2012 · 16 citations · 13 references
ComputingComputer ScienceComputer VisionFeature EngineeringInformation RetrievalData CompressionDigital Image ProcessingFeature ExtractionImage CompressionImage RetrievalTexture AnalysisContent-based Image RetrievalFeature FusionHistogramsStatistical Image FeaturesStatistical Texture AnalysisTexture DescriptorsTexture Feature ExtractionTexture Features
Effective Content-Based Image Retrieval (CBIR) is based on efficient low level features extraction for indexing and on effective query image matching with indexed images for retrieval of similar images. Feature extraction in compressed domain is an attractive area because at present almost all the images are represented in the compressed form using the DCT (Discrete Cosine Transformation) blocks transformation. Some critical information is removed in compression and only perceptual information is left which has significant attraction for information retrieval in the compressed domain. In this paper the statistical texture features are extracted from the quantized histograms in the DCT domain using only the DC and first three AC coefficients of the DCT blocks of image having more significant information. We study the effect of combination of texture features in effective image retrieval. We perform experimental comparison of combination of various statistical texture features to get the optimum combination of features for the effective image retrieval in terms of precision. Experiments on the Corel database using the proposed approach, give results which show that the combination of various features of quantized histograms give good performance in retrieval as compared to use single or less number of texture features combination.
13
A survey of content-based image retrieval with high-level semantics
Ying Liu, Dengsheng Zhang, Guojun Lu et al. · Pattern Recognition · 2006 · 1.7K citations
ON IMAGE CLASSIFICATION: CITY IMAGES VS. LANDSCAPES
Aditya Vailaya, Hong-Jiang Zhang · Pattern Recognition · 1998 · 387 citations