Current Issue : April - June Volume : 2015 Issue Number : 2 Articles : 5 Articles
We describe the development and application of a robot vision based adaptive algorithm for the quality control of the braided\nsleeving of high pressure hydraulic pipes.With our approach, we can successfully overcome the limitations, such as low reliability\nand repeatability of braided quality, which result from the visual observation of the braided pipe surface.The braids to be analyzed\ncome in different dimensions, colors, and braiding densities with different types of errors to be detected, as presented in this paper.\nTherefore, our machine vision system, consisting of a mathematical algorithm for the automatic adaptation to different types of\nbraids and dimensions of pipes, enables the accurate quality control of braided pipe sleevings and offers the potential to be used\nin the production of braiding lines of pipes. The principles of the measuring method and the required equipment are given in the\npaper, also containing the mathematical adaptive algorithm formulation.The paper describes the experiments conducted to verify\nthe accuracy of the algorithm. The developed machine vision adaptive control system was successfully tested and is ready for the\nimplementation in industrial applications, thus eliminating human subjectivity....
An electric wheelchair is the device to support the self-movement of the elderly and people with physical disabilities. In this paper, a prototype design of an electric wheelchair with a high level of mobility and safety is presented. The electric wheelchair has a high level of mobility by employing an omnidirectional mechanism. Large numbers of mechanisms have been developed to realize omnidirectional motion. However, they have various drawbacks such as a complicated mechanism and difficulty of employment for practical use. Although the ball wheel drive mechanism is simple, it realizes stable motion when negotiating a step, gap, or slope. The high level of mobility enhances the freedom of users while increasing the risk of collision with obstacles or walls. To prevent collisions with obstacles, some electric wheelchairs are equipped with infrared sensors, ultrasonic sensors, laser range finders, or machine vision. However, since these devices are expensive, it will be difficult for them to be widely used with electric wheelchairs. We have developed a prototype design of collision-detecting device with inexpensive sensors. This device detects the occurrence of collisions and can calculate the direction of the colliding object. A prototype has been developed to perform motion experiments and verify the accuracy of the device. The results of experiments are also presented in this paper....
The new visual inspection systems techniques using real time machine vision replace the human visual\nmanual inspection on PCB flux defects, which brings harmful effects on the board which may come in\nthe form of corrosion and can cause harm to the assembly. In short, it brings improvement in Printed\nCircuit Boards (PCB) production quality, principally concerning the acceptance or rejection of the\nPCB boards. To develop new algorithm in image processing which detects flux defect at PCB board\nduring re-flow process and achieve good accuracy of the PCB quality checking. The machine will be\ndesigned and fabricated with the total automation control system with mechanical PCB loader/unloader,\npneumatic system handler with vacuum cap, vision inspection station and final classification\nstation (accept or reject). The image processing system is based on shape (pattern) and color image\nanalysis techniques with Matrox Imaging Library. The shape/texture of the PCB pins is analyzed by\nusing pattern matching technique to detect the PCB flux defect area. The color analysis of the flux\ndefect in a PCB boards are processed based on their red color pixel percentage in Red, Green and Blue\n(RGB) model. The red color filter band mean value of histogram is measured and compared to the\nvalue threshold to determine the occurring on the PCB flux defects. The system was tested with PCB\nboards from factory production line and achieved PCB board flux defects sorting accuracy at 86.0%\nbased on proposed pattern matching technique combined with red color filter band histogram....
Accurate detection and identification of fruits is critically important for the success of developing automated apple\nharvesting system. Research has been conducted to identify apples in orchard environment with reasonable accuracy when\napples are clearly visible or partially occluded. However, only limited work has been carried out to identify fruit in clusters,\nwhich is critically important as fruit clusters are common in field conditions. This work focused on accurately identifying\npartially visible apples and apples in clusters using a machine vision system. An over the row platform with tunnel structure\nand artificial lighting was used to increase uniformity in imaging environment. Iterative Circular Hough Transform (CHT)\nwas used to detect clearly visible fruit as well as individual fruit in cluster. Partially occluded apples were detected using blob\nanalysis; a clustering algorithm based on Euclidean distance between centroids of blobs was used to merge the parts of an\napple divided by occlusion. Potential fruit detected by CHT and blob analysis were passed through a color identification\nprocess to decide if they were apples. This algorithm was successfully tested with 60 images of apple trees and resulted with\n90% apple identification accuracy. On average, CHT detected 54% of total identified apples whereas blob analysis detected\nremaining 46% with overall false positive of 1.8% and false negative of 8.2%. The fusion of blob analysis and CHT\nsignificantly increased detection accuracy compared to individual methods exclusively including that in clusters. The results\nshowed potential for in-field apple identification for automated apple harvesting....
We present a new analysis tool for cervical flexion-extension radiographs based on machine vision and computerized image\nprocessing. The method is based on semiautomatic image segmentation leading to detection of common landmarks such as the\nspinolaminar (SL) line or contour lines of the implanted anterior cervical plates. The technique allows for visualization of the local\ncurvature of these landmarks during flexion-extension experiments. In addition to changes in the curvature of the SL line, it has\nbeen found that the cervical plates also deform during flexion-extension examination. While extension radio graphs reveal larger\ncurvature changes in the SL line, flexion radio graphs on the other hand tend to generate larger curvature changes in the implanted\ncervical plates. Furthermore, while some lordosis is always present in the cervical plates by design, it actually decreases during\nextension and increases during flexion. Possible causes of this unexpected finding are also discussed.The described analysis may lead\nto a more precise interpretation of flexion-extension radiographs, allowing diagnosis of spinal instability and/or pseudoarthrosis\nin already seemingly fused spines....
Loading....