The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in...The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.展开更多
To prevent a vehicle from departing the lane in assistant or automatic steering, real-time vision-based detection of lane is studied. The system architecture, detecting principle and lane model are described. Then the...To prevent a vehicle from departing the lane in assistant or automatic steering, real-time vision-based detection of lane is studied. The system architecture, detecting principle and lane model are described. Then the detecting algorithm of the lane image is discussed in detail. In this algorithm, several proper sub-windows in one image are first selected as the processing regions. To every sub-window, by means of such steps as appropriate pre-processing, edge detection and Hough transform, etc., the lane description features are extracted. Experimental results reveal that this detection method is of good real-time, high recognition reliability and strong robustness, etc., which can provide the decision-making foundation for the following automatic or assistant steering to some extent.展开更多
To realize high-precision automatic measurement of two-dimensional geometric features on parts, a cooperative measurement system based on machine vision is constructed. Its hardware structure, functional composition a...To realize high-precision automatic measurement of two-dimensional geometric features on parts, a cooperative measurement system based on machine vision is constructed. Its hardware structure, functional composition and working principle are introduced. The mapping relationship between the feature image coordinates and the measuring space coordinates is established. The method of measuring path planning of small field of view （FOV） images is proposed. With the cooperation of the panoramic image of the object to be measured, the small FOV images with high object plane resolution are acquired automatically. Then, the auxiliary measuring characteristics are constructed and the parameters of the features to be measured are automatically extracted. Experimental results show that the absolute value of relative error is less than 0. 03% when applying the cooperative measurement system to gauge the hole distance of 100 mm nominal size. When the object plane resolving power of the small FOV images is 16 times that of the large FOV image, the measurement accuracy of small FOV images is improved by 14 times compared with the large FOV image. It is suitable for high-precision automatic measurement of two-dimensional complex geometric features distributed on large scale parts.展开更多
An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of th...An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of the motion information over consecutive frames to extract object features and implements machine learning based on the bag of visual words approach. Instead of using a local feature descriptor only, the proposed system uses the co-occurring local features in order to increase feature discriminative power for both object model learning and inference stages. For different objects with different textures, a hybrid sampling strategy is considered. This hybrid approach minimizes the consumption of computation resources and helps achieving good performances demonstrated on a set of a dozen different daily objects.展开更多
A stereo matching algorithm based on the epipolar line constraint is designed to meet the real-time and the accuracy requirements. The algorithm is applied to photodynamic therapy binocular surveillance system for por...A stereo matching algorithm based on the epipolar line constraint is designed to meet the real-time and the accuracy requirements. The algorithm is applied to photodynamic therapy binocular surveillance system for port wine stain （PWS） when it monitors the position of the treatment region. The corner matching based on Hu moments is used to calculate the fundamental matrix of the binocular vision system. Experimental results are in agreement with the theoretical calculation.展开更多
基金supported by the 2021 Annual Scientific Research Funding Project of Liaoning Pro-vincial Department of Education(Nos.LJKZ0535,LJKZ0526)the Natural Science Foundation of Liaoning Province(No.2021-MS-300)。
文摘The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.
文摘To prevent a vehicle from departing the lane in assistant or automatic steering, real-time vision-based detection of lane is studied. The system architecture, detecting principle and lane model are described. Then the detecting algorithm of the lane image is discussed in detail. In this algorithm, several proper sub-windows in one image are first selected as the processing regions. To every sub-window, by means of such steps as appropriate pre-processing, edge detection and Hough transform, etc., the lane description features are extracted. Experimental results reveal that this detection method is of good real-time, high recognition reliability and strong robustness, etc., which can provide the decision-making foundation for the following automatic or assistant steering to some extent.
基金The National Natural Science Foundation of China(No.51175267)the Natural Science Foundation of Jiangsu Province(No.BK2010481)+2 种基金the Ph.D.Programs Foundation of Ministry of Education of China(No.20113219120004)China Postdoctoral Science Foundation(No.20100481148)the Postdoctoral Science Foundation of Jiangsu Province(No.1001004B)
文摘To realize high-precision automatic measurement of two-dimensional geometric features on parts, a cooperative measurement system based on machine vision is constructed. Its hardware structure, functional composition and working principle are introduced. The mapping relationship between the feature image coordinates and the measuring space coordinates is established. The method of measuring path planning of small field of view （FOV） images is proposed. With the cooperation of the panoramic image of the object to be measured, the small FOV images with high object plane resolution are acquired automatically. Then, the auxiliary measuring characteristics are constructed and the parameters of the features to be measured are automatically extracted. Experimental results show that the absolute value of relative error is less than 0. 03% when applying the cooperative measurement system to gauge the hole distance of 100 mm nominal size. When the object plane resolving power of the small FOV images is 16 times that of the large FOV image, the measurement accuracy of small FOV images is improved by 14 times compared with the large FOV image. It is suitable for high-precision automatic measurement of two-dimensional complex geometric features distributed on large scale parts.
基金The National Natural Science Foundation of China(No.60672094,60971098)
文摘An object learning and recognition system is implemented for humanoid robots to discover and memorize objects only by simple interactions with non-expert users. When the object is presented, the system makes use of the motion information over consecutive frames to extract object features and implements machine learning based on the bag of visual words approach. Instead of using a local feature descriptor only, the proposed system uses the co-occurring local features in order to increase feature discriminative power for both object model learning and inference stages. For different objects with different textures, a hybrid sampling strategy is considered. This hybrid approach minimizes the consumption of computation resources and helps achieving good performances demonstrated on a set of a dozen different daily objects.
基金Supported by the National High Technology Research and Development Program of China("863"Program)(2007AA04Z231)~~
文摘A stereo matching algorithm based on the epipolar line constraint is designed to meet the real-time and the accuracy requirements. The algorithm is applied to photodynamic therapy binocular surveillance system for port wine stain （PWS） when it monitors the position of the treatment region. The corner matching based on Hu moments is used to calculate the fundamental matrix of the binocular vision system. Experimental results are in agreement with the theoretical calculation.
