A Novel Method for Cell Phenotype Image Classification

摘要

As the development of human genomic project, the life science research has entered the post-genome era. The study of the function of the encoded proteins is one of the hotspots in life-science research and protein subcellular localization is an important basis for functional study of the protein. The most common method used for determining subcellular localization of protein in cell is fluorescence microscopy. Image feature calculation has proven invaluable in the automated cell phenotype image classification. This article proposes a novel method for cell phenotype image classification which is to count the local difference features of the fluorescence images. The novel method is tested on two image sets called LOCATE Endogenous and LOCATE Transfected. A support vector machine was trained and tested for each image set and better classification accuracies were obtained on the two image sets.