ADVANCES IN DEEP LEARNING AND COMPUTER VISION

Computer Vision (CV) can be defined as “the hypothesis and innovation for building artificial frameworks that acquire data from pictures or multi-dimensional information.” A more straightforward clarification is that computer vision endeavors to take care of similar issues you can unravel with your own one of kind eyes. For instance, in case you're driving and you see a kid run into the street, your mind will rapidly translate the kid in the street in front of you, that it's perilous, and that you ought to quickly brake to abstain from hitting the kid. That is one of the issues self-driving vehicle engineers are presently striving to comprehend by the methods of computer vision. The method requires being competent of realizing object recognition, which can be subdivided into three varieties: object classification, identification, and detection. Object Classification is everywhere you have a little recently learned objects that you need to have the option to perceive in a picture. Characterizing a representation photograph as having individual's face in it is a model object classification, arranged that this photograph contains a face in it. Object Identification is the recognition of a specific instance of an object. For example, being able to identify that there are two faces in an image and that one is John and the other is Sarah is an example of object identification. Object Detection is the ability to identify that there’s an object in an image. This is typically used for things like automatic toll roads where you want to know when a new object has entered the frame so you can take a scan the license plate. Connecting this to the self-driving car problem, if you think to how the human brain would solve this problem, it would have to answer the same questions: In order for the situation to be dangerous, we would have to both identify that there is a child (object) in or approaching the road. Identify that the child in the road is something that we should avoid. You would also want to identify other objects, like trash, soccer ball, bike, etc., where you don’t necessarily need evasive action. In other words, Computer Vision is the field of study that seeks to develop techniques to help computers “see” and understand the content of digital images such as photographs and videos. The problem of computer vision appears simple because it is trivially solved by people, even very young children. Nevertheless, it largely remains an unsolved problem based both on the limited understanding of biological vision and because of the complexity of vision perception in a dynamic and nearly infinitely varying physical world.