Predictive classifier for image vector quantization (original) (raw)
Related papers
An improved vector quantization method for image compression
Vector quantization (VQ) is considered a common used image compression method. Due to the uncomplicated process of decompression and high compression ratio, it is widely used for network transmission or medical image storage. However, the reconstructed image after decompression has high distortion. To improve the quality of the reconstructed image without increasing computational complexity, a novel VQ method combined with Block Truncation Coding (BTC) is proposed to reduce the distortion of decompression image. The compressed codes of proposed method for an image block contain the block mean and the index recording the closest residual vector in the codebook is calculated. Moreover, a bit-plan which records the relationship between the pixels and the mean value. With the bit-plan, the residual vector can be consists of positive value only. Because the method of codebook training is a clustering approach, smaller variations within the residual vector make training more accurate. The proposed method is tested using public image. The experimental results show that the proposed method can get better Peak Signal to Noise Ratio (PSNR) without increasing the codebook size and the compression complexity.
Predictive Vector Quantization of Images
IEEE Transactions on Communications, 1985
The purpose of this paper is to present new image coding schemes based on a predictive vector quantization'(PVQ) approach. The predictive part of the encoder is used t o partially remove redundancy, and the VQ part further removes the residual redundancy and selects good quantization levels for the global waveform. Two implementations of this coding approach have been devised, namely, sliding block PVQ and block tree PVQ. Simulations on real images show significant improvement over the conventional DPCM and tree codes using these new techniques. The strong robustness property of these coding schemes is also experimentally demonstrated.
Modified Vector Quantization Method for Image Compression
Transactions On Engineering, Computing …, 2006
A low bit rate still image compression scheme by compressing the indices of Vector Quantization (VQ) and generating residual codebook is proposed. The indices of VQ are compressed by exploiting correlation among image blocks, which reduces the bit per index. A residual codebook similar to VQ codebook is generated that represents the distortion produced in VQ. Using this residual codebook the distortion in the reconstructed image is removed, thereby increasing the image quality. Our scheme combines these two methods. Experimental results on standard image Lena show that our scheme can give a reconstructed image with a PSNR value of 31.6 db at 0.396 bits per pixel. Our scheme is also faster than the existing VQ variants.
“Survey on Vector Quantization for Image Compression”
2020
This paper presents a hybrid (loss less and lossy) technique for image vector quantization. The codebook is generated in two steps and first step is training set is sorted based on the magnitudes of the training vectors and step 2 is from the sorted list, training vector from every nth position is selected to for the code vectors. Followed by that, centroid computation with clustering is done by repeated iterations to improve the optimality of the codebook. The code book thus generated is compressed (Iossy) to reduce the memory needed to store the codebook with the slight degradation in the quality of the reconstructed image. The future wireless networks, such as Centralized Radio Access Network (C-RAN), c will requirement to deliver data rate about 100 times to 1000 times the current 4G technology. For C-RAN based network layout, there is a pressing The future wireless networks, such as Centralized Radio Access Network (CRAN), will need to deliver data rate about 100 times to 1000 ...
2008
This paper presents a hybrid image compression scheme based on a block based compression algorithm referred to as Vector Quantization (VQ) combined with the Differential Pulse Code Modulation (DPCM) technique. The proposed image compression technique called the PVQ scheme results in enhanced image quality as compared to the standalone VQ. The generated codebooks for the PVQ scheme are more robust for image coding than that of the VQ. This made our system a suitable candidate for developing on chip image sensor with integrated data compression processor. The proposed system was validated through FPGA implementation. The resulting implementation achieved good compression and image quality with moderate system complexity.
New feature-based image adaptive vector-quantization coder
Coding and Signal Processing for Information Storage, 1995
It is difficult to achieve a good low bit rate image compression performance with traditional block coding schemes such as transform coding and vector quantization, without regard for the human visual perception or signal dependency. These classical block coding schemes are based on minimizing the MSE at a certain rate. This procedure results in more bits being allocated to areas which may not be visually important and the resulting quantization noise manifests as a blocking artifact. Blocking artifacts are known to be psychologically more annoying than white noise when the human visual response is considered. While image adaptive vector quantization (IAVQ) attempts to address this problem for traditional vector quantization (VQ) schemes by exploiting image dependency, it ignores the human visual perception when allocating bits. This paper addresses this problem through a new IAVQ scheme based on the human visual perception. In this method, the input image is partitioned into visual classes and each class, depending on its visual importance, is adaptively or universally encoded. The objective and subjective quality of this scheme has been compared with JPEG and a previously proposed image adaptive VQ scheme. The new scheme subjectively outperforms both schemes at low bit rates.
Novel codebook design techniques for vector quantization image compression
Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97, 1997
ABSTRACT In this paper new techniques for codebook design are presented. A new algorithm for codebook design is described. Specific characteristics of the blocks of the training sequence are taken into consideration during generation of the initial codebook. Beginning with a representative initial codebook the iterative optimization procedure converges quickly in representative final codebook which in turn leads to high output image quality. A technique for computational extension of small codebooks is also proposed. It is based on the application of simple transformations on the codewords. The reduced memory requirements of the proposed technique makes it very useful for applications requiring low-power consumption
Image restoration of compressed image using classified vector quantization
Pattern Recognition, 2002
To reduce communication bandwidth or storage space, image compression is needed. However, the subjective quality of compressed images may be unacceptable and the improvement of quality for compressed images may be desirable. This paper extends and modi"es classi"ed vector quantization (CVQ) to improve the quality of compressed images. The process consists of two phases: the encoding phase and the decoding phase. The encoding procedure needs a codebook for the encoder, which transforms a compressed image to a set of codeword-indices. The decoding phase also requires a di!erent codebook for the decoder, which enhances a compressed image from a set of codeword-indices. Using CVQ to improve a compressed image's quality is di!erent from the existing algorithm, which cannot reconstruct the high frequency components for compressed images. The experimental results show that the image quality is improved dramatically. For images in the training set, the improvement of PSNR is about 3 dB. For images, which are outside the training set, the improvement of PSNR is about 0.57 dB, which is comparable to the existing method.
A Vector Quantization–Entropy Coder Image Compression System
2001
Vector quantization (VQ) has been used extensively in the past for image compression. The quantized image can be further compressed via a standard entropy coder (such as the arithmetic coder). In this paper, we present a simple equivalent to VQ, where unsupervised neural nets (NN) are used to find the appropriate codevectors. Furthermore, by imposing additional constraints to the VQ-NN system, we match the entropy coder characteristics and improve the overall image compression by an additional 10%.
Image compression by vector quantization: a review focused on codebook generation
Image and Vision Computing, 1994
ABSTRACT Recently, vector quantization (VQ) has received considerable attention, and has become an effective tool for image compression. It provides a high compression ratio and a simple decoding process. However, studies on the practical implementation of VQ have revealed some major difficulties such as edge integrity and codebook design efficiency. After reviewing the state-of-the-art in the field of vector quantization, we focus on iterative and non-iterative codebook generation algorithms.