Somasundaram Karuppanagounder

Learn More
We develop and test a new, two-stage, residual vector quantization algorithm using variable bit-rate encoding. In the first stage, we partition the input image into non-overlapping blocks, vector-quantize and code them by a small codebook using the well-known K-means algorithm. The novelty in this method is the use of high eigen-valued blocks as initial(More)
An efficient lossless coding scheme to encode vector quantization (VQ) indices is presented in this paper. In our scheme, we have designed a new coding model based on the schemes proposed in the previous works. The computational complexity of the method is quite low and its memory requirement is small. So that it can be implemented in hardware. The(More)
A new technique, Bi-Level Weighted Histogram Equalization (BWHE) is proposed in this paper for the purpose of better brightness preservation and contrast enhancement of any input image. This technique applies bi-level weighting procedure on Brightness preserving Bi-Histogram Equalization (BBHE) to enhance the input images. The core idea of this method is to(More)
We present a robust technique to detect a linear boundary between the cerebral hemisphere using the knowledge of brain features and magnetic resonance imaging (MRI) characteristics. We use two approaches to extract the brain from T1 and T2 MR axial head scans to find the brain contour. From the brain contour, we detect the boundary between the hemispheres(More)
In this article, a new segmentation method to extract the brain from T1, T2 and PD-weighted Magnetic Resonance Image (MRI) of human head images based on Modified Chan-Vese (MCV) active contour model is proposed. This method first segment the brain in the middle slice of the brain volume. Then, the brain regions of the remaining slices are segmented using(More)
In this paper we present a comparative study of MR brain image segmentation techniques. The aim of this study is to assess the robustness and accuracy of three most commonly used unsupervised segmentation methods k-means (KM), FCM and EM. KM is a well known hard segmentation method for quicker processing whereas FCM and EM are popularly used soft(More)
  • 1