Название: Handbook of Research on Computer Vision and Image Processing in the Deep Learning Era
Автор: A. Srinivasan
Издательство: IGI Global
Год: 2023
Страниц: 400
Язык: английский
Формат: epub (true)
Размер: 39.2 MB

This book explores traditional and new areas of the computer vision, Machine Learning and Deep Learning combined to solve a range of problems with the objective to integrate the knowledge of the growing international community of researchers working on the application of Machine Learning and Deep Learning Methods in Vision and Robotics.

Image processing is one of the rapidly developing technologies that is spawning important research fields in Engineering discipline. Image Processing refers to the application of algorithms to images meant to improve the quality of the image or to alter it for a different visual effect. It plays a very important role to prepare images for Computer Vision models, such as applying segmentation or labelling known objects. Computer vision and image processing are inseparably linked. A computer vision system receives an image as input and produces task-specific data, such as item labels and coordinates. Computer vision systems rarely use unprocessed image data obtained directly from hardware such as cameras or sensors. Instead, they employ photos that have undergone various forms of image processing.

Today, Computer Vision applications have achieved tremendous success which includes applications likes image classification, Defect inspection, autonomous driving, Robotics, Text classification, facial recognition etc., However, for these models to work, the images need to first be labelled, segmented, or to have gone through other pre-processing steps taken with the help of image processing algorithms.

Deep Learning plays a prominent role in a variety of computer vision problems, such as object detection motion tracking action recognition human pose estimation and semantic segmentation etc., The reason behind it is that Deep learning is a rich family of methods, encompassing neural networks, hierarchical probabilistic models, and a variety of unsupervised and supervised feature learning algorithms. The recent surge of interest in deep learning methods is due to the fact that they have been shown to outperform previous state-of-the-art techniques in several tasks like visual, aural, medical, social, and sensorial ability. Thus, the chapters of the book focusses on role of Deep Learning technologies in variety of application with higher emphasis/priority for image processing and computer vision problems as the world is running behind smarter and autonomous environment.