码迷,mamicode.com
首页 > 其他好文 > 详细

京东金融大数据竞赛猪脸识别(2)- 图像特征提取之一

时间:2018-03-13 14:00:33      阅读:218      评论:0      收藏:0      [点我收藏+]

标签:图像特征提取   文件夹遍历   

图像识别进入深度学习时代后,特征提取这个词的使用频率明显下降了。因为深度网络已经完成了从图像输入到分类结果输出的全过程,似乎不需要再关心特征的好坏和特征提取对于识别结果的影响。不过,不管从算法研究还是工程实现角度看,将特征提取独立出来应该更有利。这样我们可以对各种特征提取方法和各种识别算法进行组合,找出效果最好的方案。
我们先考虑非神经网络提取的特征,在深度神经网络大热以前,局部特征、空间金字塔、稀疏编码的结合合应该是达到最高识别准确率的方案。它在一些应用场合能够以更低的代价带来不次于深度网络的识别效果,可应用于实现方案。这里的代码是在工具箱reco_toolbox基础上修改的:

%exam1.m extract features from every image
clc,close all, clear all,drawnow
database_name        = {‘JDTest‘};
database_ext         = {‘jpg‘ , ‘jpg‘ , ‘png‘};
descriptors_name     = {‘mlhoee_spyr‘ , ‘mlhmslsd_spyr‘ , ‘mlhmslbp_spyr‘ , ‘mlhmsldp_spyr‘};

choice_database      = [1]; 
choice_descriptors   = [3]; %mlhoee_spyr=1/mlhmslsd_spyr=2/mlhmslbp_spyr=3/mlhmsldp_spyr=4
do_extract_feature   = 1;   %no=0/yes=1

data_name            = database_name{choice_database(1)};
im_ext               = database_ext{choice_database(1)};
rootbase_dir         = pwd;
images_dir           = fullfile(pwd , ‘images‘ , data_name);
core_dir             = fullfile(pwd , ‘core‘);
feat_dir             = fullfile(pwd , ‘features‘);
des_dir              = fullfile(pwd , ‘descriptors‘);
addpath(core_dir);
%执行描述符配置脚本文件
eval([data_name , ‘_config_descriptors‘]);
descriptors_param    = cell(1 , length(descriptors_name));
descriptors_param{1} = mlhoee;
descriptors_param{2} = mlhmslsd;
descriptors_param{3} = mlhmslbp;
descriptors_param{4} = mlhmsldp;

descriptors_size     = cell(1 , length(descriptors_name));
descriptors_size{1}  = descriptors_param{1}{1}.size;
descriptors_size{2}  = descriptors_param{2}{1}.size;
descriptors_size{3}  = descriptors_param{3}{1}.size;
descriptors_size{4}  = descriptors_param{4}{1}.size;
nb_descriptors       = length(choice_descriptors);

if(do_extract_feature)    
    for j  = 1 : nb_descriptors
        current_path  = fullfile(pwd , ‘images‘ , data_name );
        current_dir     = dir(fullfile(current_path , [‘*.‘ , im_ext]));    
        m                    = length(current_dir);
        current_descriptor = choice_descriptors(j);
        current_size           = descriptors_size{current_descriptor};
        base_descriptor     = descriptors_name{current_descriptor};           
        eval([‘descriptors   = @‘ base_descriptor ‘;‘]);
        %初始化特征存储变量
        X                            = zeros(descriptors_size{current_descriptor} , m);      
        for i = 1 : m
            I                  = imread(fullfile(current_path , current_dir(i).name));
            [h,w]           = size(I);
                        %将图像缩小一半
            J                 = imresize(I,[h/2,w/2]);
            X(:,i)            = descriptors(J , descriptors_param{current_descriptor}{:});                       
            fprintf(‘descriptor = %s, image = %s (%d/%d)\n‘ , base_descriptor ,  current_dir(i).name , i , m)
            drawnow
        end
                %将图像特征存储为文件
        save(fullfile(feat_dir , [data_name , ‘_‘ , base_descriptor]) , ‘X‘  )
        clear X ;        
    end
    fprintf(‘Feature extraction  finished!‘);
end

运行该程序就可以对image文件夹下JDTest文件夹内各子文件夹内的图像提取特征并存为文件。

%exam2.m extract bag-of-features for every image
clc,close all, clear ,drawnow
database_name        = {‘JDPig‘ };
database_ext         = {‘jpg‘ , ‘jpg‘ , ‘png‘};
descriptors_name     = {‘denseSIFT‘ , ‘denseCOLOR‘ , ‘densePATCH‘ , ‘denseMBLBP‘ , ‘denseMBLDP‘};

encoding_name        = {‘yael_kmeans‘ , ‘mexTrainDL‘};
features_name          = {‘mlhbow_spyr‘ , ‘dl_spyr‘ , ‘mlhlcc_spyr‘};
choice_database      = [1]; 
choice_descriptors   = [1]; 
choice_encoding      = [2]; %Kmeans=1/Sparse Learning =2
choice_feature          = [2]; %SP-Histogram = 1/Sparse Pooling = 2/LCC = 3

do_extract_patches     = 1;   %no=0/yes=1
do_encoding                = 1;   %no=0/yes=1
do_compute_features  = 1;   %no=0/yes=1
dicoshared                   = 0;   %no=0/yes=1

data_name                   = database_name{choice_database(1)};
im_ext                           = database_ext{choice_database(1)};

rootbase_dir         = pwd;
images_dir            = fullfile(pwd , ‘images‘ , data_name);
core_dir                 = fullfile(pwd , ‘core‘);
feat_dir                  = fullfile(pwd , ‘features‘);
dico_dir                  = fullfile(pwd , ‘dico‘);
des_dir                   = fullfile(pwd , ‘descriptors‘);
addpath(core_dir)
dirim                       = dir(images_dir);
nb_topic                 = length(dirim) - 2;
classe_name          = cellstr(char(dirim(3:nb_topic+2).name))‘;

%执行相关配置文件
eval([data_name , ‘_config_descriptors‘]);
eval([data_name , ‘_config_encoding‘]);
eval([data_name , ‘_config_features‘]);

nbimagespertopic     = zeros(1 , nb_topic);
for i = 1:nb_topic
    dir_name            = dir(fullfile(pwd  , ‘images‘ , data_name , dirim(i+2).name , [‘*.‘ , im_ext]));
    nbimagespertopic(i) = length(dir_name);
end
N                    = sum(nbimagespertopic);

descriptors_param    = cell(1 , length(descriptors_name));
descriptors_param{1} = sift;
descriptors_param{2} = color;
descriptors_param{3} = patch;
descriptors_param{4} = mblbp;
descriptors_param{5} = mbldp;

descriptors_size     = cell(1 , length(descriptors_name));
descriptors_size{1}  = descriptors_param{1}{1}.size;
descriptors_size{2}  = descriptors_param{2}{1}.size;
descriptors_size{3}  = descriptors_param{3}{1}.size;
descriptors_size{4}  = descriptors_param{4}{1}.size;
descriptors_size{5}  = descriptors_param{5}{1}.size;

encoding_param       = cell(1 , length(encoding_name));
encoding_param{1}    = yael;
encoding_param{2}    = spams;

features_param        = cell(1 , length(features_name));
features_param{1}    = mlhbow_feat;
features_param{2}    = dl_feat;
features_param{3}    = mlhlcc_feat;

nb_descriptors       = length(choice_descriptors);
nb_encoding          = length(choice_encoding);
nb_features          = length(choice_encoding);

current_descriptor = choice_descriptors;
base_descriptor    = descriptors_name{current_descriptor};
featfile = fullfile(feat_dir , [data_name , ‘_‘ , base_descriptor]);
featfile = [featfile,‘.mat‘];
if (~exist(featfile))
    do_extract_patches = 1;
else
    do_extract_patches = 0;
end
if(do_extract_patches)
    for j  = 1 : nb_descriptors
        current_descriptor  = choice_descriptors(j);
        current_size           = descriptors_size{current_descriptor};
        base_descriptor     = descriptors_name{current_descriptor};
        nbpatches              = descriptors_param{current_descriptor}{1}.nbpatches;
        nbpatchetotal         = nbpatches*N;
        standardize            = descriptors_param{current_descriptor}{1}.standardize;
        whithning               = descriptors_param{current_descriptor}{1}.whithning;
        patchdim                = descriptors_param{current_descriptor}{1}.patchdim;

        eval([‘descriptors = @‘ base_descriptor ‘;‘]);
        fprintf(‘descriptor = %s \n\n‘ , base_descriptor)
        drawnow

        X                  = zeros(descriptors_size{current_descriptor} , N , ‘single‘);
        Z                  = zeros(nbpatches*6 , N , ‘single‘);
        S                  = zeros(2 , N , ‘uint16‘);
        Y                  = zeros(nbpatches , N , ‘single‘);
        y                  = zeros(1 , N );
        co                 = 1;

        %对每类图像进行处理
        for t = 1 : nb_topic            
            current_path  = fullfile(pwd , ‘images‘ , data_name , dirim(t+2).name);
            current_dir   = dir(fullfile(current_path , [‘*.‘ , im_ext]));
            current_topic = char(classe_name(t));         
            for i = 1 : length(current_dir)                
                I                   = imread(fullfile(current_path , current_dir(i).name));                
                fprintf(‘descriptor = %s, topic = %s (%d/%d), image = %s (%d/%d)\n‘ , base_descriptor , current_topic, t , nb_topic , current_dir(i).name , i , nbimagespertopic(t))
                drawnow                
                [des , fea]         = descriptors(I , descriptors_param{current_descriptor}{:});                
                X(: , co)            = reshape(single(des) , current_size , 1);
                Z(: , co)            = reshape(single(fea(1:6,:)) , nbpatches*6 , 1);
                Y(: , co)            = t*ones(nbpatches , 1);
                y(co)                 = t;
                co                     = co + 1;
            end
        end         
        if(dicoshared)
            Z(3:4 , :)                                                                   = 1;
            descriptors_param{current_descriptor}{1}.scale     = 1;
            descriptors_param{current_descriptor}{1}.nbscale  = 1;
            descriptors_param{current_descriptor}{1}.dimcolor = 1;
            features_param{current_features}.scale                  = 1;
        end

        X                           = reshape(X , patchdim , nbpatchetotal);
        Z                           = reshape(Z , [6 , nbpatchetotal]);
        Y                           = reshape(Y , 1 , nbpatchetotal);

        if(standardize)
            fprintf(‘Standardize patches\n‘ )
            drawnow
            mX            = mean(X , 2);
            stdX          = std(X , 0 , 2);
            stdX(stdX==0) = 1;
            X             = (X - mX(: , ones(1 , size(X , 2))))./stdX(: , ones(1 , size(X , 2)));            
            fprintf(‘End Standardize\n‘ )
            drawnow
        end
        if(whithning)            
            fprintf(‘Whithning patches\n‘ )
            drawnow           
            covX    = (1/(size(X,2)-1))*(X*X‘);
            [V,D]   = eig(covX);
            T       = (V*diag(sqrt(1 ./(diag(D) + 0.1))))*V‘;
            X       = T * X;            
            fprintf(‘End whithning\n‘ )
            drawnow            
        end        
        fprintf(‘Saving patches descriptor  %s ...\n‘ , [data_name , ‘_‘ , base_descriptor]);
        drawnow 
        save(fullfile(des_dir , [data_name , ‘_‘ , base_descriptor]) , ‘X‘ , ‘Z‘  , ‘Y‘ , ‘y‘ , ‘classe_name‘ , ‘patchdim‘ , ‘nbpatches‘ , ‘N‘  , ‘-v7.3‘)
        clear X Z Y y;
    end
end

current_descriptor = choice_descriptors;
base_descriptor    = descriptors_name{current_descriptor};
current_encoding = choice_encoding
base_encoding    = encoding_name{current_encoding};
dictfile = fullfile(dico_dir , [data_name , ‘_‘ , base_encoding , ‘_‘ , base_descriptor]);
dictfile = [dictfile,‘.mat‘];
if (~exist(featfile))
    do_encoding = 1;
else
    do_encoding = 0;
end
if(do_encoding)
    for j  = 1 : nb_encoding 
        current_encoding = choice_encoding(j);
        base_encoding    = encoding_name{current_encoding};
        eval([‘encoding = @‘ base_encoding ‘;‘]);

        for i  = 1 : nb_descriptors            
            current_descriptor = choice_descriptors(i);
            base_descriptor    = descriptors_name{current_descriptor};            
            nbpatches            = descriptors_param{current_descriptor}{1}.nbpatches;
            nbpatchetotal       = nbpatches*N;
            patchdim              = descriptors_param{current_descriptor}{1}.patchdim;
            nbscale               = descriptors_param{current_descriptor}{1}.nbscale;
            dimcolor              = descriptors_param{current_descriptor}{1}.dimcolor;
            K                         = encoding_param{current_encoding}{current_descriptor}.K;
            nbpatchesperclass  = encoding_param{current_encoding}{current_descriptor}.nbpatchesperclass;
            D                          = zeros(patchdim , K , nbscale , dimcolor , ‘single‘);            
            fprintf(‘Loading patches descriptor %s ...\n‘ , [data_name , ‘_‘ , base_descriptor]);
            drawnow            
            load(fullfile(des_dir , [data_name , ‘_‘ , base_descriptor]) , ‘X‘ , ‘Z‘ , ‘Y‘ , ‘y‘ , ‘classe_name‘)

            for c = 1 : dimcolor
                for s = 1 : nbscale
                    currentscale      = descriptors_param{current_descriptor}{1}.scale(s);
                    index                 = find( (Z(3 , :) == currentscale ) & (Z(4 , :) == c) );
                    Yindex               = Y(index);
                    lindex                 = length(index);
                    indexdico            = [];
                    for t = 1 : nb_topic
                        indt          = find(Yindex == t);
                        lindt         = length(indt);
                        idx           = randperm(lindt);
                        idxtemp   = idx(1:min(nbpatchesperclass ,lindt));
                        indexdico = [indexdico , index(indt(idxtemp))];
                    end

                    fprintf(‘Learning dictionary of K = %d words with encoder = %s, scale = %5.3f, dimcolor = %d from %d/%d patches of %s \n‘ , K , base_encoding , currentscale , c , length(indexdico) , lindex , base_descriptor)
                    drawnow
                    D(: , : , s , c)  = encoding(X(: , indexdico) , encoding_param{current_encoding}{current_descriptor});
                end
            end            
            fprintf(‘Saving dictionary  %s ...\n‘ , [data_name , ‘_‘ , base_encoding , ‘_‘ , base_descriptor]);
            drawnow            
            save(fullfile(dico_dir , [data_name , ‘_‘ , base_encoding , ‘_‘ , base_descriptor]) , ‘D‘);
            clear X Z Y y classe_name;            
        end
    end
end

current_descriptor = choice_descriptors;
base_descriptor    = descriptors_name{current_descriptor};
current_features   = choice_feature;
base_features      = features_name{current_features};
dlfeatfile = fullfile(feat_dir , [data_name , ‘_‘ , base_descriptor , ‘_‘ , base_features]);
dlfeatfile = [dlfeatfile,‘.mat‘];
if (~exist(dlfeatfile))
    do_compute_features = 1;
else
    do_compute_features = 0;
end

if(do_compute_features)
    for j  = 1 : nb_encoding
        current_features   = choice_feature(j);
        base_features      = features_name{current_features};
        current_encoding   = choice_encoding(j);
        base_encoding      = encoding_name{current_encoding};
        eval([‘features = @‘ base_features ‘;‘]);
        for i  = 1 : nb_descriptors
            current_descriptor                                          = choice_descriptors(i);
            base_descriptor                                             = descriptors_name{current_descriptor};
            nbpatches                                                      = descriptors_param{current_descriptor}{1}.nbpatches;
            nbpatchetotal                                               = nbpatches*N;
            patchdim                                                      = descriptors_param{current_descriptor}{1}.patchdim;
            nbscale                                                        = descriptors_param{current_descriptor}{1}.nbscale;
            dimcolor                                                       = descriptors_param{current_descriptor}{1}.dimcolor;
            features_param{current_features}{current_descriptor}.scale  = descriptors_param{current_descriptor}{1}.scale;
            features_param{current_features}{current_descriptor}.L      = patchdim;            
            current_feature_param                                       = features_param{current_features}{current_descriptor};            
            fprintf(‘Loading dictionnary %s ...\n‘ , [data_name , ‘_‘ , base_encoding , ‘_‘ , base_descriptor]);
            drawnow
            load(fullfile(dico_dir , [data_name , ‘_‘ , base_encoding , ‘_‘ , base_descriptor]) , ‘D‘);            
            fprintf(‘Loading patches descriptor %s ...\n‘ , [data_name , ‘_‘ , base_descriptor]);
            drawnow            
            load(fullfile(des_dir , [data_name , ‘_‘ , base_descriptor]) , ‘X‘ , ‘Z‘  , ‘y‘ ,  ‘classe_name‘);            
            K                                                           = size(D , 2);
            nH                                                          = current_feature_param.nH;
            X                                                           = reshape(X , descriptors_size{current_descriptor} , N);
            Z                                                           = reshape(Z , 6*nbpatches , N);
            F                                                           = zeros(K*nH*nbscale*dimcolor , N);

            co                                                          = 1;
            for t = 1 : nb_topic
                current_path  = fullfile(pwd , ‘images‘ , data_name , dirim(t+2).name);
                current_dir   = dir(fullfile(current_path , [‘*.‘ , im_ext]));
                current_topic = char(classe_name(t));
                for i = 1 : length(current_dir)
                    fprintf(‘encoder = %s, topic = %s (%d/%d), patches = %s , image = %s (%d/%d)\n‘ , base_features , current_topic, t , nb_topic , base_descriptor , current_dir(i).name , i , nbimagespertopic(t))
                    drawnow                    
                    XX              = reshape(X(: , co) , patchdim , nbpatches);
                    ZZ              = reshape(Z(: , co) , 6 , nbpatches);
                    F(: , co)       = features(D , XX , ZZ  , current_feature_param);
                    co              = co + 1;
                end
            end            
            X                  = F;
            clear F Z S;
            fprintf(‘Saving features  %s ...\n‘ , [data_name , ‘_‘ , base_descriptor , ‘_‘ , base_features]);
            drawnow
            dlfeatfile = fullfile(feat_dir , [data_name , ‘_‘ , base_descriptor , ‘_‘ , base_features]);
            save( dlfeatfile, ‘X‘ , ‘y‘ , ‘classe_name‘ , ‘-v7.3‘);
        end
    end
end
fprintf(‘Feature extraction  finished!!‘);

该程序提取提取后对特征聚类生成词袋,并依据词袋对图像特征进行编码,为每幅图像生成特征。详细内容可参看Matlab图像识别/检索系列(9)—开源工具介绍之图像识别reco_toolbox

京东金融大数据竞赛猪脸识别(2)- 图像特征提取之一

标签:图像特征提取   文件夹遍历   

原文地址:http://blog.51cto.com/8764888/2085964

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!