A pattern-based residual vector quantization (PBRVQ) algorithm for compressing images

The use of residual (multiple stage) vector quantizer codevectors in a nearest neighbor classifier for direct classification of image pixel data is proposed. This approach combines the successive approximation process generated by theresidual vector quantizer with sequential decision making. This approach potentially has the advantage of making large data base searches for small object or texture recognition in images both computation and memory efficient. Key Words: nearest neighbor classifier, vector quantization 1 INTRODUCTION The technical goals of counter-mine programs require that systems be developed for processing sensor data forautonomous detection and classification of mine-like objects in image data. The autonomous detection task involveslocal image decisions to discriminate between harmless and potentially hazardous subregions of an image. The au-tonomous classification task involves decisions to verify and identify potential threats. Machine-based identificationusing entire images can sometimes be achieved by very sophisticated, and often, computationally demanding algo-rithms. Machine-based classification using only small regions of an image to identify small objects is much simpler.The scope of this paper is restricted to the effective automation of the detection and classification of small objects( objects that are comprised on the order of 10 '

In this paper, we propose novel progressive scalable region of interest (ROI) image compression schemes with rate, distortion, and complexity trade-off based on vector quantization. The proposed schemes are unbalanced in the sense that the decoder has less computational requirements than the encoder. Moreover, the proposed method provides an interactive tool for fast ROI based browsing from image archives. Residual vector quantization (RVQ) equips the encoder with a multi-resolution apparatus which is useful for rate-distortion trade-of. Having all the advantages of RVQ, jointly sub-optimized RVQ provides a distortion-complexity adjustment. Since the bitstreams associated with the earlier stages of the RVQ encoder are more important for the reconstructed image quality than that of the later stages, an unequal error protection scheme, base on Reed-Solomon codes, has been considered to protect the transmitted bitstream against channel noise.

Residual vector quantization (RVQ) is a vector quantization (VQ) paradigm which imposes structural constraints on the encoder in order to reduce the encoding search burden and memory storage requirements of an unconstrained VQ. Jointly optimized RVQ (JORVQ) was introduced as an effective design algorithm for minimizing the overall quantization error. Reflected residual vector quantization (RRVQ) was introduced as an alternative design algorithm for RVQ structure with smaller computation burden. RRVQ works by imposing an additional symmetry constraint on the RVQ code book design. Savings in computation was accompanied by increase in distortion. However, it is expected that an RRVQ codebook being structured in nature, will provide lower output entropy. Therefore, we generalize RRVQ to include noiseless entropy coding. The method is referred to as Entropy-Constrained RRVQ (EC-RRVQ). Simulation results show that EC-RRVQ outperforms RRVQ by 4-dB for memoryless Gaussian and Laplacian sources. In addition, for the same synthetic sources, EC-RRVQ provided an improvement over other entropy-constrained designs, such as entropy-constrained JORVQ (EC-JORVQ). The design performed equally well on image data. In comparison with EC-JORVQ, EC-RRVQ is simpler and outperforms the EC-JORVQ.

Vector quantization is an essential tool for tasks involving large scale data, for example, large scale similarity search, which is crucial for content-based information retrieval and analysis. In this paper, we propose a novel vector quantization framework that iteratively minimizes quantization error. First, we provide a detailed review on a relevant vector quantization method named residual vector quantization (RVQ). Next, we propose generalized residual vector quantization (GRVQ) to further improve over RVQ. Many vector quantization methods can be viewed as special cases of our proposed method. To enable GRVQ on billion scale data, we introduce a nonexhaustive search scheme named aggregating tree (A-Tree) for high dimensional data that uses GRVQ encodings to build a radix tree and perform the nearest neighbor search by beam search. To search accurately and efficiently, VQ-encodings should satisfy locally aggregating encoding criterion: For any node of the corresponding A-Tree, neighboring vectors should aggregate in fewer subtrees to make beam search efficient. We show that the proposed GRVQ encodings best satisfy the suggested criterion, and the joint use of GRVQ and A-Tree shows significantly better performances on billion scale datasets. Our methods are validated on several standard benchmark datasets. Experimental results and empirical analysis show the superior efficiency and effectiveness of our proposed methods compared to the state-of-the-art for large scale search.

Competitive learning algorithms for vector quantization

This paper investigates the development of language identification based on Mel-Frequency Cepstral Coefficients (MFCC) and Vector Quantization (VQ) algorithm. In this study, a total of ten speakers were chosen randomly with different languages from online language database. A total of six males and four females were selected as subjects for this research and each of them spoke different languages, including Arabic, Chinese, English, Korean and Malay. The MFCC will be extracted to derive the related feature vector. Vector Quantization (VQ) algorithm is then used as classifier. The recognition rate is then calculated for each language. Several experiments were conducted to find the optimum parameters, in which we found that sampling frequency of 16000 Hz and codebook size of 75 provided good results. On average, the recognition rate for all five languages evaluated was 78%. The experimental results show that our proposed system provides a good recognition rate.

In this paper we study coding of video sequences at very low bitrates using an entropy-constrained variable block size residual vector quantizer. For a given complexity, it is well understood that structured vector quantizers perform better than unstructured and unconstrained vector quantizers. A combination of structured vector quantizers is used in this paper to encode the video sequences. The proposed codec uses a Discrete Cosine Transform (DCT) based transform vector quantizer and a variable-rate residual vector quantizer in cascade. The transform-VQ captures the low-frequency information using only a small portion of the bit-budget, while the later stage residual VQ captures the high-frequency information using the remaining bits. A strategy to adaptively refine only areas of high activity using recursive decomposition and selective refinement is used in the later stages. An entropy constraint is used to modify the codebooks to allow better entropy coding of the indices. Performance of the proposed codec is evaluated and compared with the H.263 based codec. Experimental results show not only better quantitative performance but also significantly better perceptual quality.

Digital image coding using vector quantization [VQ] based techniques provides low-bit rates and high quality coded images, at the expenses of intensive computational demands. The computational requirement which is due to the encoding search process had hindered application of VQ to real-time and high quality coding of color images. Reduction of the encoding search complexity through partitioning of a large code book by tree structured vector quantization [TSVQ] in the spatial domain is proposed in this paper. A. real-time TSVQ algorithm for encoding color is developed on Apollo workstation HP 9000/433. This algorithm contributes to the use of a free distortion measure and reduction of code vector dimension. The mean/quantized residual vector quantizer has been used for reducing computational complexity of the encoding search. Running at clock 33MHz, the proposed algorithm is capable of real-time processing of 512x492 pixels per frame with rate 30 frames/second. Application of this algorithm on a training image(lady face) shows the convergence with low distortion rate as shown in Fig.1(a–e).

Compared to scalar quantization (SQ), vector quantization (VQ) has memory, space-filling, and shape advantages. If the signal statistics are known, direct vector quantization (DVQ) according to these statistics provides the highest coding efficiency, but requires unmanageable storage requirements if the statistics are time varying. In code-excited linear predictive (CELP) coding, a single compromise codebook is trained in the excitation-domain and the space-filling and shape advantages of VQ are utilized in a nonoptimal, average sense. In this paper, we propose Karhunen-Loe/spl grave/ve transform (KLT)-based adaptive classified VQ (CVQ), where the space-filling advantage can be utilized since the Voronoi-region shape is not affected by the KLT. The memory and shape advantages can be also used, since each codebook is designed based on a narrow class of KLT-domain statistics. We further improve basic KLT-CVQ with companding. The companding utilizes the shape advantage of VQ more efficiently. Our experiments show that KLT-CVQ provides a higher SNR than basic CELP coding, and has a computational complexity similar to DVQ and much lower than CELP. With companding, even single-class KLT-CVQ outperforms CELP, both in terms of SNR and codebook search complexity.

We have developed novel progressive scalable region-of-interest (ROI) image compression schemes with rate-distortion-complexity tradeoff based on vector quantization. Residual vector quantization (RVQ) equips the encoder with a multi-resolution apparatus which is useful for rate-distortion tradeoff. Having all advantages of RVQ, jointly suboptimized RVQ provides a distortion-complexity adjustment. The systems are unbalanced in the sense that the decoder has less computational requirements than the encoder. The proposed jointly suboptimized RVQ method provides an interactive tool for fast ROI-based browsing from image archives.

A novel modular coding paradigm is investigated using residual vector quantization (RVQ) with memory that incorporates a modular neural network vector predictor in the feedback loop. A modular neural network predictor consists of several expert networks that are optimized for predicting a particular class of data. The predictor also consists of an integrating unit that mixes the outputs of the expert networks to form the final output of the prediction system. The vector quantizer also has a modular structure. The proposed modular predictive RVQ (modular PRVQ) is designed by imposing a constraint on the output rate of the system. Experimental results show that the modular PRVQ outperforms simple PRVQ by as much as 1 dB at low bit rates. Furthermore, for the same peak signal-to-noise ratio (PSNR), the modular PRVQ reduces the bit rate by more than a half when compared to the JPEG algorithm.

In the modern display panel manufacturing industry, the Mura problem that occurs during initial shipment has a significant impact on improving image quality. The purpose of this paper is to effectively solve these Mura defects while reducing additional production costs. We propose an innovative method of storing and compressing the De‐Mura compensation data of the display panel in external memory. Two‐dimensional compensation data compression based on machine learning using surface fitting and vector quantization is presented as an effective response to the Mura problem. This approach, which achieves up to 8:1 compression ratio while minimizing image quality degradation through vector quantization, is expected to provide economic benefits to manufacturers. The paper also introduces a new surface prediction method that replaces the existing DC‐shift and uses residual vector quantization, which can reduce the implementation complexity of vector quantization. Through experimental results, this study demonstrates that the compensated data compression technique yields excellent results in post‐compression restoration performance.

In this paper, we propose a temporal dynamic index reordering vector quantization for wavelet-based embedded coding. Da Silva et al. introduced a vector quantization concept that is similar to EZW called a successive approximation vector quantizer (SAVQ). The successive refinement process is defined as a temporal process in our proposed algorithm. The temporal updates are performed in every refinement pass, and the updates of codevectors reflect the updates of angles for vector approximation. Because the approximation trajectory of SAVQ is similar to that of the least-mean- square algorithm, temporal redundancy does not seem to be obvious. However, the redundancy becomes more clear in the improved SAVQ. By carefully analyzing the angle transitions, we are successfully able to apply dynamic index reordering vector quantization (DIRVQ) in the temporal domain and improve the coding performance. Efficient encoding and decoding algorithms for D4 lattice vector quantization are also proposed, and the algorithms can be applicable to DIRVQ to reduce the computational complexity of the reordering process. Experiments are performed with the 2x2 vector size. For almost all tested bpp's the PSNR performance of our proposed algorithm for a lena image outperforms that of SAVQ up to 0.18 dB. Improvement is measured for the highly detailed baboon image as well.

This paper will describe the vector quantization (VQ) of speech spectrum parameters as used in state of the art real time speech coding algorithms. The complexity of these speech coding algorithms, combined with the constraints of real time operation, limit the practical size of the vector quantization tables. This conflicts with the requirement that large VQ tables are needed to provide high quality coded speech. The goal of this paper is to demonstrate the feasibility of using tree searched vector quantizers to overcome this conflict.

Hidden Markov Model (HMM) algorithm and Vector Quantization (VQ) algorithm are widely used in the field of speech recognition. The innovation of this paper will be the introduction of the above two algorithms into human action recognition and making them as a solution to recognize action of the continuous multi frames video. Simulated Annealing algorithm and the empty cavity processing algorithm improve vector quantization algorithm and obtain the global optimal codebook. The recognition result of the new algorithm is much better than the original algorithm and traditional algorithms. The new method realizes the identification of abnormal behavior.