A New Approach to Automatic Classification of the Curved Chromosomes

In this paper, an effective algorithm for chromosome image processing for straightening the curved chromosomes is presented. This is a very helpful procedure which extends the domain of success of most of the previously reported algorithms to highly curved chromosomes. The procedure is based on the calculation and analyzing the vertical and horizontal projection vectors of the binary image of the chromosome. The binary image is obtained by thresholding the input image after histogram modification. When applied to the real chromosome images the proposed algorithm could straighten all of the highly bent curved chromosomes within the image dataset. To assess the effectiveness of proposed algorithm, a neural network based chromosome classification system is developed. Wavelet transform domain features are extracted and used in an MLP structure for this purpose and a classification rate of 95.3% is obtained.