Mining User Queries with Markov Chains: Application to Online Image Retrieval
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.
Annotation-Based Image Retrieval (ABIR) systems are an attempt to incorporate more efficient semantic content into both text-based queries and image captions (i.e. Google Image Search, Yahoo! Image Search). The Latent Semantic Indexing (LSI)-based approaches that were initially applied with increased success in document indexing and retrieval were incorporated into the ABIR systems to discover a more reliable concept association.
DISADVANTAGES OF EXISTING SYSTEM:
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.
A reason for this lies in the sparsity of the per-image keyword annotation data in comparison to the number of keywords that are usually assigned to documents.
We introduce the Markovian Semantic Indexing (MSI), a new method for automatic annotation and annotation based image retrieval. The properties of MSI make it particularly suitable for ABIR tasks when the per image annotation data is limited. The characteristics of the method make it also particularly applicable in the context of online image retrieval systems.
ADVANTAGES OF PROPOSED SYSTEM:
The targeting is more accurate, compared to other systems that use external means of non-dynamic or non-adaptive nature to define keyword relevance.
MSI achieves better retrieval results in sparsely annotated image data sets. A comparison to LSI on 64 images gathered from the Google Image Search and annotated in a transparent way by the proposed system, revealed certain advantages for the MSI method, mainly in retrieving images with deeper dependencies than simple keyword co-occurrence
- System : Pentium IV 2.4 GHz.
- Hard Disk : 40 GB.
- Monitor : 15 inch VGA Colour.
- Mouse : Logitech Mouse.
- Ram : 512 MB
- Keyboard : Standard Keyboard
- Operating System : Windows XP.
- Coding Language : ASP.NET, C#.Net.
- Database : SQL Server 2005
Konstantinos A. Raftopoulos,Member, IEEE, Klimis S. Ntalianis, Dionyssios D. Sourlas, and Stefanos D. Kollias,Member, IEEE “Mining User Queries with Markov Chains: Application to Online Image Retrieval” – IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 25, NO. 2, FEBRUARY 2013.