Bacilli bacterial cell image analysis using active contour segmentation with SVM classifier
Languages of publication
The main aim of the present study is to develop an automatic method to identify and classify the different cell types of bacilli bacterial cells in digital microscopic cell images using active contour method. Snakes, or active contours, are used widely in computer vision and machine learning applications, particularly to locate object boundaries. GLCM, HOG and LBP features are used to identify the arrangement of bacilli bacterial cells, namely, bacillus, cocobacilli, diplobacilli, palisades and streptobacilli using SVM classifier. The current methods rely on the subjective reading of profiles by a human expert based on the various manual staining methods. In this paper, it is proposed a method for bacilli bacterial cell classification by segmenting digital bacterial cell images using active contour model and extracting GLCM, HOG and LBP features. The experimental results proves that, the SVM classifier has yielded an overall accuracy of 97.2% with GLCM features, HOG features has yielded an accuracy of 74.8% and LBP features yielded 91.2% accuracy. The GLCM features with SVM classifier has got good classification results compared to HOG and LBP feature sets for bacilli bacteria cell types.
-  Sigal Trattner and Greenspan, Automatic Identification of Bacterial Types Using Statistical Imaging methods, IEEE Transactions on Medical Imaging, Vol. 23(7), 807-820 (2004)
-  Nicholas, B., Åke, H., Johan, W., Rocio, C-H. and Peter, K.B. (1998). Rapid determination of bacterial abundance, Biovolume, Morphology, and Growth by Neural Network-based Image Analysis. Applied and Environmental Microbiology, Vol. 64, No. 9, pp. 3246-3255
-  Perner P. (2001) Classification of HEp-2 Cells Using Fluorescent Image Analysis and Data Mining. In: Crespo J., Maojo V., Martin F. (eds) Medical Data Analysis. ISMDA 2001. Lecture Notes in Computer Science, vol 2199. Springer, Berlin, Heidelberg
-  Carolina Wahlby, Joakim, L., Mikael, V., Ewert, B. and Lennart, B. (2002). Algorithms for cytoplasm segmentation of fluorescence labeled cells. Analytical Cellular Pathology, 24, 101-111 (2002).
-  Venkataraman, S., Allison, D.P., Qi, H., Morrell-Falvey, J.L., Kallewaard, N.L., Crowe Jr., J.E. and Doktycz, M.J. (2006). Automated image analysis of atomic microscopy images of rotavirus particles. Ultramicroscopy, Vol. 106, 829-837 (2006).
-  Hiremath P. S. and Parashuram Bannigidad. Automatic Identification and Classification of Bacilli Bacterial Cell Growth Phases. IJCA Special Issue on Recent Trends in Image Processing and Pattern Recognition, 2010, Vol. 1 (2), pp. 48-52.
-  Thomas, P., Josef, F., Martin, P. and Michaela, M.S. (2009). New image analysis tool to study biomass and morphotypes of three major bacterioplankton groups in an alpine lake. Aquatic Microbiol Ecology, Vol. 54, 113-126
-  Tony F Chan, Luminita A. Vese, Active contours without edges IEEE Transaction on Image Processing, Vol. 10, No. 2, February 2001.
-  Chenyang Xu, Jerry L Prince, Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing, Vol. 7, No. 3, March 1998. 359-369
-  Michael Kass, Andrew Witkin and Demetri Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, 1998, pp. 321-331.
-  Hiremath P.S. and Parashuram Bannigidad. Automated Gram-staining Characterization of Bacterial Cells using Color and Cell Wall Properties. International Journal of Biomedical Engineering and Technology 2011, Vol. 7, No. 3, pp. 257-265
-  Hiremath P.S. and Parashuram Bannigidad Automatic Identification and classification of Cocci bacterial cells using digital Microscopic images. International Journal of Computational Biology and Drug Design 2011, Vol. 4, No. 3, pp. 262-273
Publication order reference