Summary
This paper presents a lossy compression scheme for biomedical images by using a new method. Image data compression using Vector Quantization (VQ) has received a lot of attention because of its simplicity and adaptability. VQ requires the input image to be processed as vectors or blocks of image pixels. The Finite-state vector quantization (FSVQ) is known to give better performance than the memory less vector quantization (VQ). This paper presents a novel combining technique for image compression based on the Hierarchical Finite State Vector Quantization (HFSVQ) and the neural network. The algorithm performs nonlinear restoration of diffraction-limited images concurrently with quantization. The neural network is trained on image pairs consisting of a lossless compression named hierarchical vector quantization. Simulations results are presented that demonstrate improvements in visual quality and peak signal-to-noise ratio of the restored images.
See the full content of this document
Extract
Medical Image Compression by Using Vector Quantization Neural Network (Vqnn)
1. Introduction
Medical images, like magnetic resonance (MR) and computer tomography (CT) acquired from various modalities, comprise huge amounts of data, rendering them impracticable for storage and transmission. At each examination, 40-50 MR or CT images are needed for only one patient. If each image has 256 X 256 pixels and 256 gray levels, 65536 bytes of memory are needed for an image. In an average sized hospital, many terra- bytes of digital imaging da...See the full content of this document
Sponsored links
