NUMBER RECOGNITION USING CONVOLUTION NEURAL NETWORKS

Electronics and Communication engineering , Computer Science engineering

This project is aimed at clarifying the role of Number Recognition in accordance with today's maturing technologies. Most people effortlessly recognize those digits as 504192. That ease is deceptive. In each hemisphere of our brain, humans have a primary visual cortex, also known as V1, containing 140 million neurons, with tens of billions of connections between them. And yet human vision involves not just V1, but an entire series of visual cortices - V2, V3, V4, and V5 - doing progressively more complex image processing. Neural networks approach the problem in a different way. The idea is to take a large number of handwritten digits, known as training examples, and then develop a system which can learn from those training examples. In other words, the neural network uses the examples to automatically infer rules for recognizing handwritten digits. It tries to list and clarify the components that build number recognition and related technologies such as OCR (Optical Character Recognition) and Image Recognition using machine learning. Images of digits were taken from a variety of sources, normalized in size and centered. This makes it an excellent dataset for evaluating models, allowing the developer to focus on the machine learning with very little data cleaning or preparation required. Results are reported using prediction error, which is nothing more than the inverted classification accuracy. It also has diversified applications in multiple fields such as in automatic number plate recognition and has security applications. It can also be used in archaeological surveys where digitization of archaic handwritten characters needs to be stored in a database. This technique offers an offline machine learning based algorithm to do the same.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.