Content-based image retrieval is generally about understanding of information in the images concerned. The more the system is able to understand the content of images the more effective it will be in retrieving desired images. In this paper, we have developed a method that combines a clustering technique with the color correlation histogram. According to this method, an image is divided into several blocks using a xed partitioning scheme. Then, selected lower-level MPEG-7 features are used to represent the partitions and a clustering technique is applied to group similar patterns into a cluster. The cluster indices will then be used to construct a corellogram which is not based on the lower-level primitives, but on regions consisting of a distribution of primitives. The result shows that the proposed method signi cantly outperforms other methods on image retrieval and categorization.
CIREC : Cluster Correlogram Image Retrieval and Categorization using MPEG-7 Descriptors
2007-04-01
474214 byte
Conference paper
Electronic Resource
English
Enhanced Wavelet Correlogram Methods for Image Indexing and Retrieval
British Library Conference Proceedings | 2005
|Image indexing using edge orientation correlogram [3964-11]
British Library Conference Proceedings | 2000
|Correlogram-Based Perceptual Similarity in Vehicle Probabilistic Tracking
Trans Tech Publications | 2011
|The MPEG-7 Visual Descriptors: A Basic Survey
IEEE | 2013
|