Face recognition approaches that are based on deep convolutional neural networks (CNN) have been dominating the field. The performance improvements they have provided in the so called in-the-wild datasets are significant, however, their performance under image quality degradations have not been assessed, yet. This is particularly important, since in real-world face recognition applications, images may contain various kinds of degradations due to motion blur, noise, compression artifacts, color distortions, and occlusion. In this work, we have addressed this problem and analyzed the influence of these image degradations on the performance of deep CNN-based face recognition approaches using the standard LFW closed-set identification protocol. We have evaluated three popular deep CNN models, namely, the AlexNet, VGG-Face, and GoogLeNet. Results have indicated that blur, noise, and occlusion cause a significant decrease in performance, while deep CNN models are found to be robust to distortions, such as color distortions and change in color balance.

No abstract

Accelerated investments on wind power projects because of the great demand for renewable energy are increasing the concerns about deteriorating effects of wind turbines on the performance of civil and military radar, navigation and communications systems. In this study, the authors introduce a preliminary set of analysis for assessing the performance of electronic systems such as radar, communications and navigation systems and the degrading/deteriorating effects of wind turbines. The analysis quantifies the performance degradation in the electronic systems. The proposed study can be used as a tool by decision makers in the planning and designing phases of both electronic systems and wind turbines to reduce the adverse effects of the wind farms on the mentioned systems.

No abstract