Hong Jiang Zhang

Hewlett-Packard, Palo Alto, California, United States

Are you Hong Jiang Zhang?

Claim your profile

Publications (5)3.95 Total impact

  • Qi Wei · Hong Jiang Zhang · Yu Zhuo Zhong
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a new approach for robust global motion estimation based on pre-analysis of the video content. The novel idea is to do pre-analysis of scene content based on the STGS (spatial temporal gradient scale) images derived from original image sequences. Different motion models and estimation are applied to different classes of image sequences. As a result, outliers can be removed from the dominant motion estimation, overcoming the problem of inaccurate initial descending direction estimation associated with the classical global motion estimation methods
    Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on; 02/1999
  • Source
    Wei-Ying Ma · Hong Jiang Zhang
    [Show abstract] [Hide abstract]
    ABSTRACT: A very fundamental issue in designing a content-based image retrieval system is to select the image features that best represent the image contents in a database. Such a selection requires a comprehensive evaluation of retrieval performance of image features. In this paper, we provide a detailed comparison of a number of commonly used color and texture features based on a large and diverse collection of image data. The investigated color features include color histograms, color moments, color coherence vectors and color correlogram with respect to different color spaces and quantizations. As for texture features, we compare Tamura features, edge histograms, MRSAR, Gabor texture feature, mid wavelet transform features. The result of this experiment can be used as a benchmark for selecting features in a content-based image retrieval system.
    Signals, Systems & Computers, 1998. Conference Record of the Thirty-Second Asilomar Conference on; 12/1998
  • Source
    ADITYA VAILAYA · ANIL JAIN · HONG JIANG ZHANG
    [Show abstract] [Hide abstract]
    ABSTRACT: Grouping images into semantically meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective indices can be built for an image database. In this paper, we show how a specific high-level classification problem (city images vs landscapes) can be solved from relatively simple low-level features geared for the particular classes. We have developed a procedure to qualitatively measure the saliency of a feature towards a classification problem based on the plot of the intra-class and inter-class distance distributions. We use this approach to determine the discriminative power of the following features: color histogram, color coherence vector, DCT coefficient, edge direction histogram, and edge direction coherence vector. We determine that the edge direction-based features have the most discriminative power for the classification problem of interest here. A weighted k-NN classifier is used for the classification which results in an accuracy of 93.9% when evaluated on an image database of 2716 images using the leave-one-out method. This approach has been extended to further classify 528 landscape images into forests, mountains, and sunset/sunrise classes. First, the input images are classified as sunset/sunrise images vs forest & mountain images (94.5% accuracy) and then the forest & mountain images are classified as forest images or mountain images (91.7% accuracy). We are currently identifying further semantic classes to assign to images as well as extracting low level features which are salient for these classes. Our final goal is to combine multiple 2-class classifiers into a single hierarchical classifier.
    Pattern Recognition 12/1998; 31(12-31):1921-1935. DOI:10.1016/S0031-3203(98)00079-X · 2.58 Impact Factor
  • Shih-Fu Chang · Ping Wah Wong · Hong Jiang Zhang
    Journal of Visual Communication and Image Representation 12/1998; 9(4):255. DOI:10.1006/jvci.1998.0409 · 1.36 Impact Factor
  • Source
    A. Vailaya · A. Jain · Hong Jiang Zhang
    [Show abstract] [Hide abstract]
    ABSTRACT: Grouping images into semantically meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective indices can be built for an image database. The authors show how a specific high-level classification problem (city vs. landscape classification) can be solved from relatively simple low-level features suited for the particular classes. They have developed a procedure to qualitatively measure the saliency of a feature for classification problem based on the plot of the intra-class and inter-class distance distributions. They use this approach to determine the discriminative power of the following features: color histogram, color coherence vector DCT coefficient, edge direction histogram, and edge direction coherence vector. They determine that the edge direction-based features have the most discriminative power for the classification problem of interest. A weighted k-NN classifier is used for the classification. The classification system results in an accuracy of 93.9% when evaluated on an image database of 2,716 images using the leave-one-out method
    Content-Based Access of Image and Video Libraries, 1998. Proceedings. IEEE Workshop on; 07/1998