神经网络matlab人脸检测,Face-recognition 基于BP神经网络的人脸识别MATLAB代码,构造、训练 并计算其 率。 AI-NN-PR 人工智能/ /深度学习 275万源代码下载- ...

文件名称: Face-recognition891ea1e7dab975064c6bfd22796603ae.gif下载  收藏√  [443d104427974206832dc4b12407db70.gif

 5  4  3  2  1 fb9128a58cbeaabbeb3718ed75079ccf.gif]

开发工具: Others

文件大小: 3733 KB

上传时间: 2015-06-15

下载次数: 38

提 供 者: 汪美美

详细说明:基于BP神经网络的人脸识别MATLAB代码,构造、训练BP神经网络并计算其识别率。-Face recognition based on BP neural network MATLAB code, structure, training BP neural network and computing its recognition rate.

文件列表(点击判断是否您需要的文件,如果是垃圾请在下面评价投诉):

基于BP神经网络的人脸识别MATLAB代码

..................................\Explanation.doc

..................................\FaceRecognitionByBPneuralnetwork.m

..................................\s1

..................................\s10

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s11

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s12

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s13

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s14

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s15

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s16

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s17

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

..................................\...\7.pgm

..................................\...\8.pgm

..................................\...\9.pgm

..................................\s18

..................................\...\1.pgm

..................................\...\10.pgm

..................................\...\2.pgm

..................................\...\3.pgm

..................................\...\4.pgm

..................................\...\5.pgm

..................................\...\6.pgm

输入关键字,在本站275万海量源码库中尽情搜索:

帮助

[SISO.zip] - LTE下行链路系统级仿真,本人运行过,无错误。代码中自带注释,运行的脚本文件名为commlteSISO

[FaceRecognition_CNN(olivettifaces).rar] - 智能图像/视频处理中,复杂背景环境(比如室外环境、机场、车站等)下,人脸识别的第一步是人脸的检测。它的精确度直接影响到后期识别的结果。不过,领域内的科学家们基本上很难有足够的精力和时间开发优化的C++代码,使其用于商业用途,而一般都是只在Matlab中进行模拟。

本文的目的是提供一个我开发的S

[CNN_face_detection-master.zip] - CVPR2015级联CNN进行人脸检测的MATLAB实现代码,按照流程实现,效果绝佳

[adboost-face-detection.rar] - Adaboost算法实现人脸检测,能够运行

[Face-recognition.zip] - 这是一个用BP神经网络实现的一个人脸识别程序,适合初学者的学习。

[BP-face-recognization.zip] - 基于BP神经网络的人脸识别算法的MALAB实现。采用了抽样-全样训练的方式。

阅读终点,创作起航,您可以撰写心得或摘录文章要点写篇博文。去创作
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
以下是基于PCA和BP神经网络人脸识别 MATLAB 代码: %% PCA特征提取 function [PC, V] = pca_face(images, num_components) % 输入:images为训练图像矩阵,每列为一个图像向量;num_components为PCA降维后保留的特征数。 % 输出:PC为降维后的主成分,每列为一个特征向量;V为每个特征向量对应的特征值。 [m, n] = size(images); images_mean = mean(images, 2); % 求训练图像集的平均图像 images_diff = images - repmat(images_mean, 1, n); % 将每幅图像向量减去平均图像向量 L = images_diff' * images_diff; % 计算协方差矩阵 [V, D] = eig(L); % 求特征值和特征向量 V = images_diff * V; % 将特征向量转换到原始空间 V = normc(V); % 归一化特征向量 PC = V(:, end:-1:end-num_components+1); % 选取前num_components个特征向量作为主成分 end %% BP神经网络训练 function net = train_bp(features, labels, hidden_layer_size) % 输入:features为训练集特征向量矩阵,每列为一个特征向量;labels为训练集标签向量,每列为一个标签; % hidden_layer_size为隐藏层神经元个数。 % 输出:net为训练好的BP神经网络模型。 num_features = size(features, 1); num_labels = size(labels, 1); net = feedforwardnet(hidden_layer_size); % 创建BP神经网络模型 net.trainParam.epochs = 1000; % 设置最大训练次数 net.trainParam.goal = 0.01; % 设置训练目标误差 net.trainParam.showWindow = false; % 不显示训练窗口 net = train(net, features, labels); % 训练BP神经网络 end %% BP神经网络测试 function labels_predict = test_bp(net, features_test) % 输入:net为训练好的BP神经网络模型;features_test为测试集特征向量矩阵,每列为一个特征向量。 % 输出:labels_predict为测试集标签向量,每列为一个标签。 labels_predict = sim(net, features_test); % BP神经网络预测 [~, labels_predict] = max(labels_predict); % 取最大值作为预测结果 end %% 人脸识别主程序 function face_recognition() % 加载训练图像和测试图像 train_dir = 'train_images'; test_dir = 'test_images'; train_images = load_images(train_dir); test_images = load_images(test_dir); % 提取训练图像的PCA特征 num_components = 50; [PC, ~] = pca_face(train_images, num_components); features_train = PC' * (train_images - mean(train_images, 2)); % 训练BP神经网络 hidden_layer_size = 20; labels_train = repmat(1:10, 6, 1); labels_train = labels_train(:); labels_train = full(ind2vec(labels_train)); net = train_bp(features_train, labels_train, hidden_layer_size); % 提取测试图像的PCA特征并进行BP神经网络预测 features_test = PC' * (test_images - mean(test_images, 2)); labels_predict = test_bp(net, features_test); labels_test = repmat(1:10, 4, 1); labels_test = labels_test(:); % 计算识别 accuracy = sum(labels_predict == labels_test) / length(labels_test); fprintf('Accuracy: %f%%\n', accuracy * 100); end %% 加载图像 function images = load_images(dir_path) % 输入:dir_path为图像文件夹路径。 % 输出:images为图像矩阵,每列为一个图像向量。 file_list = dir(dir_path); images = []; for i = 3:length(file_list) file_path = fullfile(dir_path, file_list(i).name); image = imread(file_path); image = imresize(image, [64, 64]); image = rgb2gray(image); image = im2double(image); images = [images, image(:)]; end end 运行 face_recognition 函数即可进行人脸识别

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值