[show abstract][hide abstract] ABSTRACT: This paper presents a novel image feature representation method, namely color difference histograms (CDH), for image retrieval. This method is entirely different from the existing histograms; most of the existing histogram techniques merely count the number or frequency of pixels. However, the unique characteristic of CDHs is that they count the perceptually uniform color difference between two points under different backgrounds with regard to colors and edge orientations in L*a*b* color space. This method pays more attention to color, edge orientation and perceptually uniform color differences, and encodes color, orientation and perceptually uniform color difference via feature representation in a similar manner to the human visual system. The method can be considered as a novel visual attribute descriptor combining edge orientation, color and perceptually uniform color difference, as well as taking the spatial layout into account without any image segmentation, learning processes or clustering implementation. Experimental results demonstrate that it is much more efficient than the existing image feature descriptors that were originally developed for content-based image retrieval, such as MPEG-7 edge histogram descriptors, color autocorrelograms and multi-texton histograms. It has a strong discriminative power using the color, texture and shape features while accounting for spatial layout.
[show abstract][hide abstract] ABSTRACT: This paper presents a simple yet efficient image retrieval approach by proposing a new image feature detector and descriptor, namely the micro-structure descriptor (MSD). The micro-structures are defined based on an edge orientation similarity, and the MSD is built based on the underlying colors in micro-structures with similar edge orientation. With micro-structures serving as a bridge, the MSD extracts features by simulating human early visual processing and it effectively integrates color, texture, shape and color layout information as a whole for image retrieval. The proposed MSD algorithm has high indexing performance and low dimensionality. Specifically, it has only 72 dimensions for full color images, and hence it is very efficient for image retrieval. The proposed method is extensively tested on Corel datasets with 15,000 natural images. The results demonstrate that it is much more efficient and effective than representative feature descriptors, such as Gabor features and multi-textons histogram, for image retrieval.
[show abstract][hide abstract] ABSTRACT: This paper presents a novel image feature representation method, called multi-texton histogram (MTH), for image retrieval. MTH integrates the advantages of co-occurrence matrix and histogram by representing the attribute of co-occurrence matrix using histogram. It can be considered as a generalized visual attribute descriptor but without any image segmentation or model training. The proposed MTH method is based on Julesz's textons theory, and it works directly on natural images as a shape descriptor. Meanwhile, it can be used as a color texture descriptor and leads to good performance. The proposed MTH method is extensively tested on the Corel dataset with 15 000 natural images. The results demonstrate that it is much more efficient than representative image feature descriptors, such as the edge orientation auto-correlogram and the texton co-occurrence matrix. It has good discrimination power of color, texture and shape features.
[show abstract][hide abstract] ABSTRACT: This paper put forward a new method of co-occurrence matrix to describe image features. This method can express the spatial correlation of textons. During the course of feature extracting, we have quantized the original images into 256 colors and computed color gradient from the RGB vector space, and then calculated the statistical information of textons to describe image features. Image retrieval experimental results have shown that our proposed method has the discrimination power of color, texture and shape features, the performances are better than that of GLCM and CCG.