Authors: P.S. Hiremath, Parashuram Bannigidad
Addresses: Department of Computer Science, Gulbarga University, Gulbarga, Karnataka, India. ' Department of Computer Science, Govt. Degree College, Gulbarga 585 105, Karnataka, India
Abstract: In cytology, automating the feature extraction process yields an objective, quantitative, detailed and reproducible computation of cell morphofunctional characteristics and allows the analysis of a large quantity of images. The objective of the present study is to develop an automatic tool to identify and classify the different types of cocci bacterial cells in digital microscopic cell images. Geometric features are used to identify the arrangement of cocci bacterial cells, namely cocci, diplococci, streptococci, tetrad, sarcinae and staphylococci using 3σ, K-NN and Neural network classifiers. The current methods rely on the subjective reading of profiles by a human expert based on the various manual staining methods. In this paper, we propose a method for cocci bacterial cell classification by segmenting digital bacterial cell images and extracting geometric and statistical features for cell classification. The experimental results are compared with the manual results obtained by microbiology expert and other methods in the literature.
Keywords: cell classification; segmentation; bacterial image analysis; cocci; diplococci; streptococci; tetrad; sarcinae; staphylococci; K-NN classifier; neural networks; classifiers; cytology; feature extraction; cell images; bacterial cells; digital microscopy; digital microscopic images.
International Journal of Computational Biology and Drug Design, 2011 Vol.4 No.3, pp.262 - 273
Available online: 21 Jul 2011Full-text access for editors Access for subscribers Purchase this article Comment on this article