Search

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

For each layer of the traditional hourglass network, using a single receptive field to extract features will lack the description of the overall and local related information of the key points, and it will be difficult to locate in complex situations such as illumination and occlusion. This paper proposed a new residual hourglass network (NRHG), which used the new residual module as the basic unit of the hourglass network. The new residual module added a new convolution branch to increase the network ' s receptive field for better extraction. To the characteristic information at different scales, the new receptive field increased the description of the network ' s overall information, and adjusted the size of the new convolutional branch receptive field for different layers of the network to balance the relationship between the feature map resolution and the receptive field. While better retaining the structural information from the local to the whole, it highlighted the local details of the network, and helped to locate key points in complex situations such as illumination and occlusion. In addition, this paper used intermediate supervision between the hourglass networks, and compared the results of each hourglass network output to avoid the problem of gradient degradation caused by network depth. Through a large number of experiments on the 300-W, IBUG, COFW dataset, it proves the effectiveness of the proposed method,and the experimental results are superior to the traditional hourglass network . [ABSTRACT FROM AUTHOR]

The traditional feature selection method of chi-square test and information gain in text classification has its inherent defect. This paper analyzed the key of feature selection in text classification being to select feature words distributed evenly and frequently in each type of documents. This should consider not only the document frequency and term frequency of feature words, but also the inter class concentration degree and the intra class scatter degree of feature words, ft proposed a feature selection evaluation function that is based on document frequency of within-class and between-class and term frequency statistics. The feature selection evaluation function could select a certain proportion of the feature words in each category of the training set to form the corresponding class of the feature word library. The entire feature word library of the training set could be composed by each of such classes as a result, ft carried out the experiment of Chinese text classification based on SVM. The experimental results show that the proposed method improves the effectiveness of text classification to a certain extent, compared with the traditional chi-square test and information gain. [ABSTRACT FROM AUTHOR]