Neighborhood matrix: A new idea in matching of two dimensional gel images

Abstract

Automated data analysis and pattern recognition techniques are the requirements of biological and proteomicsresearch studies. The analysis of proteins consists of some stages among which the analysis of two dimensionalelectrophoresis (2-DE) images is crucial. The aim of image capturing is to generate a Photostat that can be used infuture works such as image comparison. The researchers introduced a new method for matching two 2-DE gelimages. In this method, a neighborhood circular region is defined to obtain information about spots’ neighbors. Inthe present paper, the information obtained by this region is reordered into a matrix as a descriptor of the neighborsof each spot. The matrix is then used in matching the spots between two images. All conducted tests to evaluate themethod’s performance showed the power of the method in spot matching, even when the number of candidatematching spots in the second images increased. The proposed method provides a robust automatic comparison ideain gel images matching. Despite its low speed, its accuracy is excellent. The Novelty of the present study is the useof matrices as neighborhood descriptor. This idea is applicable in any other similar domain.