0

我正在研究阿拉伯字符的 OCR。我想尝试 glcm 作为特征提取方法。我在这里有代码：http: //www.mathworks.com/matlabcentral/fileexchange/22187-glcm-texture-features

输入图像（字符图像）示例：

在此处输入图像描述 在此处输入图像描述 在此处输入图像描述

我已经编写了一个代码来根据需要的功能获取 GLCM 输出。这里是：

function features = EkstraksiFitur_GLCM(x)
    glcm = graycomatrix(x,'offset',[0 1; -1 1; -1 0; -1 -1], 'NumLevels', 2); 

    stats = GLCM_Features1(glcm, 0);
    autocorrelation = double(mean (stats.autoc));
    if isnan(autocorrelation)
        autocorrelation=0;
    else
        autocorrelation=autocorrelation;
    end

    contrast = double(mean(stats.contr));
    if isnan(contrast)
        contrast=0;
    else
        contrast=contrast;
    end

    Correlation = double(mean (stats.corrm));
    if isnan(Correlation)
        Correlation=0;
    else
        Correlation=Correlation;
    end

    ClusterProminence = double(mean (stats.cprom));
    if isnan(ClusterProminence)
        ClusterProminence=0;
    else
        ClusterProminence=ClusterProminence;
    end

    ClusterShade = double(mean (stats.cshad));
    if isnan(ClusterShade)
        ClusterShade=0;
    else
        ClusterShade=ClusterShade;
    end

    Dissimilarity = double(mean (stats.dissi));
    if isnan(Dissimilarity)
        Dissimilarity=0;
    else
        Dissimilarity=Dissimilarity;
    end

    Energy = double(mean (stats.energ));
    if isnan(Energy)
        Energy=0;
    else
        Energy=Energy;
    end
    . 
    .
    .
    features=[autocorrelation, contrast, Correlation, Dissimilarity, Energy, Entropy, Homogeneity, MaximumProbability, SumAverage, SumVariance, SumEntropy, DifferenceVariance, DifferenceEntropy, InverseDifferenceMomentNormalized];

使用循环获取所有图像的特征（数据训练）：

srcFile = dir('D:\1. Thesis FINISH!!!\Data set\0 Well Segmented Character\Advertising Bold 24\datatrain\*.png');
fetrain = [];
for a = 1:length(srcFile)
    file_name = strcat('D:\1. Thesis FINISH!!!\Data set\0 Well Segmented Character\Advertising Bold 24\datatrain\',srcFile(b).name);
    A = imread(file_name);
    [gl] = EkstraksiFitur_GLCM2 (A);
    [fiturtrain] = reshape (gl, [56,1]) ;
    fetrain = [fetrain fiturtrain];
%   vectorname = strcat(file_name,'_array.mat');

end
 save ('fetrain.mat','fetrain');

我有这些功能。

在此处输入图像描述

然后使用神经网络运行训练过程，但我得到的准确率非常低。这是代码：

% clc;clear;close all;
% function net1 = pelatihan (input, target)
net = newff(fetrain,target,[10 2],{'tansig','tansig'},'trainscg');
% net.trainParam.mem_reduc = 2;
net.performFcn = 'mse'; 
net.divideFcn = 'dividetrain';
% [trainInd,valInd,testInd] = dividetrain(601);
net.trainParam.show = 10; % Frequency of progress displays (in epochs).
net.trainParam.epochs = 1000; %default 1000
net.trainParam.goal = 1e-6;
net = train(net,fetrain,target);
output = round(sim(net,fetrain));
save net1.mat net
% net2 = output;
data = fetest;

[target; output];
prediksi = round(sim (net, data));
[targetx; prediksi];

%% Calculate the accuracy %
y = 1;
j = size (prediksi, 2); 
% x = size (targetx, 2);
for i = 1:j 
    if prediksi (i) == targetx (i)
       y =y+1;
    else
        y;
    end 
end 
% y all correct data
% j all data
s = 'The accuracy is %.2f%%';
acc = 100 *(y/j);
sprintf (s,acc)

我试了几次，但准确率（NN测试结果）没有提高。它持续提供 1.96% 的输出。流程是否有问题，或者我制作的代码有问题？

任何帮助都会非常有帮助和感激

4

1 回答 1

1

首先，我可以从您提取的特征中看到它们没有归一化并且它们的范围不同。这意味着某些功能将主导其余功能。尝试规范化或标准化特征。您是仅在训练集上测量的准确性，还是您是一些测试集或交叉验证方法？我看到你正在使用 601 功能是真的吗？您是否尝试过特征选择方法来决定哪些特征更适合数据和模型？

其次，我想知道您正在为结构实现什么，而不是阅读完整的代码来了解您所做的事情。

第三，查看输入图像以了解您正在处理的环境会很有趣。

于 2016-06-03T10:58:27.473 回答