Wavelet based edge feature enhancement for convolutional neural networks

D. D. N. De Silva; S. Fernando; I. T. S. Piyatilake; A. V. S. Karunarathne

doi:10.1117/12.2522849

15 March 2019 Wavelet based edge feature enhancement for convolutional neural networks

D. D. N. De Silva, S. Fernando, I. T. S. Piyatilake, A. V. S. Karunarathne

Proceedings Volume 11041, Eleventh International Conference on Machine Vision (ICMV 2018); 110412R (2019) https://doi.org/10.1117/12.2522849
Event: Eleventh International Conference on Machine Vision (ICMV 2018), 2018, Munich, Germany

Abstract

Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary level features like edges. We propose and evaluate two wavelet-based edge-feature enhancement methods to preprocess the input images to convolutional neural networks. The first method develops representations by decomposing the input images using wavelet transform and limited reconstructing subsequently. The second method develops such feature-enhanced inputs to the network using local modulus maxima of wavelet coefficients. For each method, we have developed a new preprocessing layer by implementing each proposed method and have appended to the network architecture. Our empirical evaluations demonstrate that the proposed methods are outperforming the baselines and previously published work.

Citation Download Citation

D. D. N. De Silva, S. Fernando, I. T. S. Piyatilake, and A. V. S. Karunarathne "Wavelet based edge feature enhancement for convolutional neural networks", Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110412R (15 March 2019); https://doi.org/10.1117/12.2522849

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