Description

Image compression process is the process of reduction of the redundant and the irrelevant informations in the images. The existing methods for compression process is not completely reversible and while using for medical images the reconstructed images should be similar to the input image. The original pixel informations were not preserved since the Adaptive sparse representation process removes the redundant elements. The process is applied in 3D images and hence the processing of the image and the collection of image is a tedious process. Medical images were taken as the input and the irrelevant informations were removed from them based on lossless patch wise code formulation. The images were divided into patches and the recurrent pixels in the patches were identified. The code word for each patches were constructed and based on the code the decompression process is done. The input image is divided into patches. In the patch wise code generation the compression process is based on the pixel grouping and removing the relevant and recurrent pixels. In the proposed method the images were first reduced in size by combining the current pixel with the previous pixel. The resulting image size is nearly the half of the size of the input image. The resulting image is then divided into small patches. In the patch recurrent pixels and their locations were identified. The identified pixel locations were placed previous to the pixel value and the process is repeated for the complete image. The result of the each patch acts as the code. In the receiver side the same process is reversed in order to obtain the decompressed image. The process is completely reversible and hence the process can be employed in the transmission of the images. The performance of the process is measured in terms of the compression ratio. The performance metrics measured indicates that the proposed compression process is completely reversible and original pixel informations were well preserved.