Morphological algorithms for processing tickets by hand held assay

Mingkai Hsueh, Antonio Plaza, Jing Wang, Su Wang, Wei Min Liu, Hsuan Ren, Chein I. Chang, Janet L. Jensen, James O. Jensen, Matthew A. Odom, Ryen Hydutsky, Harlan Knapp, Ray Yin

研究成果: 雜誌貢獻會議論文同行評審

4 引文 斯高帕斯(Scopus)

摘要

There is an immediate need for the ability to detect, identify and quantify chemical and biological agents in water supplies during water point selection, production, storage, and distribution to consumers. Through a U.S. Army sponsored Joint Service Agent Water Monitor (JSAWM) program, based on hand-held assays that exist in a ticket format, we are developing new algorithms for automatic processing of tickets. In previous work, detection of control dots in the tickets was carried out by traditional image segmentation approaches such as Otsu's method and other entropy-based thresholding techniques. In experiments, it was found that the approaches above were sensitive to illumination effects in the camera reader. As a result, more robust, object-oriented approaches to detect the control dots are required. Mathematical morphology is a powerful technique for image analysis that focuses on the size and shape of the objects in the scene. In this work, we describe a novel application of morphological operations in identification of control dots in hand held assay ticket imagery. Such images were pre-processed by a light compensation algorithm prior to morphological analysis. The performance of the proposed approach is evaluated using Receiving Operating Characteristics (ROC) analysis.

原文???core.languages.en_GB???
文章編號28
頁(從 - 到)221-229
頁數9
期刊Proceedings of SPIE - The International Society for Optical Engineering
5584
DOIs
出版狀態已出版 - 2004
事件Chemical and Biological Standoff Detection II - Philadelphia, PA, United States
持續時間: 27 10月 200428 10月 2004

指紋

深入研究「Morphological algorithms for processing tickets by hand held assay」主題。共同形成了獨特的指紋。

引用此