Bayesian morphological peak estimation and its application to chromosome counting via fluorescence in situ hybridization

被引：5

作者：

Dougherty, ER ^{[1
]}

Chen, YD ^{[1
]}

Waks, A ^{[1
]}

机构：

[1] AMOCO TECHNOL CO,NAPERVILLE,IL 60566

来源：

PATTERN RECOGNITION | 1996年 / 29卷 / 06期

关键词：

morphology; Bayesian estimation; top-hat transform; chromosome analysis;

D O I：

10.1016/0031-3203(95)00138-7

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The morphological top-hat transform is often used to locate bright peaks in a gray-scale image. The method can be problematic when there are two classes of peaks, one corresponding to valid objects and the other to noise (or crud). The present paper employs Bayesian estimation in conjunction with a multinomial distribution corresponding to levels of peak heights in the top-hat image to arrive at an optimal conditional-expectation estimator of the number of valid peaks. The estimation method is applied to count chromosomes in images resulting from a biotechnological technique called FISH (fluorescence in situ hybridization). (C) 1996 Pattern Recognition Society. Published by Elsevier Science Ltd.

引用

页码：987 / 996

页数：10