Vector Quantization and the FSCL Training
نویسندگان
چکیده
An artiicial neural network vector quantizer is developed for use in data compression applications such as Digital Video. Two techniques are employed to improve the performance of the encoder. First, Diierential Vector Quantization (DVQ) is used to signiicantly improve edge delity. Second, an adaptive ANN algorithm known as Frequency-Sensitive Competitive Learning is used to develop an frequency-biased vector quantizer codebook so that the codevectors are roughly equiprobable. We demonstrate that, by using equiprobable vector quantization codebooks, the need for Huuman coding can be eliminated. This results in superior performance against channel bit errors than typical diierential methods that use variable length codes.
منابع مشابه
Image compression using a stochastic competitive learning algorithm (SCoLA)
In this article we introduce a new stochastic competitive learning algorithm (SCoLA) and apply it to vector quantization for image compression. In competitive learning, the training process involves presenting, simultaneously, an input vector to each of the competing neurons, which then compare the input vector to their own weight vectors and one of them is declared the winner based on some det...
متن کاملImage compression using frequency sensitive competitive neural network
Vector Quantization is one of the most powerful techniques used for speech and image compression at medium to low bit rates. Frequency Sensitive Competitive Learning algorithm (FSCL) is particularly effective for adaptive vector quantization in image compression systems. This paper presents a compression scheme for grayscale still images, by using this FSCL method. In this paper, we have genera...
متن کاملSegmentation Using a Competitive learning Neural Network for Image Coding
This paper describes a practical segmentation procedure using a simple competitive learning neural network to yield a complete segmentation suitable for segmentation-based image coding. Image segmentation here is considered as a vector quantization problem. The procedure using the FSCL neural network for the vector quantization has the two main parts, that is, primary and secondary segmentation...
متن کاملVector Quantization using Arti cial Neural Network Models yStanley
This paper focuses on recent developments in the use of Artiicial Neural Networks (ANNs) for Vector Quantization (VQ). A review of the fundamental ANN models used for VQ is presented, including Competitive Learning networks, Kohonen Self-Organizing Feature Maps, and Conscience Techniques including the FSCL algorithm. The paper also brieey reviews the use of VQ-based clustering techniques in cla...
متن کاملA Fast and Stable Cluster Labeling Method for Support Vector Clustering
Even though support vector clustering (SVC) is able to handle arbitrary cluster shapes effectively, its popularity is frequently degraded by highly intensive time complexity, poor label performance and even instability for efficiency. To overcome such problems, a fast and stable cluster labeling (FSCL) method is proposed. Based on stable equilibrium points, the FSCL first finds an appropriate d...
متن کامل