K. Revathy

Learn More
for the recognition of isolated handwritten Malayalam (one of the south Indian languages) characters. The key idea is that count of zero crossings of wavelet transform coefficients of an image characterize it. A set of 3000 images of 20 selected characters are used for classification. All images are normalized to have same height, binarized and inverted.(More)
—This paper deals with different techniques for registration and fusion of remote sensed images. In this work the lower spatial resolution multispectral and higher resolution panchromatic images of SPOT satellite are used. These images are registered using a registration algorithm that combines a simple yet powerful search strategy based on stochastic(More)
— Texture analysis plays an increasingly important role in computer vision. Since the textural properties of images appear to carry useful information for discrimination purposes, it is important to develop significant features for texture. Various texture feature extraction methods include those based on gray-level values, transforms, auto correlation etc.(More)
This paper deals with an image compression system for head and shoulder images which are used in photo identity cards for personal identification. The proposed Region Based Hybrid Wavelet Coding (RBHWC) method splits the images into four regions depending on their importance in recognition. Applying different wavelets and coding methods for different(More)
  • 1