Improving correlation method with convolutional neural networks

Autor:	Goncharov, Dmitriy, Starikov, Rostislav
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Electrical Engineering and Systems Science - Image and Video Processing
Druh dokumentu:	Working Paper
Popis:	We present a convolutional neural network for the classification of correlation responses obtained by correlation filters. The proposed approach can improve the accuracy of classification, as well as achieve invariance to the image classes and parameters. Comment: 8 pages, 3 figures, 2 tables, 1 formula
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.09430 Zobrazit plný text záznamu View this record from Arxiv