Vector Quantization

... 870 JZC Lai Image and Vision Computing 15 (1997) 867871 Table 2 The execution time of enci ading a real image (tiffany) for 3 different algorithms' Number of codewords Available encoding algorithm (seconds) EAWFC (seconds) E c AWFS with = 3 (seconds) Speedup ...

Learning Vector Quantization (LVQ) is a popular class of nearest prototype classifiers for multiclass classification. Learning algorithms from this family are widely used because of their intuitively clear learning process and ease of implementation. They run efficiently and in many cases provide state of the art performance. In this paper we propose a modification of the LVQ algorithm that addresses problems of determining appropriate number of prototypes, sensitivity to initialization, and sensitivity to noise in data. The proposed algorithm allows adaptive addition of prototypes at potentially beneficial locations and removal of harmful or less useful prototypes. The prototype addition and removal steps can be easily implemented on top of the many existing LVQ algorithms. Experimental results on synthetic and benchmark datasets showed that the proposed modifications can significantly improve LVQ classification accuracy while at the same time determining the appropriate number of prototypes and avoiding the problems of initialization.

We propose a new algorithm for vector quantization, the Activity Equalization Vector quantization (AEV). It is based on the winner takes all rule with an additional supervision of the average node activities over a training interval and a subsequent re-positioning of those nodes with low average activities. The re-positioning is aimed to both an exploration of the data space and a better approximation of already discovered data clusters by an equalization of the node activities. We introduce a learning scheme for AEV which requires as previous knowledge about the data only their bounding box. Using an example of Martinetz et al. , AEV is compared with the Neural Gas, Frequency Sensitive Competitive Learning (FSCL) and other standard algorithms. It turns out to converge much faster and requires less computational effort.

In the recent years, Internet multimedia applications have become very popular. Valuable multimedia content such as digital images, however, is vulnerable to unauthorized access while in storage and during transmission over a network. Streaming digital images also require high network bandwidth for transmission. For effective image transmission over Internet; therefore, both security and bandwidth issues must be considered. In this paper, we present a novel scheme, which combines Discrete Wavelet Transform (DWT) for image compression and block cipher Data Encryption Standard (DES) for image encryption. The simulation results indicate thaf our proposed method enhances the security for image transmission over the Internet as well as improves the transmission rate.

This thesis encapsulates a study conducted to use Automatic Speech Recognition (ASR) techniques to identify dog barks from ambient recordings. To achieve this, four different classifiers are developed. The first of which relies on cross-correlation, the second on Vector Quantisation (VQ) and the third on an Artificial Neural Network (ANN). The output of each classifier is fed into a fourth ‘Jury’ classifier which determines the overall identification decision.

Mel Frequency Cepstral Coefficients (MFCCs) are used extract features from each recording. The extraction process is optimised by using 30 mel filters spread from 0 to 14 KHz and 15 cepstral coefficients alongside delta features.

The VQ classifier performed the most inconsistently, with little robustness to its applied parameters. Furthermore, its performance degraded considerably when additive white Gaussian noise was introduced in tests. The ANN displayed consistent and robust results.

Of the 537 analysed instances used to test the classifiers, 493 were correctly identified with 22 false positives and 22 false negatives. A second trial was conducted on unseen data in which 61 of the 73 recordings were correctly identified. In both cases a sensitivity of over 89% and specificity of 77% was achieved.

The study successfully concludes that human ASR techniques apply extremely well, and that the use of combining the output of multiple classifiers bolsters performance.

A simple yet complex approach to modern sophistication.
In this project we used the MFCC approach to build a unique and accurate coefficients extracting processor to extract feature from the voice stored in the database, then on the next stage we again emoployed the use of MFCC to extract coefficients and used vector quantization to match with the user database. For vector Quantization we used Linde-Buzo Grey Algorithm..
Code is available on demand. Send me a private message if you want it.

Compression is the art of representing the information in a compact form rather than in its original or uncompressed form. In other words, using the data compression, the size of a particular file can be reduced. This is very useful when processing, storing or transferring a huge file, which needs lots of resources. If the algorithms used to encrypt work properly, there should be a significant difference between the original file and the compressed file. When the data compression is used in a data transmission application, speed is the primary goal. The speed of the transmission depends on the number of bits sent, the time required for the encoder to generate the coded message, and the time required for the decoder to recover the original ensemble. In a data storage application, the degree of compression is the primary concern. Compression can be classified as either lossy or lossless.
Image compression is a key technology in the transmission and storage of digital images because of vast data associated with them. This research suggests an effective approach for image compression using Stationary Wavelet Transform (SWT) and Vector Quantization which is a Linde Buzo Gray (LBG) vector quantization in order to compressed input images in four phases; namely preprocessing, image transformation, zigzag scan, and lossy/lossless compression. Preprocessing phase takes images as input, so that the proposed approach resize the image in accordance with the measured rate of different sizes to (8 × 8) And then converted from (RGB) to (gray scale). Image transformation phase received the resizable gray scale images and produced transformed images using SWT. Zigzag scan phase takes as an input the transformed images in 2D matrix and produced images in 1D matrix. Finally, in lossy/lossless compression phase takes 1D matrix and apply LBG vector quantization as lossy compression techniques and other lossless compression techniques such as Huffman coding and arithmetic coding. The result of our approach gives the highest possible compression ratio and less time possible than other compression approaches. Our approach is useful in the internet image compression.

The paper presents a novel biometric authentication approach using Principal Component Analysis (PCA), Regularized-Linear Discriminant Analysis (R-LDA) and supervised neural networks. Low dimensional feature vectors of human face images are required to drive neural networks effectively. After histogram equalization process each image is presented to PCA or R-LDA for normalization and dimension reduction. The preprocessing steps of PCA or R-LDA produce Low dimensional feature vectors appropriate for training. Neural network has a great deal of nerve cell and can accomplish parallel distributing operation. Back Propagation (BP), Radial Basis Function(RBF) & Learning Vector Quantization(LVQ) are used as classifiers. The analysis of obtained results shown that R-LDA preprocessed feature vectors driven by supervised neural networks are having better recognition performance than PCA. While among supervised neural networks RBF gave most matched output during testing.

 Is a classical quantization technique from signal processing that allows the modeling of probability density functions by the distribution of prototype vectors. It was originally used for data compression.  It works by dividing a large set of points (vectors) into groups having approximately the same number of points closest to them. Each group is represented by its centroid point, as in k-means and some other clustering algorithms.

An internally analog, externally digital architecture for parallel vector-matrix multiplication is presented. A threetransistor unit cell combines a single-bit dynamic random-access memory and a charge injection device binary multiplier and analog accumulator. Digital multiplication of variable resolution is obtained with bit-serial inputs and bit-parallel storage of matrix elements, by combining quantized outputs from multiple rows of cells over time. A prototype 512 128 vector-matrix multiplier on a single 3 mm 3 mm chip fabricated in standard 0.5-m CMOS technology achieves 8-bit effective resolution and dissipates 0.5 pJ per multiply-accumulate.

This paper presents the architecture and VHDL design of a Two Dimensional Discrete Cosine Transform (2D-DCT) with Quantization and zigzag arrangement. This architecture is used as the core and path in JPEG image compression hardware. The 2D-DCT calculation is made using the 2D-DCT Separability property, such that the whole architecture is divided into two 1D-DCT calculations by using a transpose buffer. Architecture for Quantization and zigzag process is also described in this paper. The quantization process is done using division operation. This design aimed to be implemented in Spartan-3E XC3S500 FPGA. The 2D-DCT architecture uses 1891 Slices, 51I/O pins, and 8 multipliers of one Xilinx Spartan-3E XC3S500E FPGA reaches an operating frequency of 101.35 MHz One input block with 8 x 8 elements of 8 bits each is processed in 6604 ns and pipeline latency is 140 clock cycles .

In this paper, automatic speaker recognition system is implemented by combining feature extraction and feature matching technique. Feature extraction method that is implemented by the Mel Frequency Cepstral Coefficients (MFCC). The Vector Quantization (VQ) is done using k-means algorithm that is used for the feature matching technique due to high accuracy but its simplicity. A speaker recognition experiments was performed using a 5talkers (3 male and 2 female) with different conditions of Bangla sentence utterances. So, in this proposal achieved 96% efficiency for text dependent or independent speaker recognition system with 60 -90 seconds duration test voice sample.

A fundamental goal of image compression is to reduce the bit rate for transmission or data storage while maintaining an acceptable fidelity or image quality. To improve the classical lossless compression of low efficiency, a method of image lossless compression with high efficiency is presented. In this paper, The image compression scheme contains wavelet transformation and vector quantization. Wavelets allow complex information such as music, speech, images and patterns to be decomposed into elementary forms at different positions and scales and subsequently reconstructed with high precision and The vector quantization algorithms reduces the transmission bit rate or storage. After analyzing and implementing Wavelet transform in lossless compression, a new method of combining vector quantization with wavelet transform to compress medical images is discussed. The result from this presentation will give the better quality of the image.

A new unsupervised competitive learning rule is introduced, called the Self-organizing free-topology map (Softmap) algorithm, for nonparametric density estimation. The receptive fields of the formal neurons are overlapping, radially-symmetric kernels, the radii of which are adapted to the local input density together with the weight vectors which define the kernel centers. A fuzzy code membership function is introduced in order to encompass, in a novel way, the presence of overlapping receptive fields in the competitive learning scheme. Furthermore, a computationally simple heuristic is introduced for determining the overall degree of smoothness of the resulting density estimate. Finally, the density estimation performance is compared to that of the variable kernel method, VBAR and Kohonen's SOM algorithm.

In Part I of this paper , an equivalence between the concepts of fuzzy clustering and soft competitive learning in clustering algorithms is proposed on the basis of the existing literature. Moreover, a set of functional attributes is selected for use as dictionary entries in the comparison of clustering algorithms.

Clustering is needed in various applications such as biometric person authentication, speech coding and recognition, image compression and information retrieval. Hundreds of clustering methods have been proposed for the task in various fields but, surprisingly, there are few extensive studies actually comparing them. An important question is how much the choice of a clustering method matters for the final pattern recognition application. Our goal is to provide a thorough experimental comparison of clustering methods for text-independent speaker verification. We consider parametric Gaussian mixture model (GMM) and non-parametric vector quantization (VQ) model using the best known clustering algorithms including iterative (K-means, random swap, expectation-maximization), hierarchical (pairwise nearest neighbor, split, split-and-merge), evolutionary (genetic algorithm), neural (self-organizing map) and fuzzy (fuzzy C-means) approaches. We study recognition accuracy, processing time, clustering validity, and correlation of clustering quality and recognition accuracy. Experiments from these complementary observations indicate clustering is not a critical task in speaker recognition and the choice of the algorithm should be based on computational complexity and simplicity of the implementation. This is mainly because of three reasons: the data is not clustered, large models are used and only the best algorithms are considered. For low-order models, choice of the algorithm, however, can have a significant effect.

This paper introduces a new approach to control and drive the DC motor, using speech recognition. The speech signal can be provided through microphone that is connected to computer. A DC motor connected through microcontroller can be driven in forward or reverse direction at different speeds, as well as it can be stopped by giving speech command. In this paper Mel Frequency Cepstral Co-efficient (MFCC) is used to recognize the user's speech and vector quantization is used to increase speech recognition accuracy. The MFCC and VQ algorithm, for speech recognition have been implemented in MATLAB 7.5 version on Windows Vista platform, and the supporting hardware setup is being implemented.

Speech recognition is always looked upon as a fascinating field in human computer interaction. It is one of the fundamental steps towards understanding human recognition and their behavior. This paper explicates the theory and implementation of Speech recognition. This is a speaker-dependent real time isolated word recognizer. The major logic used was to first obtain the feature vectors using LPC which was followed by vector quantization. The quantized vectors were then recognized by measuring the Minimum average distortion.

This paper presents some results on the possibilities offered by neural networks for human face recognition. In particular, two algorithms have been tested: learning vector quantization (LVQ) and multilayer perceptron (MLP). Two different approaches have been taken for each case, using as input data either preprocessed images (gray level or segmented), or geometrical features derived from a set of manually introduced landmarks. The preprocessing steps included resolution reduction and segmentation. For the geometrical features´ case, a Karhunen-Loeve expansion was used to extract features among the different possibilities offered by 14 landmark points. For the experiments, a database composed of 300 images was used. The pictures correspond to 10 frontal, inclined o rotated views from thirty male persons of similar age and race. If gray level images are used as input data, the experimental results show higher recognition rates for LVQ than for MLP (96.7% versus 83.3%). Applying a previous segmentation stage strongly decreases the recognition rates. For geometrical features, the situation is reversed: MLP yields better results than LVQ (93.3% versus 84.4%).

This paper introduces methods for reducing the table storage required for encoding and decoding with unstructured vector quantization (UVQ) or tree-structured vector quantization (TSVQ). Specifically, a low-storage secondary quantizer is used to compress the codevectors (and testvectors) of the primary quantizer. The relative advantages of uniform and nonuniform secondary quantization are investigated. An LBG-like algorithm that optimizes the primary UVQ codebook for a given secondary codebook and another that jointly optimizes both primary and secondary codebooks are presented. In comparison to conventional methods, it is found that significant storage reduction is possible (typically a factor of 2 to 3) with little loss of signal-to-noise ratio (SNR). Moreover, when reducing dimension is considered as another method of reducing storage, it is found that the best strategy is a combination of both. The method of secondary quantization is also applied to TSVQ to reduce the table storage required for both encoding and decoding. It is shown that by exploiting the correlation among the testvectors in the tree, both encoder and decoder storage can be significantly reduced with little loss of SNR-by a factor of about 4 (or 2) relative to the conventional method of storing testvectors (or test hyperplanes).

In this letter, a preliminary study of habituation in self-organizing networks is reported. The habituation model implemented allows us to obtain a faster learning process and better clustering performances. The habituable neuron is a generalization of the typical neuron and can be used in many self-organizing network models. The habituation mechanism is implemented in a SOM and the clustering performances of the network are compared to the conscience learning mechanism that follows roughly the same principle but is less sophisticated.

Multi-user wireless systems with multiple antennas can drastically increase the capac-
ity while maintaining the quality of service requirements. The best performance of these
systems is obtained at the presence of instantaneous channel knowledge. Since uplink-
downlink channel reciprocity does not hold in frequency division duplex and broadband
time division duplex systems, efficient channel quantization becomes important. This
thesis focuses on different quantization techniques in a linearly precoded multi-user wire-
less system.
Our work provides three major contributions. First, we come up with an end-to-end
transceiver design, incorporating precoder, receive combining and feedback policy, that
works well at low feedback overhead. Second, we provide optimal bit allocation across the
gain and shape of a complex vector to reduce the quantization error and investigate its
effect in the multiuser wireless system. Third, we design an adaptive differential quantizer
that reduces feedback overhead by utilizing temporal correlation of the channels in a time
varying scenario.

Clustering algorithms aim at modeling fuzzy (i.e., ambiguous) unlabeled patterns efficiently. Our goal is to propose a theoretical framework where the expressive power of clustering systems can be compared on the basis of a meaningful set of common functional features. Part I of this paper reviews the following issues related to clustering approaches found in the literature: relative (probabilistic) and absolute (possibilistic) fuzzy membership functions and their relationships to the Bayes rule, batch and on-line learning, prototype editing schemes, growing and pruning networks, modular network architectures, topologically perfect mapping, ecological nets and neuro-fuzziness. From this discussion an equivalence between the concepts of fuzzy clustering and soft competitive learning in clustering algorithms is proposed as a unifying framework in the comparison of clustering systems. Moreover, a set of functional attributes is selected for use as dictionary entries in the comparison of clustering algorithms, which is the subject of Part II of this paper [1].

The issue of Automatic Relevance Determination (ARD) has attracted attention over the last decade for the sake of efficiency and accuracy of classifiers, and also to extract knowledge from discriminant functions adapted to a given data set. Based on Learning Vector Quantization (LVQ), we recently proposed an approach to ARD utilizing genetic algorithms. Another approach is the Generalized Relevance LVQ which has been shown to outperform other algorithms of the LVQ family. In the following we present a unique description of a number of LVQ algorithms and compare them concerning their classification accuracy and their efficacy. For this purpose a real world data set consisting of spontaneous EEG and EOG during overnight-driving is employed to detect so-called microsleep events. Results show that relevance learning can improve classification accuracies, but do not reach the performance of Support Vector Machines. The computational costs for the best performing classifiers are exceptionally high and exceed basic LVQ1 by a factor of 10 4 .

In the recent years, Internet multimedia applications have become very popular. Valuable multimedia content such as digital images, however, is vulnerable to unauthorized access while in storage and during transmission over a network. Streaming digital images also require high network bandwidth for transmission. For effective image transmission over Internet; therefore, both security and bandwidth issues must be considered. In this paper, we present a novel scheme, which combines Discrete Wavelet Transform (DWT) for image compression and block cipher Data Encryption Standard (DES) for image encryption. The simulation results indicate thaf our proposed method enhances the security for image transmission over the Internet as well as improves the transmission rate.

A full-rank under-determined linear system of equations Ax = b has in general infinitely many possible solutions. In recent years there is a growing interest in the sparsest solution of this equation-the one with the fewest non-zero entries, measured by x 0 . Such solutions find applications in signal and image processing, where the topic is typically referred to as "sparse representation". Considering the columns of A as atoms of a dictionary, it is assumed that a given signal b is a linear composition of few such atoms. Recent work established that if the desired solution x is sparse enough, uniqueness of such a result is guaranteed. Also, pursuit algorithms, approximation solvers for the above problem, are guaranteed to succeed in finding this solution.

The pyramid image structure can be naturally adapted for progressive image transmission over low-speed channels and hierarchical image retrieving in computerized image archiving. An efficient pyramid image coding system using quadrature mirror filters to form the image-pyramids is proposed in this paper. Characteristics of the image-pyramids are presented. Since the Laplacian pyramids of most nature images contain sparse and spatially concentrated data, a combined run-length coding for zero-valued elements and entropy coding for elements larger than a certain threshold is employed. The textural features in the Laplacian pyramids suggest that coding techniques pursuing spatial correlation may be advantageous. Therefore, vector quantization is chosen to code the Laplacian pyramids. Simulation results have shown that simple vector quantization accomplished significant bit-rate reduction over scalar quantization. The proposed system has also shown good-quality reproduction at bit rates lower than 1 bit/pixel.

This two part paper proposes an intelligent energy management agent (IEMA) for parallel hybrid vehicles. IEMA incorporates a driving situation identification component whose role is to assess the driving environment, the driving style of the driver and the operating mode of the vehicle using long and short term statistical features of the drive cycle. This information is subsequently used by the torque distribution and charge sustenance components of IEMA to determine the power split strategy, which is shown to lead to enhanced fuel economy and reduced emissions. In Part I, the overall architecture of IEMA is presented and the driving situation identification process is described. It is specifically shown that a learning vector quantization (LVQ) network can effectively determine the driving condition using a limited duration of driving data. The overall performance of the system under a range of drive cycles is discussed in the second part of this paper.

Novel algorithms for vector quantization codebook design are presented in this paper. Two basic techniques are proposed. The first technique takes into consideration specific characteristics of the blocks of the training sequence during the generation of the initial codebook. In this way a representative initial codebook is generated. Starting from a high quality initial codebook the iterative optimization procedure converges fast to a representative final codebook which in turn leads to high output image quality. The second proposed technique extends small codebooks computationally. The main idea is the application of simple transformations on the codewords. This technique reduces the memory requirements of the traditional vector quantization making it useful for applications requiring lowpower consumption.

The color satellite image compression technique by vector quantization can be improved either by acting directly on the step of constructing the dictionary or by acting on the quantization step of the input vectors. In this paper, an improvement of the second step has been proposed. The knearest neighbor algorithm was used on each axis separately. The three classifications, considered as three independent sources of information, are combined in the framework of the evidence theory. The best code vector is then selected, after the image is quantized, Huffman schemes compression is applied for encoding and decoding.

Vector quantization is a compression technique which is used to compress the image data in the spatial domain. Since it is a lossy technique, so maintaining the image quality and the compression ratio is a difficult task. For this, the codebook which stores the image data should be optimally designed. In this paper, the K-means algorithm is used to optimize the codebook. We have generated the codebooks from LBG, KPE, KFCG and Random Selection Methods. It is found that the Mean Square Error reduces for every iteration and after a certain number of iterations it stops reducing because the optimal value is reached. We can say that the codebook is optimized at that point. The results show that the codebook obtained from KFCG Algorithm has a least Mean Square Error. This shows that KFCG codebook is more nearer to the optimal point and when applied with K-means algorithm gives the best optimization in comparison with other algorithms.

This paper presents an efficient authentication method for JPEG images based on Genetic Algorithms (GA). The current authentication methods for JPEG images require the receivers to know the quantization table beforehand in order to authenticate the images. Moreover, the quantization tables used in the JPEG compression are different for different quality factors, thus increasing the burden on the receivers to maintain several quantization tables. We propose a novel GA-based method which possesses three advantages. First, the computation at the receiver end is simplified. Second, it is no more required for the receivers to maintain quantization tables. Third, the method is resistant against Vector Quantization (VQ) and Copy-Paste (CP) attacks by generating the authentication information which is unique with respect to each block and each image. Furthermore, we develop a two-level detection strategy to reduce the false acceptance ratio of invalid blocks. Experimental results show that the proposed GA-based method can successfully authenticate JPEG images under variant attacks.

This paper studies an application of turbo codes to compressed image/video transmission and presents an approach to improving error control performance through joint channel and source decoding (JCSD). The proposed approach to JCSD includes error-free source information feedback, error-detected source information feedback, and the use of channel soft values (CSV) for source signal postprocessing. These feedback schemes are based on a modification of the extrinsic information passed between the constituent maximum a posteriori probability (MAP) decoders in a turbo decoder. The modification is made according to the source information obtained from the source signal processor. The CSVs are considered as reliability information on the hard decisions and are further used for error recovery in the reconstructed signals. Applications of this joint decoding technique to different visual source coding schemes, such as spatial vector quantization, JPEG coding, and MPEG coding, are examined. Experimental results show that up to 0.6 dB of channel SNR reduction can be achieved by the joint decoder without increasing computational cost for various channel coding rates.

This paper describes a method to randomly generate vectors of symbol probabilities so that the corresponding discrete memoryless source has a prescribed entropy. One application is to Monte Carlo simulation of the performance of noiseless variable length source coding.

This paper reports our study of how to gain consistency of states in a ball-game typed Distributed Virtual Environment (DVE) with lag, in peer-to-peer (P2P) architecture. That is, we are studying how to reduce in real-time the difference of states between the participating terminals in a virtual ball game caused by transmission lag or update interval. We are also studying how to control shared objects in real-time in a server-less network architecture. Specifically, a priority field called Allocated Topographical Zone (AtoZ) is used in P2P for DVE. By implementing this function, each terminal can compute which avatar holds the ownership of a shared object by calculating mutually the state of the local avatar predicted by the remote terminals. The region for ownership determined by AtoZ allows an avatar to access and control an object dominantly, so that a geometrical property is dynamically changed depending upon the relative arrangement between the object and avatars. Moreover considering the critical case, defined as inconsistent phenomena between the peers, caused by the network latency, a stricter ownership determination algorithm, called dead zone is introduced. By using these protocols in combination, a robust and effective scheme is achieved for a virtual ball game. As an example of the application, a real-time networked doubles air-hockey is implemented for evaluation of the influence of these protocols on interactivity and on consistency. key words: DVE (Distributed Virtual Environment), P2P (peer-to-peer), mutual prediction protocol, priority field, AtoZ (Allocated Topographical Zone), the critical cases, the dead zone

Fingerprints are imprints formed by friction ridges of the skin and thumbs. They have long been used for identification because of their immutability and individuality. Immutability refers to the permanent and unchanging character of the pattern on each finger. Individuality refers to the uniqueness of ridge details across individuals; the probability that two fingerprints are alike is about 1 in 1.9x1015. In despite of this improvement which is adopted by the Federal Bureau of Investigation (FBI), the fact still is "The larger the fingerprint files became, the harder it was to identify somebody from their fingerprints alone. Moreover, the fingerprint requires one of the largest data templates in the biometric field". The finger data template can range anywhere from several hundred bytes to over 1,000 bytes depending upon the level of security that is required and the method that is used to scan one's fingerprint. For these reasons this work is motivated to present another way to tackle the problem that is relies on the properties of Vector Quantization coding algorithm.

This paper presents a novel Vector Quantizer codebook design using Fuzzy Possibilistic C Means (FPCM) clustering technique for image compression using Wavelet Packet. The idea is to achieve higher compression ratio based on clustering the wavelet coefficients of each Wavelet Packet Tree (WPT) bands. The methodology applied here is to apply WPT to the whole image. The sub blocks are decomposed into two level Wavelet Packet Tree where the coefficients of LL band’s(approximation and details), LH band’s(approximation), HL band’s(approximation), HH band’s (approximation) are clustered using FPCM. The centroids of each cluster is arranged in the form of a codebook and indexed. The index values are coded and then transmitted across. The image is reconstructed using the inverse WPT followed by rearranging and the subsequent encoder. The results show that the psycho-visual fidelity criteria (both subjective and objective measures) of the proposed FPCM technique do better than the other existing methods.

Nowadays, face detection plays important roles in many applications, such as: human-computer interaction, security and surveillance, face recognition etc. In this paper, a novel scheme for human face detection in color images under non-constrained scene conditions is presented. Color clustering and filtering based on the vector quantization (VQ) technique are performed on the original input image, providing binary skin color regions. In order to provide a set of candidate face areas, constrains related to shape and size of faces are considered. Finally, mouths are searched in all of the candidate face regions by means of mouth detector to verify each face region. Experimental results show that the proposed method is efficient and robust to head rotation to some extent.

Cet article pr~sente une nouvelle mdthode de codage audionum6rique h faible retard et & d~bit rdduit pour des applications ~mergentes en tdldcommunication telles que l'audioconfgrence ou la vidgoconf(rence. Le codeur dgveloppd permet de traiter des signaux g~n&iques (parole, musique, sons d'accompagnement, sons d'ambiance,...) un d~bit de 64 kbit/s avec un retard de codage et d~codage aux environs de 5 ms dans la bande de fr6quence 20-15000 Hz. Ce codeur s'articule sur une d~composition en sous-bandes du signal d'entrde assocMe g~ un codage de la parole de type LD-r L'introduction d' un modkle psychoacoustique permet de d~terminer le d~bit optimal gt allouer g~ chacune des sous-bandes en fonction des caractdristiques propres de l'audition humaine. Pour satisfaire la demande de ddbit requise par le modkle psychoacoustique et pour rdduire la complexit~ algorithmique induite par cette structure de codage, nous avons prdsentd une nouvelle mdthode de quantification vectorielle bas~e sur les rYseaux rdguliers de points. Cette mdthode pennet de quantifier le signal rdsiduel au sein du codeur LO-CELP sans effectuer de recherche trop complexe du meilleur quantificateur. Des tests objectifs et subjectifs ont dt# r~alisds sur des sYquences sonores critiques utilis~es par l'tso. Des tests formels ont montrY que la qualit6 du codeur proposd est comparable aux meilleures implantations de la norme MPEG-I, touche 11, avec l'avantage, pour la solution propos6e, d'avoir un retard de codage et d6codage beaucoup plus faible (5 ms).

This paper describes an encoding technique-multilevel block truncation coding-that preserves the spatial details in digital images while achieving a reasonable compression ratio. An adaptive quantizer-level allocation scheme is introduced, which minimizes the maximum quantization error in each block and substantially reduces the computational complexity in the allocation of optimal quantization levels. A 3.2: 1 compression can be achieved by the multilevel block truncation coding itself. The truncated, or requantized, data are further compressed in a second pass using combined techniques of predictive coding, entropy coding, and vector quantization. The second pass compression can be lossless or lossy. The total compression ratios are about 4.1:l for lossless second-pass compression, and 6.2: 1 for lossy secondpass compression. The subjective results of the coding algorithm are quite satisfactory, with no perceived visual degradation.

The foremost issues with most of the existing selective encryption (SE) schemes of images are vulnerability to cryptographic and application specific attacks, reduction in the compression performance, insubstantial computational savings relative to full encryption, and lack of bit stream compliance. This paper is the first one that proposes effective schemes for joint vector quantization (VQ) based image compression and SE. We introduce an image adaptive VQ index compression algorithm suitable for SE, effectively combining remapping of indices, entropy, predictive, differential, and search order coding. We then present SE through codebook pseudorandom shuffling and block ciphering of the VQ index image bit-planes, index usage map, prediction information tables and full indices. Experimentally, the results demonstrate the improved performance and effectiveness of the proposed schemes.