Aplikasi Pengenalan Identitas Gambar Dengan Menggunakan Metode Backpropagation

Abstract

With today's technological developments, many types of identifier systems have been developed for the benefit of users of the technology. This recognition system is used for some objects or also on humans. Image recognition applications have great hopes for the future. Start with the introduction of sketch images or static photos in a certain format. Of course, this is supported by the development of science and technology in the fields of image processing, analysis, and image understanding. To recognize the identity of the image so far it is very rare, but in this study describes how to identify the identity of the image with human photos. The image (image) in question is an image or human image whose identity is not known. Currently, many manipulate images or photos with the same image. However, it is not known which one was manipulated and which one was genuine. Based on these problems, it is necessary to apply an identity recognition system so that it can be known which ones are manipulated and which ones are genuine, by applying the backpropagation method. According to previous research entitled facial recognition applications using the backpropagation algorithm and voila jones with the authors Sayuti Rahman, Emil Fitranhah, Andi Marwan Elhanafi stated that to be able to recognize a person's image with the backpropagation algorithm, one must go through several stages of training and testing stages. Image is a method found in artificial neural networks. Where the artificial neural network is an artificial representation of the human brain which always tries to simulate the learning process in the human brain. one of them is the backpropagation method, backpropagation is one of the artificial neural network models that has the ability to get a balance between the network's ability to recognize the patterns used during training and the network's ability to provide the correct response to input patterns that are similar (but not the same) with the same pattern. used during training.