On differentiability of common image processing algorithms

Alexander Zhukovsky

doi:10.1117/12.2523135

15 March 2019 On differentiability of common image processing algorithms

Alexander Zhukovsky

Proceedings Volume 11041, Eleventh International Conference on Machine Vision (ICMV 2018); 110410A (2019) https://doi.org/10.1117/12.2523135
Event: Eleventh International Conference on Machine Vision (ICMV 2018), 2018, Munich, Germany

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.

Citation Download Citation

Alexander Zhukovsky "On differentiability of common image processing algorithms", Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110410A (15 March 2019); https://doi.org/10.1117/12.2523135

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available