Multimedia information systems require efficient storage of and access to the images in a database. Recently, several image indexing techniques have been reported in the literature. Although these techniques combine image compression and image indexing, additional computational and storage costs are required to compute and store the indices. In this paper, we propose a new technique based on wavelet vector quantization for the storage and retrieval of compressed images. Here, the images are first decomposed using wavelet transform followed by vector quantization of the transform coefficients. We note that similar images map to similar codewords. Hence, the labels corresponding to a wavelet-vector-quantized image constitute a feature vector which is used as an index to store and retrieve the image. In addition, the lowest-resolution subimage resulting from the wavelet decomposition serves as a visual icon for browsing purposes. We note that the index is generated at compression time and, hence, the proposed technique eliminates the need for a separate structure to store the indices. This increases the storage efficiency and provides fast access to the compressed images in the database.
ASJC Scopus subject areas
- Language and Linguistics
- Human-Computer Interaction
- Computer Science Applications