马上注册,结交更多好友,享用更多功能,让你轻松玩转社区。
您需要 登录 才可以下载或查看,没有账号?注册
x
This book shows that traditional applications in computer vision can be solved through invoking deep learning. The applications addressed and described in the eleven different chapters have been selected in order to demonstrate the capabilities of deep learning algorithms to solve various issues in computer vision. The content of this book has been organized such that each chapter can be read independently of the others. Chapters of the book cover the following topics: accelerating the CNN inference on feld-programmable gate arrays, fre 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 classifcation. From the assortment of approaches and applications in the eleven chapters, the common thread is that deep learning for identifcation of CNN provides accuracy over traditional approaches. This accuracy is attributed to the fexibility of CNN and the availability of large data to enable identifcation through the deep learning strategy. Additionally, professionals who want to explore the advances in concepts and implementation of deep learning algorithms applied to computer vision may fnd in this book an excellent guide for such purpose. Finally, I hope that readers would fnd the presented chapters in the book interesting and inspiring to future research, from both theoretical and practical viewpoints, to spur further advances in discovering the secrets of deep learning.
|