Bag-of-Visual Words Codebook Development for the Semantic Content Based Annotation of Images

摘要

The Bag-of-Visual has been recognised as an effective mean of representing images for the purpose of image classification. This paper explains that the quality and quantity of visual-words in the Bag-of-Visual Words codebook generated from an image collection should correlate to the diversity of image contents, and proposes a BOVW codebook development approach that uses the elimination of image features spatial redundancy, batch vector quantisation, and the imposition of an image feature similarity threshold function in generating a codebook that considers the content diversity of the image collection to be classified. With the aid of experimental image collections constituted from Caltech-101 Image set, this paper also demonstrates the importance of this codebook development approach in the determination of the suitable number of latent topics for the implementation of image categorisation via Probabilistic Latent Semantic Analysis for the semantic content annotation of images.