LVQ神经网络之人脸朝向识别(源程序+图片数据集)

共105个文件

bmp：100个

m：4个

db：1个

神经网络

5星 · 超过95%的资源需积分: 50 148 浏览量 2018-01-14 20:34:49 上传评论 12 收藏 23.32MB ZIP 举报

资源推荐

资源详情

资源评论

收起资源包目录

LVQ神经网络之人脸朝向识别(源程序+图片数据集) （105个子文件）

1_3.bmp 338KB

11_1.bmp 338KB

18_3.bmp 338KB

16_5.bmp 338KB

12_4.bmp 338KB

2_3.bmp 338KB

13_2.bmp 338KB

13_5.bmp 338KB

2_2.bmp 338KB

14_2.bmp 338KB

15_1.bmp 338KB

9_3.bmp 338KB

16_3.bmp 338KB

1_2.bmp 338KB

10_5.bmp 338KB

12_1.bmp 338KB

8_1.bmp 338KB

12_5.bmp 338KB

5_3.bmp 338KB

14_4.bmp 338KB

14_5.bmp 338KB

15_2.bmp 338KB

17_1.bmp 338KB

7_3.bmp 338KB

19_2.bmp 338KB

18_2.bmp 338KB

18_4.bmp 338KB

17_4.bmp 338KB

15_4.bmp 338KB

8_4.bmp 338KB

2_1.bmp 338KB

7_4.bmp 338KB

7_1.bmp 338KB

20_5.bmp 338KB

10_3.bmp 338KB

20_2.bmp 338KB

20_1.bmp 338KB

10_1.bmp 338KB

7_5.bmp 338KB

10_4.bmp 338KB

4_2.bmp 338KB

18_5.bmp 338KB

19_3.bmp 338KB

6_4.bmp 338KB

8_5.bmp 338KB

4_5.bmp 338KB

5_4.bmp 338KB

7_2.bmp 338KB

2_5.bmp 338KB

1_4.bmp 338KB

14_3.bmp 338KB

16_1.bmp 338KB

11_4.bmp 338KB

13_4.bmp 338KB

9_1.bmp 338KB

5_1.bmp 338KB

6_5.bmp 338KB

6_2.bmp 338KB

16_4.bmp 338KB

19_1.bmp 338KB

4_1.bmp 338KB

18_1.bmp 338KB

14_1.bmp 338KB

20_4.bmp 338KB

19_4.bmp 338KB

1_5.bmp 338KB

15_5.bmp 338KB

8_3.bmp 338KB

3_1.bmp 338KB

8_2.bmp 338KB

19_5.bmp 338KB

4_3.bmp 338KB

9_2.bmp 338KB

5_2.bmp 338KB

2_4.bmp 338KB

16_2.bmp 338KB

3_5.bmp 338KB

3_4.bmp 338KB

11_3.bmp 338KB

11_5.bmp 338KB

12_3.bmp 338KB

6_3.bmp 338KB

1_1.bmp 338KB

20_3.bmp 338KB

10_2.bmp 338KB

17_3.bmp 338KB

5_5.bmp 338KB

17_5.bmp 338KB

3_2.bmp 338KB

9_5.bmp 338KB

17_2.bmp 338KB

12_2.bmp 338KB

4_4.bmp 338KB

6_1.bmp 338KB

13_1.bmp 338KB

3_3.bmp 338KB

9_4.bmp 338KB

13_3.bmp 338KB

11_2.bmp 338KB

15_3.bmp 338KB

共 105 条

%% LVQ神经网络的预测——人脸识别 % % <html> % <table border="0" width="600px" id="table1"> <tr> <td>该案例作者申明：</td> </tr> <tr><td>1：本人长期驻扎在此<a target="_blank" href="http://www.ilovematlab.cn/forum-158-1.html">板块</a>里，对该案例提问，做到有问必答。本套书籍官方网站为：<a href="http://video.ourmatlab.com">video.ourmatlab.com</a></td></tr><tr> <td>2：点此<a href="http://union.dangdang.com/transfer/transfer.aspx?from=P-284318&backurl=http://www.dangdang.com/">从当当预定本书</a>：<a href="http://union.dangdang.com/transfer/transfer.aspx?from=P-284318&backurl=http://www.dangdang.com/">《Matlab神经网络30个案例分析》</a>。</td></tr><tr> <td>3：此案例有配套的教学视频，视频下载方式<a href="http://video.ourmatlab.com/vbuy.html">video.ourmatlab.com/vbuy.html</a>。 </td> </tr> <tr> <td> 4：此案例为原创案例，转载请注明出处（《Matlab神经网络30个案例分析》）。</td> </tr> <tr> <td> 5：若此案例碰巧与您的研究有关联，我们欢迎您提意见，要求等，我们考虑后可以加在案例里。</td> </tr> </table> % </html> %% 清除环境变量 clear all clc %% 人脸特征向量提取 % 人数 M = 20; % 人脸朝向类别数 N = 5; % 特征向量提取 pixel_value = feature_extraction(M,N); %% 训练集/测试集产生 % 产生图像序号的随机序列 rand_label = randperm(M*N); % 人脸朝向标号 direction_label = repmat(1:N,1,M); % 训练集 train_label = rand_label(1:80); P_train = pixel_value(train_label,:)'; Tc_train = direction_label(train_label); T_train = ind2vec(Tc_train); % 测试集 test_label = rand_label(81:end); P_test = pixel_value(test_label,:)'; Tc_test = direction_label(test_label); %% K-fold交叉验证确定最佳神经元个数 k_fold = 10; Indices = crossvalind('Kfold',size(P_train,2),k_fold); error_min = 10e10; best_number = 1; best_input = []; best_output = []; best_train_set_index = []; best_validation_set_index = []; h = waitbar(0,'正在寻找最佳神经元个数.....'); for i = 1:k_fold % 验证集标号 validation_set_index = (Indices == i); % 训练集标号 train_set_index = ~validation_set_index; % 验证集 validation_set_input = P_train(:,validation_set_index); validation_set_output = T_train(:,validation_set_index); % 训练集 train_set_input = P_train(:,train_set_index); train_set_output = T_train(:,train_set_index); for number = 10:100 for j = 1:5 rate{j} = length(find(Tc_train(:,train_set_index) == j))/length(find(train_set_index == 1)); end net = newlvq(minmax(train_set_input),number,cell2mat(rate)); % 设置网络参数 net.trainParam.epochs = 100; net.trainParam.show = 10; net.trainParam.lr = 0.1; net.trainParam.goal = 0.001; % 训练网络 net = train(net,train_set_input,train_set_output); waitbar(((i-1)*21 + number)/219,h); %% 仿真测试 T_sim = sim(net,validation_set_input); Tc_sim = vec2ind(T_sim); error = length(find(Tc_sim ~= Tc_train(:,validation_set_index))); if error < error_min error_min = error; best_number = number; best_input = train_set_input; best_output = train_set_output; best_train_set_index = train_set_index; best_validation_set_index = validation_set_index; end end end disp(['经过交叉验证，得到的最佳神经元个数为：' num2str(best_number)]); close(h); %% 创建LVQ网络 for i = 1:5 rate{i} = length(find(Tc_train(:,best_train_set_index) == i))/length(find(best_train_set_index == 1)); end net = newlvq(minmax(best_input),best_number,cell2mat(rate),0.01); % 设置训练参数 net.trainParam.epochs = 100; net.trainParam.goal = 0.001; net.trainParam.lr = 0.1; %% 训练网络 net = train(net,best_input,best_output); %% 人脸识别测试 T_sim = sim(net,P_test); Tc_sim = vec2ind(T_sim); result = [Tc_test;Tc_sim] %% 结果显示 % 训练集人脸标号 strain_label = sort(train_label(best_train_set_index)); htrain_label = ceil(strain_label/N); % 训练集人脸朝向标号 dtrain_label = strain_label - floor(strain_label/N)*N; dtrain_label(dtrain_label == 0) = N; % 显示训练集图像序号 disp('训练集图像为：' ); for i = 1:length(find(best_train_set_index == 1)) str_train = [num2str(htrain_label(i)) '_'... num2str(dtrain_label(i)) ' ']; fprintf('%s',str_train) if mod(i,5) == 0 fprintf('\n'); end end % 验证集人脸标号 svalidation_label = sort(train_label(best_validation_set_index)); hvalidation_label = ceil(svalidation_label/N); % 验证集人脸朝向标号 dvalidation_label = svalidation_label - floor(svalidation_label/N)*N; dvalidation_label(dvalidation_label == 0) = N; % 显示验证集图像序号 fprintf('\n'); disp('验证集图像为：' ); for i = 1:length(find(best_validation_set_index == 1)) str_validation = [num2str(hvalidation_label(i)) '_'... num2str(dvalidation_label(i)) ' ']; fprintf('%s',str_validation) if mod(i,5) == 0 fprintf('\n'); end end % 测试集人脸标号 stest_label = sort(test_label); htest_label = ceil(stest_label/N); % 测试集人脸朝向标号 dtest_label = stest_label - floor(stest_label/N)*N; dtest_label(dtest_label == 0) = N; % 显示测试集图像序号 fprintf('\n'); disp('测试集图像为：'); for i = 1:20 str_test = [num2str(htest_label(i)) '_'... num2str(dtest_label(i)) ' ']; fprintf('%s',str_test) if mod(i,5) == 0 fprintf('\n'); end end % 显示识别出错图像 error = Tc_sim - Tc_test; location = {'左方' '左前方' '前方' '右前方' '右方'}; for i = 1:length(error) if error(i) ~= 0 % 识别出错图像人脸标号 herror_label = ceil(test_label(i)/N); % 识别出错图像人脸朝向标号 derror_label = test_label(i) - floor(test_label(i)/N)*N; derror_label(derror_label == 0) = N; % 图像原始朝向 standard = location{Tc_test(i)}; % 图像识别结果朝向 identify = location{Tc_sim(i)}; str_err = strcat(['图像' num2str(herror_label) '_'... num2str(derror_label) '识别出错.']); disp([str_err '(正确结果：朝向' standard... '；识别结果：朝向' identify ')']); end end % 显示识别率 disp(['识别率为：' num2str(length(find(error == 0))/20*100) '%']); %web browser http://www.matlabsky.com/thread-11193-1-1.html %% % <html> % <table width="656" align="left" > <tr><td align="center"><a href="http://video.ourmatlab.com/">Matlab神经网络30个案例分析</a>相关论坛：《Matlab神经网络30个案例分析》官方网站：<a href="http://video.ourmatlab.com">video.ourmatlab.com</a>Matlab技术论坛：<a href="http://www.matlabsky.com">www.matlabsky.com</a>Matlab函数百科：<a href="http://www.mfun.la">www.mfun.la</a>Matlab中文论坛：<a href="http://www.ilovematlab.com">www.ilovematlab.com</a></td> </tr></table> % </html>

评论收藏

内容反馈