Karuppanagounder Somasundaram

Learn More
In this paper we propose a brain extraction method that solely depends on the brain anatomy and its intensity characteristics. Using an adaptive intensity thresholding method on the MRI head scans, a binary image is obtained. The binary image is labeled using the anatomical facts that the scalp is the boundary between head and background, and the skull is(More)
The high-resolution magnetic resonance brain images often contain some nonbrain tissues (ie, skin, fat, muscle, neck, eye balls, etc) compared with the functional images such as positron emission tomography, single-photon emission computed tomography, and functional magnetic resonance imaging (MRI) scans, which usually contain few nonbrain tissues.(More)
Two sets of ischiopagus conjoined twins were successfully operated on at the University Hospital, Kuala Lumpur in 1981 and 1982. The anatomy of the organ and system malformations are discussed which determined the technique of reconstruction after surgical separation to obtain optimum cosmetic and functional results. Permanent colostomy was not required in(More)
In this paper we have proposed three and two stage still gray scale image compressor based on BTC. In our schemes, we have employed a combination of four techniques to reduce the bit rate. They are quad tree segmentation, bit plane omission, bit plane coding using 32 visual patterns and interpolative bit plane coding. The experimental results show that the(More)
A novel Modified Histogram Equalization (MHE) technique for contrast enhancement is proposed in this paper. This technique modifies the probability density function of an image by introducing constraints prior to the process of histogram equalization (HE). These constraints are formulated using two parameters which are optimized using swarm intelligence.(More)
OBJECTIVE To develop an automatic skull stripping method for magnetic resonance imaging (MRI) of human head scans. METHODS The proposed method is based on gray scale transformation and morphological operations. RESULTS The proposed method has been tested with 20 volumes of normal T1-weighted images taken from Internet Brain Segmentation Repository.(More)
Block Truncation Coding (BTC) is one of the lossy image compression techniques. The computational complexity involved in this method is very simple. In the proposed method, the feature of inter-pixel correlation is exploited to further reduce the requirement of bits to store a block. The proposed method gives very good performance in terms of bit-rate and(More)
One of the main area under medical research is the analysis of brain image. A lot of researches are going on for segmenting the brain images automatically. Hippocampus is an important component of brain which plays an important role in the normal behaviour of the human beings. It is a new region of research now. It takes many hours for a specialist in this(More)