当前位置:
X-MOL 学术
›
J. Comput. Syst. Sci. Int.
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Training a Classifier by Descriptors in the Space of the Radon Transform
Journal of Computer and Systems Sciences International ( IF 0.5 ) Pub Date : 2020-07-12 , DOI: 10.1134/s1064230720030053 N. A. Samsonov , A. N. Gneushev , I. A. Matveev
中文翻译:
在Radon变换空间中通过描述符训练分类器
更新日期:2020-07-12
Journal of Computer and Systems Sciences International ( IF 0.5 ) Pub Date : 2020-07-12 , DOI: 10.1134/s1064230720030053 N. A. Samsonov , A. N. Gneushev , I. A. Matveev
Abstract
The problem of detecting objects in images is solved by training the classifier by the descriptors constructed based on the local Radon transform of the gradient field of the image. The space of the Radon transform is considered as the Hough space accumulator in which projections are constructed. The set of local projections forms a descriptor of the region related to the object that is a generalization of the known histogram of oriented gradients (HOG) descriptor. The issues of the effect of the approximation of the Radon transform contribution function, the form of local normalization, and the number of directions in the projection histograms on the results of detecting pedestrians are investigated. The results produced by the proposed descriptor are compared with the results obtained using the HOG descriptor and convolutional neural networks (CNN) based on the ResNext and MobileNet architectures on the INRIA and CityScapes databases.中文翻译:
在Radon变换空间中通过描述符训练分类器