Light conditions affect the performance of computer vision algorithms by creating spatial changes in color and intensity across a scene. Convolutional neural networks (CNNs) use color components of the input image and, as a result, are sensitive to ambient light conditions. This work analyzes the influence of ambient light conditions on CNN classifiers. We suggest a method for boosting the performance of CNN-based object detection and classification algorithms by using light invariant video imaging (LIVI). LIVI neutralizes the influence of ambient light conditions and renders the perceived object's appearance independent of the light conditions. Training sets consist mainly, if not only, of objects in natural light conditions. As such, using LIVI boosts CNN performance by matching object appearance to that expected by the CNN model, which was created according to the training set. We further investigate the use of LIVI as a general self-supervised learning framework for CNN. Faster region-based CNN (Faster R-CNN) was used as a case study in order to validate the importance of light conditions on CNN performance and on how it can be improved by using LIVI as an input or feedback mechanism in a self-supervised framework. We show that LIVI enables reduced CNN size, enhanced performance and improved training.

Controlled light conditions improve considerably the performance of most computer vision algorithms. Dynamic light conditions create varying spatial changes in color and intensity across the scene. These condition, caused by a moving shadow for example, force developers to create algorithms which are robust to such variations. We suggest a computational camera which produces images that are not influenced by environmental variations in light conditions. The key insight is that many years ago, similar difficulties were already solved in radio communication, As a result each channel is immune to interference from other radio channels. Amplitude Modulated (AM) video camera separates the influence of a modulated light from other unknown light sources in the scene, Causing the AM video camera frame to appear the same - independent of the light conditions in which it was taken. We built a prototype of the AM video camera by using off the shelf hardware and tested it. AM video camera was used to demonstrate color constancy, shadow removal and contrast enhancement in real time. We show theoretically and empirically that: 1. the proposed system can produce images with similar noise levels as a standard camera. 2. The images created by such camera are almost completely immune to temporal, spatial and spectral changes in the background light.

One of the most important issues for researchers developing image processing algorithms is image quality. Methodical quality evaluation, by showing images to several human observers, is slow, expensive, and highly subjective. On the other hand, a visual quality matrix (VQM) is a fast, cheap, and objective tool for evaluating image quality. Although most VQMs are good in predicting the quality of an image degraded by a single degradation, they poorly perform for a combination of two degradations. An example for such degradation is the color crosstalk (CTK) effect, which introduces blur with desaturation. CTK is expected to become a bigger issue in image quality as the industry moves toward smaller sensors. In this paper, we will develop a VQM that will be able to better evaluate the quality of an image degraded by a combined blur/desaturation degradation and perform as well as other VQMs on single degradations such as blur, compression, and noise. We show why standard scalar techniques are insufficient to measure a combined blur/desaturation degradation and explain why a vectorial approach is better suited. We introduce quaternion image processing (QIP), which is a true vectorial approach and has many uses in the fields of physics and engineering. Our new VQM is a vectorial expansion of structure similarity using QIP, which gave it its name-Quaternion Structural SIMilarity (QSSIM). We built a new database of a combined blur/desaturation degradation and conducted a quality survey with human subjects. An extensive comparison between QSSIM and other VQMs on several image quality databases-including our new database-shows the superiority of this new approach in predicting visual quality of color images.