Earticle

Linde–Buzo–Gray (LBG) algorithm is a universal method to design codebook in vector quantization(VQ). This paper proposed an adaptive orthogonal M-split initialization method to improve the computational efficiency of LBG algorithm. The method splits one code word into 2, 4 or 5 new code words with adaptive split coefficient vectors and set the increment to be orthogonal in 4-split and 5-split situations, aiming at decreasing the iterations of the following clustering. Experiment is conducted on both TIMIT and RASC863 speech database, which shows that the proposed algorithm provides a reduction of 18%~45% in designing codebook in size of 64~2048 with almost equal VQ performance, compared with the universal codebook generation algorithm.

The solitary greatest mounting investigate fields in the pasture of hypermedia technicality is the transformation of color to grayscale. This paper represents the transformation of color to grayscale with small amount of ASD and PMSE. The unexploited bit may be removing by means of the Differential pulse code modulation (DPCM) in the image for image transformation. We contrast the transformation of image for 1 as well as 3, segments average square distortion and estimation error using DPCM with permanent coefficient and DPCM with LMS algorithm. The outcome are presented which show LMS may present less average square distortion (ASD) and prediction mean square error (PMSE) in transformed image contrast to DPCM with good visual quality. The LMS method was replicated by means of Mat-lab among appreciated to the claim of image exchange contrast by means of DPCM through LMS method. Simple to execute and computationally not expensive is LMS Method. It facet makes the LMS gorgeous designed for image transfer contrast to only DPCM. It is found that a supplementary discriminating grayscale image as compared to established methods converges by the wished-for method.

Multiple-input multiple-output (MIMO) radar waveforms design with specified properties has a number of superiority over its phased-array counterpart, such as clutter suppression and interference mitigation. In this paper, we consider the problem of waveform optimization with prior information on targets of interest to improve the parameter estimation performance of MIMO radar in the presence of signal-dependent noise, which is based on the constrained Cramer-Rao bound (CRB). The waveform covariance matrix (WCM) is designed to minimize the trace of the constrained CRB such that the parameter estimation performance can be improved. In order to solve the resultant nonlinear optimization problem, a novel diagonal loading (DL) based method is proposed to relax this optimization issue as a semidefinite programming (SDP) one, which can be solved very efficiently. Following that, an optimal solution to the initial issue can be obtained via the least squares (LS) fitting of the solution acquired by the relaxed one. The effectiveness of the proposed method is verified by numerical examples, as compared to the uncorrelated waveforms.

A new fabric defect detection algorithm base on Gabor filters is proposed. The spectral characteristics of both fabric texture and defects are analyzed. Gabor wavelet which can be considered as a bank of Gabor filters are used for the decomposition of fabric image. Based on spectral characteristics of fabric texture and defects, a new tuning method of Gabor wavelet is proposed to enhance the energy of defective region and attenuate the energy of normal texture. Decomposition images from different scales and orientations are fused into a single one to emphasize the presence of different kinds of defects. For comparison, the performance of proposed method as well as other two other defect detection methods using Gabor filters is evaluated with typical fabric defect samples. The experiment results obtained indicate that the proposed method is more effective than the other two.

Microstrip patch antennas are most widely used antennas because of its application in mobile phones, low cost, ease of fabrication etc. These antennas are planar, have applications in defense, aircraft and have so many shapes like rectangular, circular, triangle, square etc. Circular shape is one of the famous shapes among all. In CMPA as frequency increases the radius of circular patch decreases. In this paper circular patch designed at 900MHz & the important parameter like reflection coefficient, VSWR, polar plot, gain (IEEE) calculated. With application of air gap between dielectric there is variation in resonant frequency of the antenna. The frequency get shifted from 900 MHz to 2.712, 2.2298, 2.268 GHz. If the radius calculated for increased frequency the radius is small in comparison of 900MHz frequency that means antenna get compact. The comparison of all four designs has been done. Hence in this paper CMPA get compact in terms of frequency using air gap.

Value tracking aims to capture the changes of attribute values along with the evolution of topic. Existing researches on value tracking only extracted the attribute values chronologically, and took no use of the context information to verify the correctness of the values. This paper proposes a context-based value tracking method. First, extract the candidate attribute values according to the patterns generated by the regular expressions; Second, recognize the temporal expressions in the source sentences of the candidate values based on conditional random fields; Finally, identify the real attribute values according to the temporal features and location features in the context. Experiments on TREC 2013 Knowledge Base Acceleration (KBA) stream corpus and human-build Chinese corpus demonstrate that the proposed method can track the changes of the attribute values effectively.

Mechanical properties of tissue are often related to the pathological state of tissue. Therefore, non-invasively measuring tissue stiffness has important clinical applications. With the assumption of isotropy, incompressibility and linearity, the shear modulus of tissue is related to its shear wave propagation speed. Acoustic radiation force from a focused ultrasound beam can be used to generate shear waves at the focal region within tissue, which propagate orthogonally to the direction of the pushing ultrasound beam. The shear wave speed can be estimated based on the so called time-to-flight principle. The shear wave arrival time determined at several lateral positions along the shear wave propagation path can be measured by the displacement profiles, which can be tracked using correlation-based method by pulse-echo ultrasound. This approach has been successively used with various modifications by several groups. The purpose of this study is to design a simulation method to generate the pulse-echo ultrasound signal, calculate the displacement profile in the spatial and time domain, and estimate the shear wave speed using RANSAC, Radon Sum and robust linear regression method, compare and analyze the algorithm performance of these methods.

The calibration of polarization imaging system is the premise to obtain target polarization information accurately, in this paper, we propose a method of calibration based on the radian of distorted curves in the checkboard to solve the problem of losing polarization information in the underwater distorted polarization images. Firstly, we use the radian of distorted curves in the checkboard to calculate the coordinates of distortion center, and calibrate the region near the distortion center. Then we use the calibrated region to reconstruct the whole image. Finally, we combine the distorted image, the reconstructed image and the distortion model to obtain the calibration parameters. With these parameters we can get the calibrated polarization images. The experiments show that our method can calibrate the polarization image accurately, reduce the coupled error and calculate parameters independently.

It is of great importance to classify all kinds of hypersurface in different space forms. In this paper, we focus on the hypersurfaces foliated by time-like pseudo circles. In order to complete the classification, we study the moduli space 𝐐23 of time-like pseudo circles in 𝐑13. Firstly, We build the moduli space 𝐐23 of time-like pseudo circles in 𝐑13 which is definitely a Riemannian manifold. Secondly, we build Riemannian metric, Riemannian connections in 𝐐23 and prove that those are M𝑜̈bius invariant. Thirdly, up to M𝑜̈bius transformation, all the geodesics in 𝐐23 are determined to form a one-parameter family of time-like pseudo circles on a generalized helicoid in space form 𝐌13(1), 𝐌13(−1),𝐌13(0), resp. Moreover, we show that mean curvature of those hypersurfaces are zero in three space forms respectively. Finally by software Mathematica and Jreality, we show some special hypersurfaces foliated by time-like pseudo circles.

This paper describes a small vocabulary Bengali database development to evaluate the performance of speech recognition algorithms in clean conditions. The database is constructed by Bangla digit sequences (/ak/, /dui/, /tin/, /chaar/, /panch/, /chhoy/, /shaat/, /aat/, /noy/, /zero/, /shunno/) are used. The developed database is consisted of two sets of data which are training and testing datasets. The training dataset contains 3824 utterances of 50 speakers; on the other hand, the testing dataset is subdivided into four groups (clean1, clean2, clean3 and clean4) and contains 1985 utterances of 52 speakers. In both sets of data the speaker’s age ranges from 19 to 25 years. All the recordings have been done in a quiet room but not soundproof with the A4Tech HS-60 headset microphone interfaced to an Intel Dual Core 2.0 GHz CPU. The software used to record and edit the speech file is wave-pad; ver. 3.05.The recognition experiment is presented in this thesis to obtain comparable recognition results for the speaker-independent recognition of connected sequences of Bangla digit. As the research results has proved that the words accuracy is average 98%.

Hardware simulation pager usually is very expensive and can only simulate 16 subscriber line or 32 subscriber line. And in FMC (fixed and mobile convergence) system, FSK (frequency shift keying) is used to transfer information between home gateway and the program controlled switch. In this paper, a novel FSK call simulation method to design a pager is proposed to use software to simulate the interaction of FSK between home gateway and the program controlled switch during a normal call procedure, and to meet the demand of the performance and capacity testing of the FMC system. The FSK call simulation includes a back-end management system and a foreground simulation system. And the foreground simulation system consists of MP (module process) module, SP (subscriber process) module, ASIG (analog signal) module, and so on. The MP is the module’s main control process, and it will control the logic of call, and transfer simulation control information between back-end management system and the other modules in the foreground. The SP is the module, in which the FSK call simulation process lying in. And ASIG module can send FSK signal to home gateway, and receive FSK signal from home gateway. The novel FSK call simulation method can test the performance and capacity of the FMC platform by the means of software, and lower the expense of testing.

In order to improve the robustness of face identification with the changes of illumina-tion, expression and facial alteration, a new facial feature extraction algorithm based on weighted adaptive lifting wavelet(ALW) scheme and pulse-coupled neural network (PCNN) is involved in this paper. The face images are decomposed into several subbands by weighted adaptive lifting scheme. Then the PCNN is utilized to decompose each weighted subbands into a series of binary images, the entropies of which are calculated and regarded as facial features. Experimental results show that the method yields a good robustness against the illumination, expression and facial variability and reduces the computer burden.

In this paper, it is proposed to implement the image compression, encryption and ECG data compression using by binary description of Discrete Cosine Transform (DCT), Binary Haar Transform and Discrete Hartley Transform (DHT). In this Binary Discrete Cosine Transform (Binary DCT), Binary Haar Transform and Binary Discrete Hartley Transforms (Binary DHT) are developed using the Walsh Hadamard transform (WHT). The resulting transform nearly exact the underlying transform very well, while maintaining all the advantages and properties of WHT. The Binary DCT is a well known sequency ordered Walsh Hadamard Transform (WHT), where as the Binary DHT can be considered as a new Hartley ordered WHT. Specifically, the properties of the proposed Hartley ordering are discussed and a shift copy scheme is proposed for a simple and direct generation of the Hartley ordering functions.

Aiming at the problem that the theoretical spectrum expression of the output voltage waveform in the space vector pulse width modulation strategy is often extremely complicated, most tedious and quite error-prone, the study develops a universal procedure and algorithm with adaptive precision to analyze the harmonic spectrum. The key steps and technique of the procedure and algorithm are given firstly. The algorithm steps include storing the switching states and the vector sequences, computing the basic space vector duration time, storing the duration time, sampling output voltage values and computing the spectrum using the fast Fourier transform algorithm. The sampling number doubles in each iteration for the next iteration. The adaptive precision is realized through controlling the amplitude or magnitude error between the current result and the previous result. The realization method and the key codes are presented secondly. Finally, three numerical experiments are presented to verify the developed algorithm, and the results verify its correctness, reliability and convenience.

In today’s age, communication through internet has become inseparable entity of many applications. These applications often require secrecy of data to be transmitted for security reasons. Therefore, commonly used security mechanisms such as cryptography and steganography can be employedto provide security, however using these techniques standalone often poses security threats. Therefore, a hybrid approach can be used for improving security features. In this paper comparison is drawn of recently published hybrid security mechanisms on the basis of following parameters: Visual assessment, Encrypted code Analysis, Similarity Analysis, Peak Signal Noise Ratio (PSNR), Information Entropy Analysis, Embedding Capacity Analysis, Key space analysis. The schemes are implemented and comparedusing MATLAB-2015.

Because the single chaotic mapping easily creates security weaknesses in the image encryption algorithm, the security needs to be improved. Aiming at this problem, a bit-level image encryption algorithm based on composite chaotic mapping (CCM-IEA) is proposed. First of all, the algorithm scrambles the plain image on bit level through the Cat mapping for the first time. And then the Henon mapping of two dimensional discrete is used to scramble for the second time. Finally, image diffusion is operated through the one dimensional Logistic mapping, and the data sensitivity is enhanced. The experimental results show that the performance of the CCM-IEA algorithm is better on the histogram, information entropy and correlation analysis. Compared with the single chaotic images encryption algorithm, the CCM-IEA algorithm has the ability to resist the information entropy analysis and correlation analysis. It can be seen that the CCM-IEA algorithm has high safety performance and good encryption effect.

Due to the concrete crack images are self-similarity in the contents, it makes the matching procedure more difficult and unstable than the others. For the purpose of finding out the stable and accurate matching algorithm of concrete crack images, we give an analysis of different kinds of characters, such as, scale invariant feature transform (SIFT), local maximum gradient descriptor, Harris corners, and the maximum curvature points of the image edges, etc. Based on the experiments of different concrete crack images, a new stable matching algorithm is proposed in this paper. In our model, the edge information is combined with the local maximum gradient of the input matching images. After the extraction of the local maximum gradient character points, we use the edge information to divide these points into different classes. Then, the searching of the stable and accurate matching problem becomes to find out the best matching results which agree to the edge constraints. The experimental results show that the proposed algorithm is more consistence and stable than the other kinds of matching algorithms especially in the proposing of sequential concrete crack images.

Offline signature recognition has great importance in our day to day activities. Researchers are trying to use them as biometric identification in various areas like banks, security systems and for other identification purposes. Fingerprints, iris, thumb impression and face detection based biometrics are successfully used for identification of individuals because of their static nature. However, people’s signatures show variability that makes it difficult to recognize the original signatures correctly and to use them as biometrics. The handwritten signatures have importance in banks for cheque, credit card processing, legal and financial transactions, and the signatures are the main target of fraudulence. To deal with complex signatures, there should be a robust signature verification method in places such as banks that can correctly classify the signatures into genuine or forgery to avoid financial frauds. This paper, presents a pixels intensity level based offline signature verification model for the correct classification of signatures. To achieve the target, three statistical classifiers; Decision Tree (J48), probability based Naïve Bayes (NB tree) and Euclidean distance based k-Nearest Neighbor (IBk), are used. For comparison of the accuracy rates of offline signatures with online signatures, three classifiers were applied on online signature database and achieved a 99.90% accuracy rate with decision tree (J48), 99.82% with Naïve Bayes Tree and 98.11% with K-Nearest Neighbor (with 10 fold cross validation). The results of offline signatures were 64.97% accuracy rate with decision tree (J48), 76.16% with Naïve Bayes Tree and 91.91% with k-Nearest Neighbor (IBk) (without forgeries). The accuracy rate dropped with the inclusion of forgery signatures as, 55.63% accuracy rate with decision tree (J48), 67.02% with Naïve Bayes Tree and 88.12% (with forgeries).

It cannot avoid the noise interference in image processing, whether it is image generation, or image transmission, among them, the most typical noise is salt and pepper noise and Gaussian noise. The salt and pepper noise will cause the image showing the random distribution of noise points, thus greatly reduce the image quality. The Gaussian noise affects the input, collection and output of the image processing. Gaussian noise will make the image blurred. Therefore, the image de-noising plays a very important role in image processing. It has direct influence on image segmentation, feature extraction and image recognition. As is known to all, the support vector machine has the advantages of solving the problem of nonlinear, high dimension and local minimum points. In this article, we use this advantage to propose an image de-noising method which is based on it. The method uses support vector regression to construct the filter for image de-noising. The feature extraction and training samples are designed to suppress different types of noise. Firstly, we use the noise pixel as the center of the 5*5 window, and generate the input vector of SVM from row to column. Secondly, we set the output of the support vector filter as an image that is not contaminated by noise. At this point, we get the training samples of SVM filter. In addition, the parameter selection of support vector machine has a great influence on the result of image de-noising. Therefore, the particle swarm optimization algorithm is proposed in this article to optimize the parameters of SVM. Finally, we adding the simulated salt and pepper noise and Gaussian noise in the original Lena image, and using several methods to carry out the de-noising experiment. From the experimental results we can see that the de-noising effect of filtering algorithm of this paper is very good for the two kinds of noise. It can effectively remove the noise, and better maintain the details and the color of the image.

In recent years, face recognition technology has been widely used as a kind of important modern biological recognition technology. As one of the main factors that affect the recognition rate, the illumination variation has attracted the attention of many researchers. In order to improve the face recognition under illumination variation condition, a novel face recognition algorithm based on improved Retinex and sparse representation is proposed in this paper. Retinex algorithm can be used to solve the problem of face illumination variation in face recognition, but it is easy to produce ‘halo’ phenomenon. In order to improve the face recognition rate under the change of illumination condition. In this paper, firstly, in order to eliminate the interference of illumination on face recognition, we apply the Retinex that is improved by partial differential equations to face image processing. Then, sparse representation is used to extract face feature vector, and the voting method is used to realize the face recognition. Finally, the performance of the algorithm is tested by 3 standard face databases. The results show that the proposed algorithm can improve the face recognition rate under different illumination conditions, and has good robustness to illumination.

Phase frequency detector is the main component that is used in almost all high speed communication system especially in sensors. With the improving technology it is important for phase frequency detector to meet the requirement of modern communication system. Such requirements can be improved delay and less power consumption. With this idea this paper presents the Phase Frequency Detector having less power consumption and minimal delay. Conventional latch based phase frequency detectors are most commonly used, therefore we propose an enhanced phase frequency detector which can meet the requirement of modern circuits and will reduce the shortcomings of conventional circuit. In this paper standard D flip flop is simulated and then a comparison is made between conventional and proposed model .The proposed model uses two extra transistors to reduce the blind zone, dead zone which ensures improved device characteristics. Simulations are done using tanner v14.11 tools with .35 μm CMOS technology.

H.264/AVC coding standard slices the encoded Data using the Data Partitioning (DP) based on syntax priority to improve the error resistance for H.264 bit stream. According to this feature, considering the temporal and spatial correlation in stereoscopic video, network performance and terminal error concealment technology. A derived algorithm for determining the transmission distortion based on different DP parts in a Group-of-Pictures (GoP) is proposed. The algorithm takes both the distortion introduced by error diffusion and error concealment into account, which can be estimated by the stereo video quality at encode side under the condition of the specific network. Experimental results show that the algorithm used to calculate the distortion basically coincided with simulation results, and the algorithm can be applied to different sequences with various movement characteristics.

Zebra-crossing Recognition is one of the essential parts of the visual based intelligent vehicle navigation or intelligent driving assistant system. In order to address the real-time and robustness, Zebra-crossing Recognition Method which is based on spatial-temporal correlation has been proposed. Firstly, calibrate a camera mounted on the vehicle by a practical method. Then, according to the prior knowledge such from GPS etc, a judgment whether it's in the Crossing area is made. Next, utilize the bipolar property of Zebra-crossing to extract features. Finally, the recognition results are obtained according to the model constraints. In this paper, proposed methods can improve real time identification of the zebra line by using spatial correlation, reduce the cost of recognition and lower errors during identification. The method overcomes some disadvantages of traditional identification approaches based upon video recognition, for instance higher cost and errors.

Because of gait sequences are naturally three-dimensional data, there have been several tensorial feature extraction methods to deal with tensors while there are effective tensorial classifiers. In this work, by using a linear tensor projection, a new classifier based on neural networks with random weights is introduced. Due to the proposed algorithm can classify gait samples directly without vectorizing them, the intrinsic structure information of the input data can be reserved. In addition, discriminative features sets are generated using MPCA to ascertain classification accuracy. Finally, Extensive experiments are carried out on two gait databases and results are compared against state-of-the-art techniques. It is demonstrated that the proposed algorithm MPCA plus TNNRE achieves better recognition performance.

Face recognition is an assignment that people perform routinely and easily in their everyday lives. The most recent decade has seen a pattern towards an inexorably universal nature, where compelling and minimal effort registering frameworks are, no doubt coordinated into cell telephones, autos, therapeutic instruments and very nearly every part of our lives. In the previous work, few researchers have focused on detection of face using some methodology. In this research paper, the face recognition system proposed the Detection time, false negative in missed faces and optimality of the face. This proposed research work has been focused on optimality features of the neural network for the face images and detection time. In this paper, we have applied the neural network for three parameters such – detection time, false acceptance rate, successful rates, no. of failure, and cross correlation. Our proposed parameters provide better result as compared to the previous methodology.

To ensure the quality of thick-walled seamless steel pipe, the defects in thick-walled seamless steel pipe should be detect. This paper has developed PC-based microcomputer water immersion, digital multi-channel automatic ultrasonic testing system based on the principle of ultrasonic flaw detection of thick-walled seamless steel pipe. The hardware and software of this detection system were designed. To improve detection efficiency and accuracy, all sorts of effective anti-interference measures were proposed. They could effectively remove interference signals in ultrasonic echo signal by analyzing interference source and dissemination way of automatic ultrasonic flaw detection system for small-diameter steel pipe with thick wall. An improved wavelet threshold was proposed to remove mixed noise in the echo signal to improve the echo signal-to-noise ratio at the same time. Experimental results show that the ultrasonic flaw detection system can achieve defect detection of the Small-Diameter Steel Pipe with Thick Wall, the wavelet threshold de-noising method can effectively remove mixed noise in the ultrasonic echo signal and the echo signal-to-noise ratio was improved greatly.

Fuzzy c-means clustering (FCM) with spatial information (FCM_S) is an effective algorithm for image segmentation. However, the FCM_S algorithm is not used for color image segmentation and also it produces over-segmentation results. In this paper, we present a novel fuzzy c-means algorithm named nFCM_S that incorporates spatial information into the membership function and cluster center function for segmentation of color images. Firstly, HSV color space is used for decomposition of color images. Then, to label the data points reliably, a linearly-weighted sum image is calculated on each HSV component before clustering process. Finally, spatial information is incorporated in the standard FCM algorithm and nFCM_S is applied separately on each component of HSV color space. Experiment results have shown that the nFCM_S algorithm achieves competitive segmentation results compared to other FCM-based algorithms.

Image super-resolution is the process of combining multiple images into a single image that has higher resolution than any of the original images. We present a variational framework for fusing multiple co-registered images using the Total Variation (TV) and Mumford-Shah regularizations. We also propose an alternating minimization strategy for aligning and fusing multiple images in the case when the co-registration parameters are unknown. We discuss applications to video enhancement and present two novel applications to barcode scanning and Magnetic Resonance Imaging (MRI).

As a key step in the visual inspection, image to appear particularly important. Compared with the traditional algorithm, graph cut algorithm overall high precision and faster convergence speed in discontinuous area. Based on adaptive algorithm on the basis of in-depth study, this paper proposes a three-dimensional adaptation algorithm based on graph cut theory in order to realize the image matching. Experimental results show that this algorithm can well meet the requirements of high precision and high real time capability, solve the problems such as large amount of calculation in the traditional algorithm.