Call For Paper Volume:4 Issue:8 Aug'2017 |

Multimedia Answer Generation and User Queries Mining with Markov Chains for Annotation Based Image Retrieval

Publication Date : 19/05/2015



Author(s) :

ARISHMA RANE , Prof. Prabhakara B. K..


Volume/Issue :
Volume 2
,
Issue 5
(05 - 2015)



Abstract :

An approach that allows community members to post queries and answer the questions is the community question answering (cQA) service. This service has gained popularity over the past few years. It also enables general users to seek information from a comprehensive set of well answered questions. But however existing cQA system provides the user with only textual answers, these may not be informative enough for many questions. In this paper, we propose a scheme that is able to enrich multimedia data in addition to only textual data. This approach helps to automatically determine which type of multimedia data should be added to the textual answer. Here we also propose a new method for automatic indexing, annotation and annotation-based retrieval of images. The new method, Markovian Semantic Indexing (MSI), is presented in context of online image retrieval system. User queries are used to construct an Aggregate Markov Chain (AMC) by which it helps to define the relevance between the keywords seen by the system. This approach is built based on community contributed textual answers and therefore is able to deal with more complex queries.


No. of Downloads :

25


Indexing

Web Design MymensinghPremium WordPress ThemesWeb Development

Multimedia Answer Generation and User Queries Mining with Markov Chains for Annotation Based Image Retrieval

May 15, 2015