Research and Implementation for License Plate Recognition Based on Improved Projection Algorithm简

This paper analyzes and dissertates the discrete wavelet transform and improved projection algorithm in four kernel stages （image preprocessing, license plate localization, character segmentation, license plate recognition, i.e.） of license plate recognition system in detail. At last, it gives some conclusions and suggestions on future research.     

Local thresholding with adaptive window shrinkage in the contourlet domain for image denoising

Threshold selection is a challenging job for the image denoising in the contourlet domain. In this paper, a new local threshold with adaptive window shrinkage is proposed. According to the anisotropic energy clusters in contourlet subbands, local adaptive elliptic windows are introduced to determine the neighboring coefficients with strong dependencies for each coefficient. Utilizing the maximum likelihood estimator within the adaptive window, the signal variance is estimated from the noisy neighboring coefficients. Based on the signal variance estimation, the new threshold is obtained in the Bayesian framework. Since it makes full use of the captured directional information of images, the threshold extends to the anisotropic spatial adaptability and behaves reliably. Simulation experiments show that the new method exhibits better performance than other outstanding wavelet and contourlet denoising schemes obviously, both in the PSNR value and the visual appearance.     

Unsupervised image segmentation based on MRFs and graph cuts

Markov random fields （MRFs） can be used for a wide variety of vision problems. In this paper we will propose a Markov random field （MRF） image segmentation model. The theoretical framework is based on Bayesian estimation via the energy optimization. Graph cuts have emerged as a powerful optimization technique for minimizing energy functions that arise in low-level vision problem. The theorem of Ford and Fulkerson states that min-cut and max-flow problems are equivalent. So, the minimum s/t cut problem can be solved by finding a maximum flow from the source s to the sink t. we adopt a new min-cut/max-flow algorithm which belongs to the group of algorithms based on augmenting paths. We propose a parameter estimation method using expectation maximization （EM） algorithm. We also choose Gaussian mixture model as our image model and model the density associated with one of image segments （or classes） as a multivariate Gaussian distribution. Characteristic features related to the information in color, texture and position are extracted for each pixel. Experimental results will be provided to illustrate the performance of our method.     

A fast audio digital watermark method based on counter-propagation neural networks

In this thesis, we present a novel audio digital watermark method based on counter-propagation neural networks. After dealing with the audio by discrete wavelet transform, we select the important coefficients which are ready to be trained in the neural networks. By making use of the capabilities of memorization and fault tolerance in CPN, watermark is memorized in the nerve cells of CPN. In addition, we adopt a kind of architecture with an adaptive number of parallel CPN to treat with each audio frame and the corresponding watermark bit. Comparing with other traditional methods by using CPN, it was largely improve the efficiency for watermark embedding and correctness for extracting, namely the speed of whole algorithm. The extensive experimental results show that, we can detect the watermark exactly under most of attacks. This method tradeoff both the robustness and inaudibility of the audio digital watermark efficaciously.     

Improving extraction of watermarks in color attacked watermarked images

A new approach for modeling color attacks of RGB-color watermarked images is presented in this paper. We have used a based interpolation watermarking algorithm and supposed that the attacks are simulated by a scaling of the colors followed by a translation. Then give bounds for the extracted watermark depending on the original image, the watermark and the attack. Different attacks like LSB, embedding another watermark, Stirmark have been simulated and the quality of the extracted watermark is discussed in each case.     

Application of data warehouse in power transformer diagnosis system

Electric power companies have accumulated huge amounts of historical fault data of power transformer after many years operation, but the decision-makers have not been greatly supported because of the limitation of knowledge and can not make decision for transformer condition assessment. A real power corporation is selected as the research background. Based on analyzing and reorganizing the various existing data sources, the power transformer fault information data warehouse is constructed and snowflake mode cubes for multi-dimension data are established. By using Processing） and data mining analyzing and inquiring data OLAP（On-Line Analysis technology, forecasting load, warehouse are realized from different point view and multi-layers, including rolling up, drilling down, slicing, dicing and rotating etc.. Moreover, this paper proposes a novel transformer fault data mining system based on data warehouse. Finally, bayes network of fault patterns are obtained, which can greatly help the decision-making for the system operating and management. The results show that transformer fault diagnosing system based on data warehouse technology can provide efficient decision supporting.     

Rescheduling to minimize total completion time under a limit on the makespan of the original jobs

We consider the rescheduling problems arising when two agents, each with a set of nonpreemptive jobs, compete to perform their respective jobs on a common processing resource. Each agent wants to minimize a certain objective function, which depends on the completion time of its jobs only. In this paper, we consider the two agents rescheduling problems for jobs on a single machine to minimize total completion time under a limit on the makespan of the original jobs. We show that the considered problems can be solved in polynomial time or pseudopolynomial time.     

Audio recording of rock/metal music using personal computers

Personal computers and their relevant technologies have been widely used by artists and musicians to create and record their own music and electroacoustic compositions. ＂Laptoppers＂ are famous for using their laptops for their dance/electronic beats and music. A genre that has not relied on the use of PCs for the production of its music is rock/heavy metal, since bands of these genres usually book recording studio time where professionals take on the task of the production using expensive equipment. This study shows that in today＇s day and age, and with the software and hardware currently available, it is possible for rock/metal artists to use their PC to record and produce their own CD successfully and at an extremely competitive cost. The effort＇s of a rock band that does just this is followed from the beginning and the results of their CD production and song successes is presented. The article also serves as a ＂HowTo＂ guide that bands on a low budget can follow to make good quality demo CDs and enter the music business industry.     

The existence and synchronization properties of symmetric fix-free codes

Fix-free codes are a type of variable length codes with both prefix-free and suffix-free properties, and there are two types of fix-free codes： symmetric fix-free codes and asymmetric fix-free codes. In this paper, we mainly discuss symmetric fix-free codes. First, the existence of symmetric fix-free codes is studied in detail, and some necessary and sufficient conditions are proposed. We also discuss the problem of achieving synchronization of symmetric fix-free codes, which is important in application. We then establish a scheme with synchronizing codewords to resolve this problem.     

Power efficient scheme for self localization in wireless sensor networks

With the tremendous applications of the wireless sensor network, self-localization has become one of the challenging subject matter that has gained attention of many researchers in the field of wireless sensor network. Localization is the process of assigning or computing the location of the sensor nodes in a sensor network. As the sensor nodes are deployed randomly, we do not have any knowledge about their location in advance. As a result, this becomes very important that they localize themselves as manual deployment of sensor node is not feasible. Also, in WSN the main problem is the power as the sensor nodes have very limited power source. This paper provides a novel solution for localizing the sensor nodes using controlled power of the beacon nodes such that we will have longer life of the beacon nodes which plays a vital role in the process of localization as it is the only special nodes that has the information about its location when they are deployed such that the remaining ordinary nodes can localize themselves in accordance with these beacon node. We develop a novel model that first finds the distance of the sensor nodes then it finds the location of the unknown sensor nodes in power efficient manner. Our simulation results show the effectiveness of the proposed methodology in terms of controlled and reduced power.     

An FPGA-based face recognition using combined 5/3 DWT with PCA methods

This paper describes a new scheme for feature extraction from facial images on FPGA. The proposed method is comprised of two stages. The first stage uses the 5/3 DWT to decompose the original face image into LL, LH, HL, and HH wavelet coefficient to reduce the size of the image. In the second stage, PCA is employed to extract the face features from the wavelet coefficients. Here we use the power iteration algorithm to find the eigenvector of the covariance matrix. We present an efficient hardware architecture using combination of parallel processing module and serial processing module. This method can take the benefits of parallel usage advantage of FPGAs and can save hardware resources. Complete hardware implemented on a Stratix II FPGA. The experimental results show that the system works with high processing rate and only 21% of the logic resources an FPGA are consumed by face recognition logic Thus it is very suitable for the low cost implementation of the face recognition system.     

Finger Braille teaching system-teaching of prosody of finger Braille

Finger Braille is one of tactual communication media of deaf-blind people. Deaf-blind people who are skilled in Finger Braille can catch up with speech conversation, because of prosody of Finger Braille. Features of prosody are： （1） characters at the end of clauses are dotted long; （2） characters of voiced sounds and double consonants are dotted shortly. In this paper, we designed three teaching patterns which taught prosody of Finger Braille （dot conditions about duration of dotting）. Teaching pattern 1 indicated a dot pattern with colored solid background. Teaching pattern 2 indicated a dot pattern with colored empty background. Teaching pattern 3 indicated a dot pattern with colored arrow （long or short）. Every teaching pattern includes 6 colors （red, orange, yellow, green, blue and purple）. In the questionnaire, the yellow pattern of teaching pattern 3 was selected as the most visible pattern. In the evaluation experiment, the yellow pattern of teaching pattern 3, the red and purple patterns of teaching pattern 1 （the least visible pattern） and the existing patterns without teaching of dot conditions are compared. As a result, every subject could dot long at the end of clauses and could dot shortly at the voiced sounds and double consonants. The answers of questionnaire indicated that the yellow pattern of teaching pattern 3 was also the most visible and easiest teaching pattern.     

C2G2FSnake： automatic tongue image segmentation utilizing prior knowledge

Extraction of the tongue body from digital images is essential for automated tongue diagnoses in traditional Chinese medicine. This paper presents a fully automated active contour initial method that utilizes prior knowledge of the tongue shape and its location in tongue images. Then colorspace information is introduced to control curve evolution. Combining the geometrical Snake model with the parameterized GVFSnake model, a novel approach for automatic tongue segmentation： C2G2FSnake （color control-geometric gradient flow Snake） is proposed. This method increases the curve velocity but decreases the complexity. C2G2FSnake greatly extends practical usage to tongue segmentation, at the same time increasing the precision. Compared with other state-of-the-art works using different images of tongue color, C2G2FSnake realizes automatic tongue segmentation with greatly improved accuracy.     

Analysis on Width Spread of Cold Rolled Strip

Width spread is usually considered in hot rolling, nevertheless, it can be ignore in cold rolling. In order to control the crown and flatness better simultaneously and realize the decoupling of crown and flatness, the transverse displacement function of strip is defined and deduced. The factors that affects the width spread are analyzing with the function. According to the unchanged principle of volume before and after rolling, the flatness model which considers the width spread is deduced. Through the model, the transverse metal flowing of different stands and different thickness is analyzing, it is found that the width spread is biggest in cold rolling at the No. 1 stand because of the maximum thickness and reduction and the minimum deformation resistance. It gives a good foundation for the decoupling of crown and flatness.     

Construction of Endpoint Constrained Cubic Rational Curve with Chord-Length Parameterization

This paper discusses the problem that constructing a curve to satisfy the given endpoint constraints and chord-length parameters. Based on the research of Lu, the curve construction method for the entire tangent angles region （α0, α1）∈（-r, r）×（-r, r） is given. Firstly, to ensure the weights are always positive, the three characteristics of cubic rational Bezier curve is proved, then the segment construction idea for the other tangent angles are presented in view of the three characteristics. The curve constructed with the new method satisfies the endpoint constraint and chord-length parameters, it＇s G1 continuous in every segment curve, and the shapes of the curve are well.     

Cluster synchronization of a class of multi-agent systems with a bipartite graph topology

This paper investigates cluster synchronization of a class of multi-agent systems with a directed bipartite graph topology,and presents a number of new results by using the neighbor’s rules for the following two cases:I)there is competition among the agents of diferent clusters,and II)there are both competition and cooperation among the agents.Firstly,for case I),a linear control protocol is designed for cluster synchronization of multi-agent systems,and a method is presented to determine the final state with the initial conditions based on state-space decomposition.Secondly,we study case II),and design a control protocol based on the information of neighbors and that of two-hop neighbors(that is,neighbors’neighbors).Finally,two examples are studied by using our presented results.The study of illustrative examples with simulations shows that our results as well as designed control protocols work very well in studying the cluster synchronization of this class of multi-agent systems.