Classification of Protein Kinase B using discrete wavelet transform

In this paper a CAD system was designed for the classification of Protein Kinase B (PKB) using ten different discrete wavelet transforms and SSVM and SVM classifier. A set of different images has been collected from which data is divided into training and testing data set. The PKB is categorized into two classes called absent or present. The highest overall classification accuracy of 80% was obtained with biorthogonal: bior 4.4 wavelet transforms and daubechies: db6 wavelet transforms using SSVM classifier.