Papers by Keyword: Character Recognition

Abstract: Cash register devices are used in every place and every shopping area in the world. Cashier takes the money from customer and put the cash register. The structure of these devices does not have any control mechanisms. If the cashier does not use any money control device, counterfeit money may deposit into the account of companies working honestly. Especially, there may be many customers in the big shopping malls and sometimes they can constitute large queues in front of the cashier. In such cases, cashier may not pay much attention to whether the money is the fake or not. In this study, a new counterfeit money detection system, which is applicable on all the cash register devices, was designed. System is based on recognition of the appearing characters above money which is illuminated with ultraviolet light. Designed detection system can be applied on the money holding mechanisms which is over the small departments in cash register drawer. In the case of any fake money detection event, system can produce an alert with light, sound or using of short message service according to the selections. Designed new system aims to protect both cashier and companies against to ill-intentioned people. The most important features of the designed system are to be cost-effective and easily assembled in the every cash register.

Abstract: The relevance of this study is stipulated by the necessity of designing techniques, algorithms, and programs improving the efficiency of automatic number plate recognition (ANPR) on images with complex backgrounds.Purpose: The aim of this work is to improve the efficiency of automatic number plate recognition on images with complex backgrounds using methods, algorithms, and programs invariant to affine and projective transformations.Design/methodology: Such techniques as artificial intelligence, pattern identification and recognition, the theory of artificial neural networks (ANN), convolutional neural networks (CNN), evolutionary algorithms, mathematical modeling, the probability theory and mathematical statistics were applied via Visual Studio and MatLab software.Findings: The software is developed allowing the automatic number plate recognition on complex background images. The convolutional neural network comprising seven layers is suggested to identify the plate localization, i.e. finding and isolating the plate on the picture. The pixel intensity histogram-based algorithm was used for character segmentation or finding individual characters on the plates. The convolutional neural network comprising six layers is designed to recognize characters. The suggested software system allows automatic number plate recognition at large angles of inclinations and rather a high speed.

Abstract: The vehicle license plate recognition system is the intelligent traffic management system based on the image and the character recognition technology, which is an important part of the intelligent transportation system. This paper introduces a method of vehicle license plate location based on edge detection and morphological operations, virtual instrument is combined with machine vision of the license plate recognition method ^[1]. Finally the license plate number of the vehicle is get. Experiment results show that such method can simplify the algorithm and has some correct location rate.

Abstract: To improve the performance of the character recognition based on wavelet neural network (WNN) with gradient descent algorithm, a new character recognition method based on WNN optimized by PSO algorithm is proposed. PSO is adopted to optimize the weights and the topological structure of WNN at the same time, which can overcome the slow convergence rate and easy to drop in the local minimum, and the WNN after optimization is used to the character recognition. The invariant moments of the license plate character image after preprocessing, such as two valued and normalized, are taken as the input of WNN to implement the character recognition. The simulation results show that, compared with WNN, the WNN optimized by PSO algorithm has better performance in character recognition, and has higher recognition ratio.

Abstract: According to the current technological deficiency of license plate recognition, this paper uses digital graphic processing technique and BP Neural Network algorithm fusion to achieve automatic recognition of license plate. Input the image settled in the previous period in the trained BP neural network to obtain the final license plate character through simulation. The validity and feasibility of the algorithm can be verified through the simulation experiment of standard license plate image.

Abstract: Aiming at how to solve the problem of cheque image discrimination quickly and accurately,an automatic system for cheque discrimination by using Optical Character Recgnition (OCR) technique based on the features of a cheque image was designed and developed, the main functional modules and key technologies of the system were studied, and all the functional modules were organized in a good logic way,finally, the automatic system for cheque discrimination was intergratted. The results of the experimental tests showed that the system can identify the information of one cheque quickly and accurate, the discrimination results were good.

Abstract: Aiming at the deficiency of large volume and complex installation monitoring system the traditional character recognition system, this paper proposes a character recognition scheme of Android intelligent terminal based on. This paper introduces the whole structure of the system, through the analysis and Research on the character recognition process, introduces the overall design process and recognition system, character recognition system client.

Abstract: This paper based on license plate image preprocessing ,license plate localization, and character segment ,using BP neural network algorithm to identify the license plate characters. Through k-l algorithm of characters on the feature extraction and recognition of license plate character respectively then taking the extraction of license plate character features into the character classifier to the training. When the end of training, extracting the net-work weights and offset matrix, and storing in the computer. To take the identified character images input to the MATLAB, and with the preservation weights and offset matrix operations, obtain the final results of recognition.

Abstract: At present, the traffic engineering and automation have developed, and the vehicle license plate recognition technology need get a corresponding improvement also. In case of identifying a car license picture, the principle of automatic license plate recognition is illustrated in this paper, and the processing is described in detail which includes the pre-processing, the edge extraction, the license plate location, the character segmentation, the character recognition. The program implementing recognition is edited by Matlab. The example result shows that the recognition method is feasible, and it can be put into practice.

Abstract: In this paper, the embedded license plate recognition system based on TMS320DM642 is researched. During the design, median filter, threshold, and morphology closing operations are used to obtain license plate region, then segmented into disjoint characters for the character recognition phase, where the template matching is used to identify the characters. Embedded License Plate Recognition System, being smaller, has less power consumption with respect to software based LPR systems. The resulting hardware is suitable for applications where cost, compactness, and efficiency are system design constraints.