Automatic extraction of information from music data is an important and challenging issue in the field of content-based music retrieval. As part of the research effort, this study presents a technique that automatically identifies cover versions of songs specified by users. The technique enables users to search for songs with an identical tune, but performed by different singers, in different l...

This work presents a novel approach to content-based image retrieval in categorical multimedia databases. The images are indexed using a combination of text and content descriptors. The categories are viewed as semantic clusters of images and are used to confine the search space.

This is to certify that I have examined this copy of a master's thesis by Anand Sivaraman and have found that it is complete and satisfactory in all respects, and that any and all revisions required by the final examining committee have been made. ABSTRACT Content-based image retrieval systems retrieve images from a database that are

Texture is widely used in CBIR, and there have been a number of studies over the years to establish which features are perceptually significant. However, it is still diSJicult to retrieve reliably images that the human user would agree are “similar”. This paper reviews a range of computational methods, and compares their performance in class@ing and retrieving imagesporn the Brodatz set. Their ...

We describe the outcome of an effort to understand the behavior of content-based image retrieval (CBIR) technology by examining the behavior of a CBIR system in response to carefully constructed input query images. This work is preliminary and only considers a single CBIR system, SIMPLIcity[4]. We chose this particular system for expediency. It is our intention to develop a methodology suitable...

In this paper, we propose a novel method for cross-media semantic-based information retrieval, which combines classical textbased and content-based image retrieval techniques. This semantic-based approach aims at determining the strong relationships between keywords (in the caption) and types of visual features associated with its typical images. These relationships are then used to retrieve im...

296-220 Abstract In this paper we present a study of the comparison of the performance of content-based image retrieval systems based on structure [1] with those based on histogram and texture analysis methods, where retrieval is concerned with locating images containing manmade objects. The advantage of using structure in such queries is demonstrated by analyzing an image database containing m...

In this paper we analyze the image retrieval problem in presence of possible foreground disturbances. The foreground may be irrelevant for the retrieval but it occludes the background and hence reduces the retrieval accuracy. We propose the use of a video as a query so that the moving foreground can be extracted. The segmented foreground region is subsequently filled into increase the retrieval...