项目代码matlab

 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 % 可调参数

 test_path='';
 neighbour_pixels_affect=;
 target_digit=;
 % forestTrain()参数设置
 %   .M          - [] number of trees to train
 %   .H          - [max(hs)] number of classes
 %   .N1         - [*N/M] number of data points for training each tree
 %   .F1         - [sqrt(F)] number features to sample for each node split
 %   .split      - ['gini'] options include 'gini', 'entropy' and 'twoing'
 %   .minCount   - [] minimum number of data points to allow split
 %   .minChild   - [] minimum number of data points allowed at child nodes
 %   .maxDepth   - [] maximum depth of tree
 %   .dWts       - [] weights used for sampling and weighing each data point
 %   .fWts       - [] weights used for sampling features
 %   .discretize - [] optional function mapping structured to class labels
 %                    format: [hsClass,hBest] = discretize(hsStructured,H);
 varargin.M=;
 %varargin.H=;

 % forestApply()的输入设置
 %  data     - [NxF] N length F feature vectors
 %  forest   - learned forest classification model
 %  maxDepth - [] maximum depth of tree
 %  minCount - [] minimum number of data points to allow split
 %  best     - [] if true use single best prediction per tree

 %  forestApply()输出结果及对比的阀值
 %  hs       - [Nx1] predicted output labels
 %  ps       - [NxH] predicted output label probabilities
 ps_val_more_than0_3=0.2;

 %滑窗检测,窗口尺度，步长
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

 data=[];
 label=[];
 temp_r1=;
 temp_c1=;

 for i_digit=:
 %     if(i_digit==target_digit)                                %%%%%%%%%%%%%%%%%%%%%%
 %         this_image_label=;
 %     end
     %数字转字符
     str=num2str(i);                                          %%数据是不是不平衡
     path_temp=strcat('C:\Users\cong\Desktop\研一实战\项目\图像中时间数字识别\trainingSample\num',str,'\');
     file=dir(path_temp);
     for i=:length(file)
         path= strcat(path_temp,file(i).name);

         %%%%%%%%%%%%%%%%%%%%%%%%%%
         % 加载图片
         %%%%%%%%%%%%%%%%%%%%%%%%%%
         I=imread(path);
         %I=imread('E:/WeChat.jpg');
         %%%%%%%%%%%%%%%%%%%%%%%%%%
         % 提取channel features
         %%%%%%%%%%%%%%%%%%%%%%%%%%
         [all_channel_difference_features,temp_r1,temp_c1]=extract_features(I,);
         data=[data,all_channel_difference_features];
         label=[label;i_digit+];

 %         if(i> && this_image_label~=)               %%这里只取了前100帧，实际上可以随意抽取一百张
 %             break;
 %         end
     end % for i=:length(file)

 end  % for i_digit=:

 %%%%%%%%%%%%%%%%%%%%%%%%%%
 % 扔进分类器中，训练
 %%%%%%%%%%%%%%%%%%%%%%%%%%

 forest = forestTrain( data, label, varargin );

 %%%%%%%%%%%%%%%%%%%%%%%%%%
 % 检测，测试
 test_image=imread(test_path);
 %滑窗检测,窗口尺度，步长
 [test_r,test_c,test_z]=size(test_image);
 for i_test=:test_r
     %model

     %resize
     test_image=imresize(model,temp_r1,temp_c1);
     test_data=extract_features(test_image,);
     [hs,ps] = forestApply( test_data, forest, [], [], [] );%尺度问题
     if(ps>ps_val_more_than0_3)
       %画框

     end
 end

 %%%%%%%%%%%%%%%%%%%%%%%%%%

 function [ all_channel_difference_features,,r1,c1 ] = extract_features( I,shrink_or_not )
 %EXTRACT_FEATURES 此处显示有关此函数的摘要
 %   此处显示详细说明
     %%%%%%%%%%%%%%%%%%%%%%%%%%
     % 提取channel features
     %%%%%%%%%%%%%%%%%%%%%%%%%%
     % 参数设置
     if(shrink_or_not==)
         pChns.shrink=;
     end

     pChns.pColor.enabled=;
     pChns.pColor.smooth=;
     pChns.pColor.colorSpace='luv';

     pChns.pGradMag.enabled=;
     pChns.pGradMag.colorChn=;
     pChns.pGradMag.normRad=;
     pChns.pGradMag.normConst=.;
     pChns.pGradMag.full=;

     pChns.pGradHist.enabled=;
     %pChns.pGradHist.binSize=
     pChns.pGradHist.nOrients=;
     pChns.pGradHist.softBin=;
     pChns.pGradHist.useHog=;
     pChns.pGradHist.clipHog=.;

     %pChns.pCustom.**

     %pChns.complete=

     % 提取channel features
     chns = chnsCompute( I, pChns );
     % 将各个通道放在矩阵中
     [r1,c1,ch1]=size(chns.data{});
     [r2,c2,ch2]=size(chns.data{});
     [r3,c3,ch3]=size(chns.data{});
     ch=ch1+ch2+ch3;
     all_channel=zeros(r1,c1,ch);
     all_channel(:,:,:ch1)=chns.data{};
     all_channel(:,:,ch1+:ch1+ch2)=chns.data{};
     all_channel(:,:,ch1+ch2+:ch)=chns.data{};
     %%%%%%%%%%%%%%%%%%%%%%%%%%
     % pooling
     %%%%%%%%%%%%%%%%%%%%%%%%%%
     for ii=:ch
             %向下采样
             all_pooling(:,:,ii)=imresize(all_channel(:,:,ii),0.2);
     end

     %%%%%%%%%%%%%%%%%%%%%%%%%%
     % 再次做相减特征
     %%%%%%%%%%%%%%%%%%%%%%%%%%
     all_channel_difference_features=[];
     for ij=:ch
         temp=difference_features( all_pooling(:,:,ij),neighbour_pixels_affect );
         all_channel_difference_features = [all_channel_difference_features;temp];
     end

 end

 function [ one_channel_difference_features ] = difference_features( one_channel_features,neighbour_pixels_affect )
 %DIFFERENCE_FEATURES 计算邻域内个特征之间两两相减
 %input:
 % one_channel_features
 %neighbour_pixels_affect
 %output:
 %one_channel_difference_features

 [r,c]=size(one_channel_features);

 one_channel_difference_features=[];
 for i=:r-neighbour_pixels_affect+
     for j=:c-neighbour_pixels_affect+
         local_features=one_channel_features(i:i+neighbour_pixels_affect-,j:j+neighbour_pixels_affect-);
         temp=local_feature_compute(local_features);
         one_channel_difference_features=[one_channel_difference_features;temp];%特征拼接
     end
 end
 end

 function [ local_differece_feature ]=local_feature_compute( local_features )
 [r,c]=size(local_features);
 result_mat=local_features-local_features(,).*ones(r,c);
 result_vector=reshape(result_mat,r*c,);
 local_differece_feature=result_vector(:r*c,);%把第一个特征去掉，自己减自己没有任何特征信息可言
 end

%{
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% 可调参数

test_path='C:\Users\cong\Desktop\研一实战\项目\图像中时间数字识别\OCR\one\3.jpg';
neighbour_pixels_affect=;
target_digit=;
% forestTrain()参数设置
%   .M          - [] number of trees to train
%   .H          - [max(hs)] number of classes
%   .N1         - [*N/M] number of data points for training each tree
%   .F1         - [sqrt(F)] number features to sample for each node split
%   .split      - ['gini'] options include 'gini', 'entropy' and 'twoing'
%   .minCount   - [] minimum number of data points to allow split
%   .minChild   - [] minimum number of data points allowed at child nodes
%   .maxDepth   - [] maximum depth of tree
%   .dWts       - [] weights used for sampling and weighing each data point
%   .fWts       - [] weights used for sampling features
%   .discretize - [] optional function mapping structured to class labels
%                    format: [hsClass,hBest] = discretize(hsStructured,H);
varargin.M=;
%varargin.H=;

% forestApply()的输入设置
%  data     - [NxF] N length F feature vectors
%  forest   - learned forest classification model
%  maxDepth - [] maximum depth of tree
%  minCount - [] minimum number of data points to allow split
%  best     - [] if true use single best prediction per tree

%  forestApply()输出结果及对比的阀值
%  hs       - [Nx1] predicted output labels
%  ps       - [NxH] predicted output label probabilities
ps_val_more_than0_3=0.2;

%滑窗检测,窗口尺度，步长
win_h=;
win_w=;
step=;
disp('参数配置成功...');
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
disp('正在读入图片及特征提取...');
%读入图片及特征提取
data=[];
label=[];
temp_r1=;
temp_c1=;

for i_digit=:
%     if(i_digit==target_digit)                                %%%%%%%%%%%%%%%%%%%%%%
%         this_image_label=;
%     end
    %数字转字符
    str=num2str(i_digit);                                          %%数据是不是不平衡
    path_temp=strcat('C:\Users\cong\Desktop\研一实战\项目\图像中时间数字识别\trainingSample\num',str,'\');
    file=dir(path_temp);
    for i=:length(file)
        path= strcat(path_temp,file(i).name);

        %%%%%%%%%%%%%%%%%%%%%%%%%%
        % 加载图片
        %%%%%%%%%%%%%%%%%%%%%%%%%%
        I=imread(path);
        %I=imread('E:/WeChat.jpg');
        %%%%%%%%%%%%%%%%%%%%%%%%%%
        % 提取channel features
        %%%%%%%%%%%%%%%%%%%%%%%%%%
        [all_channel_difference_features,temp_r1,temp_c1]=extract_features(I,neighbour_pixels_affect,);
        data=[data,all_channel_difference_features];
        label=[label;i_digit+];
        if(rem(i,)==)
            disp('...');
        end
    end % for i=:length(file)
    disp('数字')
    i_digit
    disp('的特征提取完毕...');
end  % for i_digit=:
disp('读入图片及特征提取完毕...');
%%%%%%%%%%%%%%%%%%%%%%%%%%
% 扔进分类器中，训练
%%%%%%%%%%%%%%%%%%%%%%%%%%
data=data';
disp('正在训练，请稍等...');
forest = forestTrain( data, label, varargin );
disp('训练完毕...');
%}
%%%%%%%%%%%%%%%%%%%%%%%%%%
% 检测，测试
test_label=[];
test_label_p=[];
win_h=;
win_w=;
windSize = [,];
step=;
ps_val_more_than0_3=0.07;

disp('正在检测...');
test_image=imread(test_path);
%滑窗检测,窗口尺度，步长
[test_r,test_c,test_z]=size(test_image);
figure;
imshow(test_image);
hold on

for i_test=:step:test_r-win_h+
    for j_test=:step:test_c-win_w+
        %model
        model=test_image(i_test:i_test+win_h-,j_test:j_test+win_w-,:);
        %resize
        test_image_rs=imresize(model,[temp_r1 temp_c1]);
        test_data=extract_features(test_image_rs,neighbour_pixels_affect,);
        test_data=test_data';
        test_data=single(test_data);

        [hs,ps] = forestApply( test_data, forest,,,);%尺度问题
         test_label=[test_label,hs];
         test_label_p=[test_label_p,ps(hs)];
        if(ps>ps_val_more_than0_3)
          %画框
          %draw_rect(test_image,);
          i_test
          j_test
          rectangle('Position',[i_test,j_test,,],'LineWidth',,'EdgeColor','r');
          %pointAll = [i_test,j_test];
          %[state,results]=draw_rect(test_image,pointAll,windSize);
          hold on
        end 

    end
    hold on
end
disp('检测完毕！恭喜恭喜！')
%%%%%%%%%%%%%%%%%%%%%%%%%%