A quaternion deterministic monogenic CNN layer for contrast invariance
Document typePart of book or chapter of book
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder
Deep learning (DL) is attracting considerable interest as it currently achieves remarkable performance in many branches of science and technology. However, current DL cannot guarantee capabilities of the mammalian visual systems such as lighting changes. This paper proposes a deterministic entry layer capable of classifying images even with low-contrast conditions. We achieve this through an improved version of the quaternion monogenic wavelets. We have simulated the atmospheric degradation of the CIFAR-10 and the Dogs and Cats datasets to generate realistic contrast degradations of the images. The most important result is that the accuracy gained by using our layer is substantially more robust to illumination changes than nets without such a layer.
CitationMoya, E. [et al.]. A quaternion deterministic monogenic CNN layer for contrast invariance. A: "Systems, patterns and data engineering with geometric calculi". Berlín: Springer, 2021, p. 133-152.