分布式多通道计算机视觉测量系统

提出了一种新颖的分布式多通道计算机视觉测量系统 ,并成功地解决了钢卷尺自动检测问题。讨论了系统的原理、HUB控制器的设计、图像自动识别与自动检测以及定时器编程等核心技术。实践证明 。

Facial expression feature extraction method based on improved LBP

Local binary pattern(LBP)is an important method for texture feature extraction of facial expression.However,it also has the shortcomings of high dimension,slow feature extraction and noeffective local or global features extracted.To solve these problems,a facial expression feature extraction method is proposed based on improved LBP.Firstly,LBP is converted into double local binary pattern(DLBP).Then by combining Taylor expansion(TE)with DLBP,DLBP-TE algorithm is obtained.Finally,the DLBP-TE algorithm combined with extreme learning machine(ELM)is applied in seven kinds of ficial expression images and the corresponding experiments are carried out in Japanese adult female facial expression(JAFFE)database.The results show that the proposed method can significantly improve facial expression recognition rate.

Improved nonconvex optimization model for low-rank matrix recovery

Low-rank matrix recovery is an important problem extensively studied in machine learning, data mining and computer vision communities. A novel method is proposed for low-rank matrix recovery, targeting at higher recovery accuracy and stronger theoretical guarantee. Specifically, the proposed method is based on a nonconvex optimization model, by solving the low-rank matrix which can be recovered from the noisy observation. To solve the model, an effective algorithm is derived by minimizing over the variables alternately. It is proved theoretically that this algorithm has stronger theoretical guarantee than the existing work. In natural image denoising experiments, the proposed method achieves lower recovery error than the two compared methods. The proposed low-rank matrix recovery method is also applied to solve two real-world problems, i.e., removing noise from verification code and removing watermark from images, in which the images recovered by the proposed method are less noisy than those of the two compared methods.

Research and application on wireless remote measurement system of drill hydrology

The configuration, function, principle of operation and the main design of the wireless remote measurement system of drill hydrology based on GPRS were introduced in this paper. The current resources of GPIRS network was used by the system, and water level, water temperature and turbidity were measured by the intelligent sensors. Then the data were transmitted to the monitoring computer by the GPRS modem in wireless, which processed the data, forecasted and predicted water disaster. The monitoring computer software has the Chinese operation interface in the windows circumstance with simple and convenience using. The managers can operate every function by the Chinese cue. The data communications between the remote indicating instrument distributing in every drill and the monitoring computer is built only by one monitoring computer. The technology of data collection, GPRS wireless communication, computer, data processing, database were collected by the system, some functions such as real time supervising, early-warning, decision-making supporting, and so on had been achieved. The system has such merits as high precision, low cost, flexible distributing, credible transmitting and simple operation.

Method for Signals Detection in Single Crystal Diffraction Patterns through a Diffraction Pattern Indexing Software

The correct use of information in science and technology is very important for its progress. Nowadays, the equipment used for the scientific and technological development provides results that are later interpreted by the researchers, in most of the above mentioned equipment the results are images full of information which has to be analyzed. A powerful stage with multiple benefits in this field is the image pre-processing by means of intelligent systems, which are capable to do image analysis throwing very useful results that enhance the scientific and technological information. There are currently more than 500 functions in the computational vision specialized open source library OpenCV, which associated with the C＋＋ programming language. These functions are used for application development in many areas of computer vision such as products inspection, medical images, safety, user＇s interfaces, camera calibration, stereoscopic vision and robotics. In this development and research work, by using the available functions and modifying the exposed methods, we present a proposal for signal detection in images originated in the transmission electron microscope （known as diffraction patterns）, which are attached to the detailed analysis of crystalline structures used in the study of the materials science, the results show a profit of at least 18% in the detection of signs by means of the method proposed in this work.

Theoretical Research on Novel Data Mining Algorithm based on Fuzzy Clustering Theory and Deep Neural Network

With the progress of computer technology, data mining has become a hot research area in the computer science community. In this paper, we undertake theoretical research on the novel data mining algorithm based on fuzzy clustering theory and deep neural network. The focus of data mining in seeking the visualization methods in the process of data mining, knowledge discovery process can be users to understand, to facilitate human-computer interaction in knowledge discovery process. Inspired by the brain structure layers, neural network researchers have been trying to multilayer neural network research. The experiment result shows that out algorithm is effective and robust.