Deep Learning in Computer Vision Principles and Applications

Deep learning algorithms have brought a revolution to the computer vision community by introducing non-traditional and efficient solutions to several image-related problems that had long remained unsolved or partially addressed. This book presents a collection of eleven chapters where each individual chapter explains the deep learning principles of a specific topic, introduces reviews of up-to-date techniques, and presents research findings to the computer vision community. The book covers a broad scope of topics in deep learning concepts and applications such as accelerating the convolutional neural network inference on field-programmable gate arrays, fire detection in surveillance applications, face recognition, action and activity recognition, semantic segmentation for autonomous driving, aerial imagery registration, robot vision, tumor detection, and skin lesion segmentation as well as skin melanoma classification. The content of this book has been organized such that each chapter can be read independently from the others. The book is a valuable companion for researchers, for postgraduate and possibly senior undergraduate students who are taking an advanced course in related topics, and for those who are interested in deep learning with applications in computer vision, image processing, and pattern recognition.

Chapter 1 Accelerating the CNN Inference on FPGAs[Kamel Abdelouahab, Maxime Pelcat, and François Berry]Chapter 2 Object Detection with Convolutional Neural Networks[Kaidong Li, Wenchi Ma, Usman Sajid, Yuanwei Wu, andGuanghui Wang]Chapter 3 Efficient Convolutional Neural Networks for Fire Detection inSurveillance Applications[Khan Muhammad, Salman Khan, and Sung Wook Baik]Chapter 4 A Multi-biometric Face Recognition System Based onMultimodal Deep Learning Representations[Alaa S. Al-Waisy, Shumoos Al-Fahdawi, and Rami Qahwaji]Chapter 5 Deep LSTM-Based Sequence Learning Approaches for Actionand Activity Recognition[Amin Ullah, Khan Muhammad, Tanveer Hussain,Miyoung Lee, and Sung Wook Baik]Chapter 6 Deep Semantic Segmentation in Autonomous Driving[Hazem Rashed, Senthil Yogamani, Ahmad El-Sallab,Mahmoud Hassaballah, and Mohamed ElHelw]Chapter 7 Aerial Imagery Registration Using Deep Learning forUAV Geolocalization[Ahmed Nassar, and Mohamed ElHelw]Chapter 8 Applications of Deep Learning in Robot Vision[Javier Ruiz-del-Solar and Patricio Loncomilla]Chapter 9 Deep Convolutional Neural Networks: Foundations andApplications in Medical Imaging[Mahmoud Khaled Abd-Ellah, Ali Ismail Awad,Ashraf A. M. Khalaf, and Hesham F. A. Hamed]Chapter 10 Lossless Full-Resolution Deep Learning ConvolutionalNetworks for Skin Lesion Boundary Segmentation[Mohammed A. Al-masni, Mugahed A. Al-antari, and Tae-Seong Kim]Chapter 11 Skin Melanoma Classification Using Deep ConvolutionalNeural Networks[Khalid M. Hosny, Mohamed A. Kassem, and Mohamed M. Foaud]

Mahmoud Hassaballah received the Doctor of Engineering (D. Eng.) in Computer Science from Ehime University, Japan in 2011. He was a visiting scholar with the Department of Computer & Communication Science, Wakayama University, Japan and GREAH laboratory, Le Havre Normandie University, France. He is currently an Associate Professor of Computer Science at the Faculty of Computers and Information, South Valley University, Egypt. His research interests include feature extraction, object detection/recognition, artificial intelligence, biometrics, image processing, computer vision, machine learning, and data hiding.Ali Ismail Awad is currently an Associate Professor (Docent) with the Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Luleå, Sweden, where he also serves as a Coordinator of the Master Programme in Information Security. He is a Visiting Researcher with the University of Plymouth, United Kingdom. He is also an Associate Professor with the Electrical Engineering Department, Faculty of Engineering, Al-Azhar University at Qena, Qena, Egypt. His research interests include information security, Internet-of-Things security, image analysis with applications in biometrics and medical imaging, and network security.