广东东软学院本科毕业设计(论文)基于 Python 人脸识别系统 Face recognition system based on Python广东东软学院本科毕业设计(论文)摘要随着科技的不断发展,人工智能在人类生活的应用越来越普及,作为当前最受关注的生物特征识别的方法,人脸识别在考勤、边检、安防、运输等领域有着巨大应用前景,是人工智能与计算机视觉领域的研究热点之一。本文是基于 python 语言实现的人脸识别系统,利用 keras 搭建CNN 卷积神经网络构造一个 18 层网络结构的识别模型,实现人脸录入、图像处理、模型训练、识别人脸等功能。主要描述图像处理与模型搭建两个模块。图像处理包括图像的尺寸比例调整、数据归一化等知识,模型搭建包括模型建立、训练、评估。最终识别准确率达到 99.6% 。关键词:人脸识别 图像预处理 模型训练 CNN广东东软学院本科毕业设计(论文)AbstractWith the rapid development of science and technology, artificial intelligence is more and more popular in human life. As the currently most concerned method of biometrics recognition, face recognition has great application prospects in the fields of time and attendance, border inspection, security, transportation, etc. It is one of the research hotspots in the field of artificial intelligence and computer vision. This paper is a face recognition system based on python. It use keras to build a convolutional neural network to construct an 18-layer structure recognition model to realize functions such as face input, image processing, model training, and face recognition. It mainly describes two modules of image processing and model building. Image processing includes knowledge such as image size adjustment and data normalization, and model building includes model establishment, training, and evaluation. The final recognition accuracy reached 99.6%.Key words: Face recognition Image preprocessing Model training CNN目广东东软学院本科毕业设计(论文)录第一章 课题背景.................................................