Advanced Materials Research Vols. 860-863

Abstract: A novel integrated mathematical model for the devaluation of residential buildings with time is presented. Devaluation model is an useful tool to predict residual life span of the building. Knowing how building behaves with time, one can influence on its properties by the means of renovation or reconstruction activities which counteract the aging processes. This approach can be regarded as the way to make total service life span of residential buildings longer.

Abstract: Discuss extracting the contour of region with Visual C++. The first step is to clear burr of contour in threshed image, whose purpose is to prevent endless loop. The algorithm to extract the contour is put forward, and the detailed steps are given out, too. And the main program code in visual C++ is given out, too. This method is not only real-time, but also needs less memory. In this paper, detecting moving targets is used as example to prove this algorithm. At the end, experiment proves the good effect of the method.

Abstract: There are a lot of methods to select threshold in image processing. Because BP neural network can adapt to fixed environment, it is applied in this area in this paper. Firstly, according to the feature of image, BP neural network is constructed. The input items of network are the features of image. The mean value and variance of gray in the image is the important features of image, so two input items can be chosen. The output items are the values of threshold. If one threshold is chosen, one output item can be chosen. In some condition, two thresholds should be set, then two output items would be chosen. In order to overcome the shortcomings of BP neural network, it should be improved by certain momentum which is used to avoid local minimums. In order to speed the training of the network, adaptive learning rate should be used, too. The BP neural network establishes the relationship between the features of image and the threshold. After training, the network can select suitable threshold for images in fixed environment. Some practical images are used to prove its good effect.

Abstract: The article main introduction take the STC monolithic integrated circuit as master control MCU,through MCU in car license inserting realization to vehicles information read,as well as carries on localization tracing to the vehicles,and through special-purpose equipment read car license in information.

Abstract: The disunion of communication protocol standards at present creates a huge barrier against the interconnection and interoperability of heterogeneous devices in home. To solve this problem, a method of multiple protocols conversion of home gateway was proposed to integrate a variety of heterogeneous protocol networks. Firstly, a new task description language based on ClassAD was designed to describe different heterogeneous devices for communicating each other in home networks. And a plug-in expansion mechanism was introduced to improve the scalability of heterogeneous protocols and the throughput of home networks system. As a result, the ability of semantic interoperability of heterogeneous devices is achieved to integrate new applications and drivers into the deployed intelligent home system during runtime based on the proposed home gateway.

Abstract: Edge detection is an important field in image processing. Edge detection is in the forefront of image processing for object detection, it is crucial to have a good understanding of edge detection techniques. Various image edge detection techniques are introduced. These techniques are compared by using MATLAB7.0. The qualities of these techniques are elaborated. The results show that Canny edge detection techniques is better than others.

Abstract: Thresholding is one of the critical steps in pattern recognition and has a significant effect on the upcoming steps of image application, the important objectives of thresholding are as follows, and separating objects from background, decreasing the capacity of data consequently increases speed. Various threshold segmentation methods are studied. These methods are compared by using MATLAB7.0. The qualities of image segmentation are elaborated. The results show that iterative threshold segmentation method is better than others.

Abstract: with the development of intelligent transportation technology, which all countries are suitable for their own license plate recognition system is developed. But because of the CCD camera Angle problem will make license plate image tilt; Segmentation after do not match the characters in size and character discontinuity, led to license plate recognition rate is not high, speed slow, reduce the real-time performance of the system. In order to improve the rate of convergence, the recognition rate presents a license plate recognition algorithm based on BP neural network. First put the image correction, segmentation of character normalization processing and eliminate the unfavorable factors, then puts forward characteristics of characters input for training the BP neural network. By setting the network weights and training transfer function, improved algorithm to improve the recognition rate of the system, as well as the real-time performance.

Abstract: In view of the heterogeneous gulf between service providers and resource service demanders in cloud manufacturing platform, an ontology mapping reusing algorithm was proposed to improve the performance of service discovery. Firstly, a semantic bipartite graph between the concepts profile was built to get the similarity of neighboring concepts from the best match of the bipartite graph. Then inspired by the similarity transmission between neighboring concepts, whether the new mapping should be established was decided by the existing mapping and the similar degree between the neighboring concepts. Finally, I testified the algorithm by an experiment.

Abstract: This article presents the design ideas of patrol system based on real-time image acquisition in patrol points. In this system, the image acquisition terminals are mounted on many patrol points, which are set in a predetermined patrol line. When patrol officers arrived at a patrol point, the image acquisition terminal mounted on the patrol point will capture a live image via a GPRS MMS module ,and then the image acquisition terminal sends this image to the central control unit in a form of MMS. The central control unit receives the sent MMS message, and separate out the image information from the received message, and then saves it to a database. According to the actual test results of this patrol system, it can not only meet the design requirements, but also the whole system has a high stability and reliability.