mostly low-level features and the link between low-level features and high-level semantics of image content is lost. Neither a single low-level feature nor a combination of multiple low-level features has explicit semantic meaning in general. In addition, the similarity measures between visual features do not necessarily match human perception and, thus, retrieval results of low-level approaches are generally unsatisfactory and often unpredictable. This is what is called the semantic gap: the lack of coincidence between the information that one can extract from the visual data and the interpretation that the same data have for a user in a given situation. However, the retrieval process fails also due to the sensory gap: the gap between the object in the world and the information in a (computational) description assigned to a recording of that object. While the former gap brings in the issue of users’ interpretations of images and how it is inherently difficult to capture them in visual content, the latter gap makes recognition from image content challenging due to limitations in recording and description capabilities. Currently, only 10 percent of online image files have a professional description (annotation). As a result, image search engines are only able to deliver precision of around 42 percent and recall of around 12 percent, while 60 percent of search engine visitors use at least two different search engines since they are not satisfied by the retrieved content. The most common complaint is that search engines do not recognize content semantics. Additionally, about 77 percent of searchers change keywords more than once because they cannot detect content of interest.

“SPEND LESS SCORE MORE”

Final Year Projects for all Computer Science Degrees, We provide Full Source Code, Complete Documentation and 24/7 Support for Online Configuration – Execution.

Most Affordable …..!!!!!
7 Years of Expertise …..!!!!!
More Than 1200 Projects …..!!!!!
More Than 4000 Facebook Fans …..!!!!!
24/7 Online Support for Execution …..!!!!!

As a part of project you will get below mentioned documentation along with SOURCE CODE,

1). BIBLIOGRAPHY
2). CONCLUSION
3). HARDWARE SOFTWARE SPECIFICATION
4). IMPLEMENTATION
5). INPUT DESIGN &OUTPUT DESIGN
6). INTRODUCTION
7). LITERATURE SURVEY
8). SCREENSHOT
9). SOFTWARE ENVIRONMENT
10). SYSTEM ANALYSIS
11). SYSTEM DESIGN
12). SYSTEM STUDY
13). SYSTEM TESTING

WE RUN PROJECT IN YOUR SYSTEM via TEAM VIEWER and SKYPE.

Need more details?
Email us : info@thebookmyproject.com OR ieee.project7@gmail.com
Call us : +91 98450 91623

Please refer your friends if they are looking for any projects.

Mining User Queries with Markov Chains: Application to Online Image Retrieval

Mining User Queries with Markov Chains: Application to Online Image Retrieval

Technology: DOT NET and DOT NET IEEE PROJECTS.Project Tags: Cloud Computing, Final Year Projects, IEEE 2013 Projects, and KNOWLEDGE AND DATA ENGINEERING-DATA MINING.

Send To Friend

Get Project

Related Projects

Your Reviews