Share Email Print
cover

Proceedings Paper • new

On differentiability of common image processing algorithms
Author(s): Alexander Zhukovsky
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present differentiable implementations of several common image processing algorithms: Canny edge detector, Niblack thresholding and Harris corner detector. The implementations are presented in the form of fully convolutional networks and explicitly arranged exactly to the original algorithms. Usage of such form of the algorithms allows to tune their parameters with a gradient descent. We performed parameter tuning in the edge detection problem and it shows that our implementation enables us to obtain better results on the BSDS-500 dataset. As a part of implementations of algorithms, we introduce a generalization of pooling method, which allows using arbitrary structure element. We also analyze the given neural network architectures and show the connections with contemporary approaches.

Paper Details

Date Published: 15 March 2019
PDF: 8 pages
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110410A (15 March 2019); doi: 10.1117/12.2523135
Show Author Affiliations
Alexander Zhukovsky, Moscow Institute of Physics and Technology (Russian Federation)
Smart Engines Ltd. (Russian Federation)


Published in SPIE Proceedings Vol. 11041:
Eleventh International Conference on Machine Vision (ICMV 2018)
Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top