H
Hui Zhang
Researcher at Washington University in St. Louis
Publications - 11
Citations - 1688
Hui Zhang is an academic researcher from Washington University in St. Louis. The author has contributed to research in topics: Image segmentation & Segmentation-based object categorization. The author has an hindex of 9, co-authored 10 publications receiving 1604 citations. Previous affiliations of Hui Zhang include University of Washington.
Papers
More filters
Journal ArticleDOI
Image segmentation evaluation: A survey of unsupervised methods
TL;DR: An extensive evaluation of the unsupervised objective evaluation methods that have been proposed in the literature are presented and the advantages and shortcomings of the underlying design mechanisms in these methods are discussed and analyzed.
Journal ArticleDOI
Localized Content-Based Image Retrieval
TL;DR: A localized CBIR system is presented that uses labeled images in conjunction with a multiple-instance learning algorithm to first identify the desired object and weight the features accordingly, and then to rank images in the database using a similarity measure that is based upon only the relevant portions of the image.
Proceedings ArticleDOI
An entropy-based objective evaluation method for image segmentation
TL;DR: A novel objective segmentation evaluation method based on information theory that uses entropy as the basis for measuring the uniformity of pixel characteristics (luminance is used in this paper) within a segmentation region.
Proceedings ArticleDOI
Localized content based image retrieval
TL;DR: A localized CBIR system that uses labeled images in conjunction with a multiple-instance learning algorithm to first identify the desired object and weight the features accordingly, and then to rank images in the database using a similarity measure that is based upon only the relevant portions of the image.
Proceedings ArticleDOI
A co-evaluation framework for improving segmentation evaluation
TL;DR: A co-evaluation framework is proposed, in which different effectiveness measures judge the performance of the segmentation in different ways, and their measures are combined by using a machine learning approach which coalesces the results.