Informatics Publishing Limited

S. Vinod Kumar ¹, P. Maheswari ²

Affiliations
1 PG.Department of Computer Science, Sree Saraswathi Thyagaraja College, IN
2 Department of Computer Science, Sree Saraswathi Thyagaraja College, IN

Abstract

The escalating quantity of multimedia data leads to a requirement for new sophisticated technique to extract the focused data. The traditional method – manual annotation – alone cannot keep up with the fast increase of accessible information anymore. As a result, Content-Based Image Retrieval (CBIR) systems developed to index the media documents according to the characteristics gathered from their content rather than by textual query based retrieval. Some of the features that can be considered for image retrieval are color, shape, texture, objects layout, edge direction, etc. This paper focuses on using the color feature called YUV along with the texture features using wavelet transform for image retrieval. In this paper, used YUV color space and wavelet transform approach for feature extraction. Firstly, the color space is quantified in non-equal intervals, then constructed one dimension feature vector and represented the color feature. Similarly, the texture feature extraction is obtained by using wavelet. Finally, color feature and texture feature are combined based on wavelet transform. Experimental result shows that the proposed image retrieval system results in better retrieval of images than the existing techniques.

Keywords

YUV Color Space, Texture Feature, Content-Based Image Retrieval (CBIR).

Full Text

     

P. Maheswari ¹, R. Manavalan ¹

Affiliations
1 Department of Computer Science and Applications, K.S.Rangasamy College of Arts and Science Thiruchengode, Tamilnadu, IN

Abstract

Human interaction is one of the most important characteristics of group social dynamics in meetings. The sequence of human interaction is generally represented as a tree. Tree structure is used to capture how the person interacts in meetings and to discover the interactions. The human interaction are proposing as an idea, giving comments, ask opinion, acknowledge, etc., Frequent interaction tree pattern mining algorithm and Frequent interaction sub tree pattern mining algorithm are utilized to analysis the structure and to extract interaction flow patterns, where co-occurring only the tags are considered. To overcome this problem, Sentiment Analysis (SA) is proposed work to the entire flow of interaction in meetings. A sentiment analysis approach to extract sentiments associated with opinions of positive or negative for specific subjects the from the document instead of classifying the whole document into positive or negative. Sentiment analysis approach identifies the semantic relationship between the sentiment expressions and subject properly and also improve the performance of discovering pattern of Human interactions in meetings.

Keywords

Tree Based Mining, Frequent Interaction Subtree Mining, Frequent Interaction Mining and Modified Embedded Sub Tree Mining.

Full Text