17 March 2017 Combining convolutional neural networks and Hough Transform for classification of images containing lines
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103411C (2017) https://doi.org/10.1117/12.2268717
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
Abstract
In this paper, we propose an expansion of convolutional neural network (CNN) input features based on Hough Transform. We perform morphological contrasting of source image followed by Hough Transform, and then use it as input for some convolutional filters. Thus, CNNs computational complexity and the number of units are not affected. Morphological contrasting and Hough Transform are the only additional computational expenses of introduced CNN input features expansion. Proposed approach was demonstrated on the example of CNN with very simple structure. We considered two image recognition problems, that were object classification on CIFAR-10 and printed character recognition on private dataset with symbols taken from Russian passports. Our approach allowed to reach noticeable accuracy improvement without taking much computational effort, which can be extremely important in industrial recognition systems or difficult problems utilising CNNs, like pressure ridge analysis and classification.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alexander Sheshkus, Elena Limonova, Dmitry Nikolaev, Valeriy Krivtsov, "Combining convolutional neural networks and Hough Transform for classification of images containing lines", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103411C (17 March 2017); doi: 10.1117/12.2268717; https://doi.org/10.1117/12.2268717
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT


Back to Top