FPGA Implementation of Pattern Detection using Convolutional Neural Networks

The main objective of this research work is the detection of number of patterns from the input image. Artificial Neural Network (ANN) is used for solving may complex problems. Pattern recognition is generalized according to the type of learning procedure used to generate the output value. In image processing, pattern recognition has may real world applications such as identification and authentication. Eg: license plate recognition, finger print analysis, face detection/verification and voice-based authentication. For detecting number of patterns, at first input image and input pattern need to be converted into the text file through MATLAB and that text files will be given as input in the Verilog coding. So, based on the pattern, detection of number of times pattern repeated is calculated is shown and implementation of the same algorithm in Artix 7 FPGA board is shown.