Deep Learning Applied in Computer Vision

Abstract ―​

Computer vision is a multidisciplinary field in computational intelligence and artificial intelligence that guide intelligent systems and machines towards understanding the content of images or video. It has come under the spotlight in recent times due to the remarkable advancement and breakthroughs day-by-day such as autonomous driving, intelligent systems, pedestrian system, robotics, medical imaging, remote sensing, object detection, security, speech sequence, image registration, biometric technologies, image retrieval and video processing to mention just a few. The aim of this work is to provide a systematic review in the application of deep learning in various aspects of computer vision that is object detection, object classification, scene classification, image segmentation, image retrieval, image registration, object recognition, feature extraction, image fusion and anomaly detection by providing detail description in a systematic way of all the deep learning techniques; Convolutional Neural Network (CNN), Deep Boltzmann Machine (DBM) and Deep Belief Network (DBN) that are applied in solving this problem of computer vision. This work also explored all the review and survey researches that applied deep learning techniques in computer vision in a systematic format and identify the countries that the researches were conducted which is one of the unique attributes of this paper that makes it exceptional in a state-of-art review and surveys. In addition to datasets that were used in the recent research of computer vision with the software and toolboxes used for the implementation of deep learning techniques in computer vision. We have also identified all the top journals (ISPRS Journal of Photogrammetry and Remote sensing, IEEE Geoscience and Remote Sensing Letter, IEE Transaction of Geoscience and Remote sensing etc.) and conferences proceedings (IEEE Conference of Computer vision and Pattern recognition) for advanced publication of computer vision researches in the world. This work would serve as a roadmap for any researcher that wants to use deep learning algorithms in computer vision.