Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Evaluating the Impact of Color Information in Deep Neural Networks

: Buhrmester, Vanessa; Münch, David; Bulatov, Dimitri; Arens, Michael


Morales, A.:
Pattern Recognition and Image Analysis. 9th Iberian Conference, IbPRIA 2019. Proceedings. Pt.1 : Madrid, Spain, July 1-4, 2019
Cham: Springer Nature, 2019 (Lecture Notes in Computer Science 11867)
ISBN: 978-3-030-31331-9 (Print)
ISBN: 978-3-030-31332-6 (Online)
Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) <9, 2019, Madrid>
Conference Paper
Fraunhofer IOSB ()
color space representation; degraded texture; color dependence; robustness of color model change; ClusterML

Color images are omnipresent in everyday life. In particular, they provide the only necessary input for deep neural network pipelines, which are continuously being employed for image classification and object recognition tasks. Although color can provide valuable information, effects like varying illumination and specialties of different sensors still pose significant problems. However, there is no clear evidence how strongly variations in color information influence classification performance throughout rearward layers. To gain a deeper insight about how Convolutional Neural Networks make decisions and what they learn from input images, we investigate in this work suitability and robustness of different color augmentation techniques. We considered several established benchmark sets and custom-made pedestrian and background datasets. While decreasing color or saturation information we explore the activation differences in the rear layers and the stability of confidence values. We show that Luminance is most robust against changing color system in test images irrespective of degraded texture or not. Finally, we present the coherence between color dependence and properties of the regarded datasets and classes.