Papers by Keyword: Machine Vision

Paper TitlePage

Authors: Fu Hai Huang
Abstract: In this paper a method of bar code detection and recognition is introduced, and discussed a combination of machine vision technology and virtual instrument, on this account, USB camera is used to capture images and detection and information extraction of the image of bar code, so user can store the function of product information. This method has very high recognition accuracy, speed and better practicality.
Authors: Qing Hua Wu, Na Dai, Tao He
Abstract: A Circle-shape is an important figure in most small rule mechanical parts, and usually be measured to get the radius or used as a stand calibration mark. In this paper, a 2-D circle measurement system for small rule mechanical parts based on machine vision is designed and built. The basic components and work principle of the machine vision measurement system are introduced, and the measurement produce is designed and discussed. An available algorithm for circle contour detected and fitted is described. Using this algorithm, the measurement software flow and architecture are built and the software system realized in the Microsoft visual studio program platform. Certainly, the calibration of machine vision system is introduced also. Using the system and method introduced above, an experiment is designed to measure the outer ring radius of one certain model bearing. The measured data is processed and analyzed. Through the experiment and result, it can be found that the measurement system can get relatively high precision and the measurement method is relatively steady, and the system precision and speed can be suit for the demand of on-line and real-time circle measurement.
Authors: Yuan Feng Zhu, Li Zhang, Ke Tian Li
Abstract: Adopting high-speed line scan industrial camera, through window function of the software to capture interested areas scanning by linear structured light, through image processing algorithms and splicing technique to extract 3D feature information of the detected object surface, combined with the camera calibration technology, calculated the three-dimensional coordinates of the detected object, and real-time displayed intuitive pseudo color map, monitored picture signal and weeded out unqualified products. Compared with similar systems at home and abroad, the system are real-time pseudo color graphics display, open system and lower cost.
Authors: Yan Fang, Xi Chen Yang, Jian Bo Lei
Abstract: A repair method for damaged parts based on laser robot system is proposed. First, to obtain 3D point cloud in the robot coordinate system, damaged part surfaces are scanned with binocular stereo vision system, including camera calibration and image matching. Secondly, with the point cloud data and laser processing parameters, system accomplishes path planning, generates robot programs. Experimental results show that system can effectively achieves 3D reconstruction and path planning, which further enable high precision remanufacturing.
Authors: Yao Wu Zhang, Xi Chen Yang
Abstract: As an advanced repair technology, the laser remanufacturing technology has been paid much more attentions recently. The authors previously studied the vision calibration by using the Matlab Calibration toolbox. Since the boundaries of a single image have to be specified manually, however, the Matlab toolbox based calibration method will be time consuming and low precision. This article continues the study of vision calibration for laser remanufacturing machine system and proposes a new binocular vision calibration method based on Halcon10.0 software. Experimental results show that the proposed calibration process consumes shorter time and is able to achieve higher precision.
Authors: Yun Ding, Yong Guang Yin
Abstract: In this paper, a novel close to real-time artificial intelligent system for enumerating Total Viable Bacteria (TVB) in drinking water was developed by using pattern recognition and machine vision technology. In order to identify the viable bacteria accurately, four shape features including circularity ratio, eccentricity, rectangularity, and compact degree, and four color features (GRsd, BRsd, HRsd, SRsd) of the stained viable bacteria image were extracted. An optimal artificial neural network was used as the bacterial recognition classifier, whose inputs were the extracted feature parameters and output was bacteria signal or non-bacteria signal. By using this intelligent system, TVB counts in each sample can be enumerated within 1 h, but the traditional Aerobic Plate Count (APC) method will take us 48 h. The comparative test also indicated that the counting results by two methods are closely correlated (R2=0.9942). This close to real-time accurate information may contribute to melioration and instauration of drinking water safety systems and risk management for TVB.
Authors: Shun Qing Xu
Abstract: This paper introduces operational path planning system of visual industrial robot, which could be applied to arc welding, cutting and gluing. It depicts a calibration method of camera coordinate. It gains environmental messages via the method of image acquisition. It uses the method of image procession to process the signals acquired. It fulfills robotic real-time control and offline programming. Practice has proved that this system has high repeatability precision, which can meet the challenge of arc welding, cutting and gluing, and also meet the needs of production line.
Authors: Bin Huang, Ping Wang, Si Le Ma
Abstract: In the fields of transparent liquid impurity detection based on machine vision technology, how to effectively detect impurities in the liquid is a difficult problem which has not yet been solved, mainly in the low recognition rate, the slow recognition speed, and the phenomenon of error detection and undetected. Therefore, this paper presents a new impurity detection method. Firstly, the hardware structure of the system is introduced in this paper. Then the flow diagram of impurity detection is presented. Finally, the algorithm of impurity detection is studied. Experiments show that the system introduced in this paper can identify impurities in liquid well on condition of ensuring the detection speed and detection accuracy.
Authors: Ming Heng Zhang, Long Hui Gang, Yi Bing Zhao
Abstract: Driving fatigue is one of the main reasons of traffic accident. In this field, the method based on multi-source information fusion has been a leading technique. A driver fatigue recognition model based on the Bayesian network was introduced in this paper. The real-time system monitored the state of the driver's features such as eyes, mouth and head movement through computer vision technique, their results were fused with Bayesian network inference algorithm and the final fusion result could be inferred according to the probability values of different variables states. Test results showed that this method could be more reasonably robust, reliable, and accurate in fatigue detection.
Authors: Hu Zhou, Jian Guo Yang
Abstract: Image measurement based on machine vision is a promising method for the precise measurements of machine parts. As for a large sized workpiece that exceeds the FOV (field of view) of the camera, image mosaic must be performed to implement measurement. While traditional template matching algorithms will lead to long runtime consumption, a combination of algorithms with precise mechanical positioning function using motion control was proposed and applied in the machine vision system. The manufacturing and installing errors have been taken into account to improve the positioning accuracy. This method minimized the search space and thereby reduced the runtime substantially. In addition, a stop criterion of the computation for the algorithms was applied to save a considerable amount of time in the process. Experimental results show that the precision of the image mosaic meets the requirements while speeding up the process significantly.
Showing 1 to 10 of 295 Paper Titles