Papers by Keyword: Machine Vision

Abstract: This paper studies the automatic test system of bus dashboard EOL (end of line) based on machine vision. Based on machine vision theory, Identification and detection algorithm of panel signal indicator elements and tachometer pointer readings was studied combining single-frame still images and real-time processing of color video image, the automatic parallel detection of multiple dashboard was realized by distributed network architecture. This paper first describes the function requirements, the overall composition and working principle of automatic test system. Then, it proposes an automatic identification and detection algorithm of dashboard symbol sheets and pointer position. Finally, it shows the designing of automatic test software with a self-learning and auto-detection function, and describes the working process of the software. The tests prove that the system is capable of realizing fast and accurate auto-test of bus dashboard functions based on the non-contact of machine vision, which improves the overall efficiency of the bus dashboard line.

Abstract: The development and application of the machine vision technology is greatly liberating the human labor force and improved the production automation level and the situation of human life, which has very broad application prospects. The intelligent empty bottle inspection robot this paper studies is a typical application of the machine vision in the industrial detection. This paper mainly introduces the concept of machine vision, some important technology related to automatic cleaning robots and application of the machine vision in the production of all areas of life.

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.

Abstract: In order to solve the defect detection problems of black line and white line of QR Code. According to the linear properties of defect, this paper puts forward a kind of defect detection algorithm based on Hough Transform and vertical projection. Through the experiment testing, the accuracy of algorithm detection reached 98.57%, the average test time is 38.28ms. This algorithm can be transplanted to other types of QR code and industrial on-line detection system.

Abstract: There are a great amount of electronic meters equipped in the distribution substations, which were traditionally monitored by operators. On-site monitoring for risk assessment of these meters is very important. In this paper, we presented an advanced machine vision based automatic meter detection method toward the development of an online automatic meter reading intelligent inspection robot in substation. Firstly, the image received from the inspection robot was enhanced using histogram equalization. Then, the image was segmented into two parts based on the threshold obtained by Otsu’s method. Using these two parts, and the whole enhanced image, circular Hough transformation was applied on these three images and detected the circle with highest probability on them. The normalized correlation coefficients were calculated between the corresponding areas of those three circles from three images and the template image of SF₆ meter. Finally, the circle with highest correlation coefficient, which was higher than a certain threshold, was determined to be the meter. If it is lower than the threshold, the algorithm would decide that no meter was found in the image. The method was tested with 222 images obtained in one substation in Xi’an, Shanxi, China, and an 87.4% accuracy was achieved using these images, which indicated the potential of this method.

Abstract: With the constant improvement of the living standard of the people and the increased expectations for food products of high quality and safety standards, the quality of food materials needs to satisfy the higher demand. The separation quality of the cereals and oils is one of the key factors for ensuring food quality. The traditional separating methods have many shortages such as inconsistency and uncertainty. The machine vision technology applied in the separation processing can realize the quality inspection of products and satisfy the requirements of objectivity, accuracy, consistency, efficiency and online inspection. So machine vision technology improves the separating quality of cereals and oils and realize the intelligence and the automation in the separating process.

Abstract: Technology of machine vision is used to measure the inside and outside diameter and concentricity of the optical fiber connector internal parts without contact. The image is got by million-pixel industrial camera. Then the image gets pretreatment, such as, grayscale transformation, binarization, smoothing, etc. Appropriate detection threshold is found by the image analysis. The edge of parts is found by the circular probe method. Inside and outside diameter and concentricity of parts are obtained by using the edge of the data through the least squares method. Experiment of 6.4 mm diameter parts, absolute error is less than one pixel. The largest error is less than 0.05 mm compared with the manual measurements and can meet the measurement requirements.

Abstract: Real-time detecting information marked on billets is important for automatically manufacturing and management in steelworks. But due to the tough production environments in steel enterprises, capturing and identifying characters marked on hot billets have many challenges. This paper presents a real-time image capturing and segmenting method with machine vision for characters marked on hot billets, and characters area is located based on color information of images. Furthermore, considering the marked characters are often slant, we proposed a kind of characters skew correction method to adjust the alignment of characters, and then segment characters into singles for recognition. Finally, with the proposed method, we have conducted some experiments in Baosteel Company. The result shows that our method can achieve 97% segmentation rate if we select proper image acquisition device and preprocessing algorithm. Additionally, it provides a new way for steel enterprise real-time capturing and segmenting marked characters image.

Abstract: In this paper, a new yarn appearance measurement system based on machine vision is introduced. The yarn images are continuously captured by image acquisition system. To extract the main body of the yarn accurately, the yarn images are processed sequentially with threshold segmentation and morphological opening operation. Then the coefficient of variation (CV value) of diameter is calculated to characterize the yarn evenness. The measurement process achieves result (CV value) which can be compared with USTER evenness tester by image processing techniques. By comparing different methods which use different algorithms, a suitable method is chosen to be used in this new measurement system. Then a more accurate, more efficient and faster measurement system will meet requirements in the future.

Abstract: As an important part of Advanced Driver Assistance System (ADAS), the traffic sign detection has been paid more and more attention. This paper studied and implemented a valid algorithm of traffic sign detection. Using K-means clustering algorithm to complete the image separation and extraction of prohibition signs from the RGB color image, and then matching them with templates to realize the detection of traffic signs by SIFT algorithm. Series of experiments for traffic sign detection have been carried out to prove the validity and correctness of the algorithm on the basis of the road images in front of the vehicle collected by CCD camera.