Aibing Rao

Spatial color histograms for content-based image retrieval

The color histogram is an important technique for color image database indexing and retrieval. In this paper, the traditional color histogram is modified to capture the spatial layout information of each color, and three types of spatial color histograms are introduced: annular, angular and hybrid color histograms. Experiments show that, with a proper trade-off between the granularity in the color and spatial dimensions, these histograms outperform both the traditional color histogram and some existing histogram refinements such as the color coherent vector.

Keyblock: an approach for content-based image retrieval

We propose a new framework termed Keyblock for content-based image retrieval, which is a generalization of the text-based information retrieval technology in the image domain. In this framework, methods for extracting comprehensive image features are provided, which are based on the frequency of representative blocks, termed keyblocks, of the image database. Keyblocks, which are analogous to index terms in text document retrieval, can be constructed by exploiting the vector quantization (VQ) method which has been used for image compression. By comparing the performance of our approach with the existing techniques using color feature and wavelet texture feature, the experimental results demonstrate the effectiveness of the framework in image retrieval.

Advanced feature extraction for Keyblock-based image retrieval

Keyblock, which is a new framework we proposed for content-based image retrieval, is a generalization of the text-based information retrieval technology in the image domain. In this framework, keyblocks, which are analogous to keywords in text document retrieval, can be constructed by exploiting the Vector Quantization (VQ) method which has been used for image compression. Then an image can be represented as a code matrix in which the elements are the indices of keyblocks in a codebook. Based on this image representation, information retrieval and database analysis techniques developed in the text domain can be generalized to image retrieval. In this paper, we propose new models named N-block models which are the generalization of the N-gram models in language modeling to extract comprehensive image features. The effort to capture context in a text document motivated the N-gram models. Similarly, the attempt to capture the content in an image motivates us to consider the correlations of keyblocks within an image. By comparing the performance of our approach with conventional techniques using color feature and wavelet texture feature, the experimental results demonstrate the effectiveness of these N-block models.

Image background search: combining object detection techniques with content-based image retrieval (CBIR) systems

A framework for combining object detection techniques with a content based image retrieval (CBIR) system is discussed. As an example, a special CBIR system which focuses on human faces as foreground and decides the similarity of images based on background features is presented. This system may be useful in automatically generating albums from consumer photos.

Using thesaurus to model keyblock-based image retrieval

Keyblock, which is a new framework we proposed for content-based image retrieval, is a generalization of the textbased information retrieval technology in the image domain. In this framework, keyblocks, which are analogous to keywords in text document retrieval, can be constructed by exploiting the method of Vector Quantization (VQ). Then an image can be represented as a list of keyblocks similar to a text document which can be considered as a list of keywords. Based on this image representation, various feature models can be constructed for supporting image retrieval. In this paper, we present a new feature representation model which use the keyblock-keyblock correlation matrix, termed keyblock-thesaurus, to facilitate the image retrieval. The feature vectors of this new model incorporate the effect of correlation between keyblocks, thus being more effective in representing image content.

A method for measuring the complexity of image databases

We present a framework for measuring the complexity of image databases, which characterizes the databases for image retrieval. Motivated from the concept of text corpus perplexity, the complexity of image databases is formulated based on image database statistics and information theory. We propose a quantitative metric which can be used to measure the degree of difficulty to retrieve images based on contents of the database. This metric is independent of queries, hence, it is objective. Experiments on both synthetic and real-world images demonstrate that the proposed measurement is highly effective in quantitatively measuring the contents of image databases for content-based retrieval.

A model for multimodal information retrieval

Finding useful information from large multimodal document collections such as the WWW without encountering numerous false positives poses a challenge to multimodal information retrieval systems (MMIR). A general model for multimodal information retrieval is proposed by which a users information need is expressed through composite, multimodal queries, and the most appropriate weighted combination of indexing techniques is determined by a machine learning approach in order to best satisfy the information need. The focus is on improving precision and recall in a MMIR system by optimally combining text and image similarity. Experiments are presented which demonstrate the utility of individual indexing systems in improving overall average precision.

Face detection and its applications in intelligent and focused image retrieval

This paper presents a face detection technique and its applications in image retrieval. Even though this face detection method has relatively high false positives and a low detection rate (as compared with the dedicated face detection systems in the literature of image understanding), because of its simple and fast nature, it has been shown that this system may be well applied in image retrieval in certain focused application domains. Two application examples are given: one combining face detection with indexed collateral text for image retrieval regarding human beings, and the other combining face detection with conventional similarity matching techniques for image retrieval with similar background. Experimental results show that our proposed approaches have significantly improved image retrieval precision over existing search engines in these focused application domains.

Advanced feature extraction for keyblock-based image retrieval

Keyblock, which is a new framework we proposed for content-based image retrieval, is a generalization of the text-based information retrieval technology in the image domain. In this framework, keyblocks, which are analogous to keywords in text document retrieval, can be constructed by exploiting the vector quantization method which has been used for image compression. Then an image can be represented as a code matrix in which the elements are the indices of the keyblocks in a codebook. Based on this image representation, information retrieval and database analysis techniques developed in the text domain can be generalized to image retrieval. In this paper, we present new models named n-block models which are the generalization of the n-gram models in language modeling to extract comprehensive image features. The effort to capture context in a text document motivated the n-gram models. Similarly, the attempt to capture the content in an image motivates us to consider the correlations of keyblocks within an image. By comparing the performance of our approach with conventional techniques using color feature and wavelet texture feature, the experimental results demonstrate the effectiveness of these n-block models.

Geometric histogram: a distribution of geometric configurations of color subsets

Spatial distribution of color is very important for refining color histograms use din indexing and retrieving color images. Existing histogram refinement techniques are based on the spatial distribution of a single color or color pair. In this paper, the concept of spatial distribution of a subset of colors, which is defined as the occurrence of different geometric configurations of the color set, is used to provide new clues for refining traditional color histogram. The concept is a unification of some existing techniques such as color density maps, color correlogram and color tuples. Experimental results demonstrate that triangular geometric histogram, on e of the simplest special cases of geometric histograms, which is defined as the occurrence of a list of isosceles right triangles of different side lengths of color triples, is more desirable than existing techniques for content-based image retrieval, especially when the database in question consists of on-line color images which are extremely heterogenous in terms of the content of images, camera types, lighting conditions and so on.