Current Issue : July - September Volume : 2015 Issue Number : 3 Articles : 4 Articles
Driving fatigue is one of the most important factors in trafficaccidents. In this paper,we proposed an improved strategy and practical\nsystem to detect driving fatigue based on machine vision and Adaboost algorithm. Kinds of face and eye classifiers are well trained\nby Adaboost algorithm in advance. The proposed strategy firstly detects face efficiently by classifiers of front face and deflected face.\nThen, candidate region of eye is determined according to geometric distribution of facial organs. Finally, trained classifiers of open\neyes and closed eyes are used to detect eyes in the candidate region quickly and accurately. The indexes which consist of PERCLOS\nand duration of closed-state are extracted in video frames real time.Moreover, the system is transplanted into smart device, that is,\nsmartphone or tablet, due to its own camera and powerful calculation performance. Practical tests demonstrated that the proposed\nsystem can detect driver fatigue with real time and high accuracy. As the system has been planted into portable smart device, it\ncould be widely used for driving fatigue detection in daily life....
The presented movable vision measurement for the three-dimensional (3D)\nsurface of a large-sized object has the advantages of system simplicity, low cost, and high\naccuracy. Aiming at addressing the problems of existing movable vision measurement\nmethods, a more suitable method for large-sized products on industrial sites is introduced\nin this paper. A raster binocular vision sensor and a wide-field camera are combined to\nform a 3D scanning sensor. During measurement, several planar targets are placed around\nthe object to be measured. With the planar target as an intermediary, the local 3D data\nmeasured by the scanning sensor are integrated into the global coordinate system. The\neffectiveness of the proposed method is verified through physical experiments....
Packaging the integrated circuit (IC) chip is a necessary step in the\nmanufacturing process of IC products. In general, wafers with the same size and process\nshould have a fixed number of packaged dies. However, many factors decrease the number\nof the actually packaged dies, such as die scratching, die contamination, and die breakage,\nwhich are not considered in the existing die-counting methods. Here we propose a robust\nmethod that can automatically determine the number of actual packaged dies by using\nmachine vision techniques. During the inspection, the image is taken from the top of the\nwafer, in which most dies have been removed and packaged. There are five steps in the\nproposed method: wafer region detection, wafer position calibration, dies region detection,\ndetection of die sawing lines, and die number counting. The abnormal cases of fractional\ndies in the wafer boundary and dropped dies during the packaging are considered in the\nproposed method as well. The experimental results show that the precision and recall rates\nreach 99.83% and 99.84%, respectively, when determining the numbers of actual packaged\ndies in the 41 test cases....
We propose a novel bolt-on module capable of\nboosting the robustness of various single compact 2D gait\nrepresentations. Gait recognition is negatively influenced by\ncovariate factors including clothing and time which alter\nthe natural gait appearance and motion. Contrary to traditional\ngait recognition, our bolt-on module remedies this by\na dedicated covariate factor detection and removal procedure\nwhich we quantitatively and qualitatively evaluate. The\nfundamental concept of the bolt-on module is founded on\nexploiting the pixel-wise composition of covariate factors.\nResults demonstrate how our bolt-on module is a powerful\ncomponent leading to significant improvements across gait\nrepresentations and datasets yielding state-of-the-art results...
Loading....