Deep Learning for Computer Vision
Dipanjan Sarkar, Raghav Bali, Tushar Sharma · Apress eBooks · 2017
Deep Learning is not just a keyword abuzz in the industry and academics alike, it has thrown open a whole new field of possibilities. Deep Learning models are being employed in all sorts of use cases and domains, some of which we saw in the previous chapters. Artificial neural networks have tremendous potential to learn complex non-linear functions, patterns, and representations and their power is driving research in multiple fields, including computer vision, audio-visual analysis, chatbots and natural language understanding, to name a few. In this chapter, we touch on some of the advanced areas in the field of computer vision, which have recently come into prominence with the advent of Deep Learning. This includes real-world applications like image categorization and classification and they very popular concept of image artistic style transfer. Computer vision is all about the art and science of making machines understand high-level useful patterns and representations from images and video so that it would be able to make intelligent decisions similar to what a human would do upon observing its surroundings. Building on core concepts like convolutional neural networks and transfer learning, this chapter provides you with a glimpse into the forefront of Deep Learning research with several real-world case studies from computer vision.