Inspec keywords: brightness; computer vision; feedforward neural nets; image coding; data compression; face recognition; image colour analysis; learning (artificial intelligence)

Other keywords: compression artifacts; blur; model characteristics; labelled faces in the wild dataset; SqueezeNet; image degradations; occlusion; descriptor-computation strategy; deep convolutional neural network based approach; image quality; missing pixels; face verification performance; image brightness; VGG-Face; descriptor computation; model architectures; face recognition; computer vision tasks; CNN architecture; colour information; deep CNN models; contrast; noise; learning techniques; AlexNet; deep learning model strength; GoogLeNet; deep learning model weakness; Joint Photographic Experts Group compression

Subjects: Knowledge engineering techniques; Image and video coding; Neural computing techniques; Image recognition; Computer vision and image processing techniques