程序付费分享:
微信:1075933062
这个文章介绍使用matlab 识别车牌内的信息:
识别的步骤如下:
1、导入图片
2、定位到车牌矩形框的位置
3、进行畸形矫正
4、字符分割
5、生成字符库
6、SVM训练
7、基于SVM 车牌识别系统 的设计
由于需要进行SVM训练 所以需要建立一个对应的车牌字符库
下面建立一个生成字符库的APP ,来生成对应的库
然后会生成一个下面这样的字符库最后可以通过SVM 训练
关于SVM 的训练可以参考这篇博客
基于MATLAB,使用SVM和ANN实现车牌识别_weixin_42864037的博客-CSDN博客_matlab svm车牌识别
由于该程序的图片是灰度的所以需要对函数进行相应的更改 然后就可以进行训练了:
提取图片特征函数:
function [trainingFeatures,trainingLabels,testFeatures,testLabels]=extractFeature(trainingSet,testSet)%% 确定特征向量尺寸img = read(trainingSet(1),1);%转化为灰度图像% img=im2gray(img);% %转化为2值图像% lvl = graythresh(img);% img = im2bw(img, lvl);img=imresize(img,[256 256]);cellSize = [4 4];[hog_feature, vis_hog] = extractHOGFeatures(img,'CellSize',cellSize);glcm_feature = getGLCMFeatures(img);SizeOfFeature = length(hog_feature)+ length(glcm_feature);trainingFeatures = [];trainingLabels = [];for digit = 1:numel(trainingSet) numImages = trainingSet(digit).Count;features = zeros(numImages, SizeOfFeature, 'single');%初始化特征向量% 遍历每张图片for i = 1:numImagesimg = read(trainingSet(digit), i);% 取出第i张图片 % img=rgb2gray(img);% 转化为灰度图像% glcm_feature = getGLCMFeatures(img); % 提取GLCM特征 % lvl = graythresh(img); % 阈值化% img = im2bw(img, lvl); % 转化为2值图像img=imresize(img,[256 256]);% 提取HOG特征[hog_feature, vis_hog] = extractHOGFeatures(img,'CellSize',cellSize); % 合并两个特征features(i, :) = [hog_feature glcm_feature];end% 使用图像描述作为训练标签labels = repmat(trainingSet(digit).Description, numImages, 1); % 逐个添加每张训练图片的特征和标签trainingFeatures = [trainingFeatures; features];trainingLabels = [trainingLabels; labels]; endtestFeatures = [];testLabels = [];for digit = 1:numel(testSet) numImages = testSet(digit).Count; %初始化特征向量features = zeros(numImages, SizeOfFeature, 'single'); for i = 1:numImages img = read(testSet(digit), i); %转化为灰度图像% img=rgb2gray(img);% glcm_feature = getGLCMFeatures(img); %转化为2值图像% lvl = graythresh(img);% img = im2bw(img, lvl);img=imresize(img,[256 256]);[hog_4x4, vis4x4] = extractHOGFeatures(img,'CellSize',cellSize);features(i, :) = [hog_4x4 glcm_feature];end % 使用图像描述作为训练标签labels = repmat(testSet(digit).Description, numImages, 1); testFeatures = [testFeatures; features];testLabels=[testLabels; labels];endend
function [features] = getGLCMFeatures(image)features_all = [];for i = 1:10glcm = graycomatrix(image, 'Offset', [0,i]);stats = graycoprops(glcm);glcm45 = graycomatrix(image, 'Offset', [-i,i]);stats45 = graycoprops(glcm45);glcm90 = graycomatrix(image, 'Offset', [-i,0]);stats90 = graycoprops(glcm90);glcm135 = graycomatrix(image, 'Offset', [-i,-i]);stats135 = graycoprops(glcm135);stats7x4 = [stats.Contrast stats.Correlation stats.Energy stats.Homogeneity;stats45.Contrast stats45.Correlation stats45.Energy stats45.Homogeneity;stats90.Contrast stats90.Correlation stats90.Energy stats90.Homogeneity;stats135.Contrast stats135.Correlation stats135.Energy stats135.Homogeneity];features_all = [features_all mean(stats7x4,1) std(stats7x4,0,1)];endfeatures = features_all;
clear;dir=('\DataWork\车牌识别SVM\GUI\train');testdir=('\DataWork\车牌识别SVM\GUI\train');trainingSet = imageSet(dir,'recursive');testSet = imageSet(testdir,'recursive');[trainingFeatures,trainingLabels,testFeatures,testLabels]=extractFeature(trainingSet,testSet);classifier = fitcecoc(trainingFeatures, trainingLabels);save classifier.mat classifier -v7.3;predictedLabels = predict(classifier, testFeatures);confMat=confusionmat(testLabels, predictedLabels)accuracy=(confMat(1,1)/sum(confMat(1,:))+confMat(2,2)/sum(confMat(2,:)))/2
load classifier.mat;% 加载训练好的SVM模型 img=imread("img034-00026.png");glcm_feature = getGLCMFeatures(img);%提取GLCM特征% lvl = graythresh(img);% img = im2bw(img, lvl);img=imresize(img,[256 256]);[hog_4x4, ~] = extractHOGFeatures(img,'CellSize',[4 4]);%提取HOG特征testFeature = [hog_4x4 glcm_feature]; %合并特征 predictedLabel = predict(classifier, testFeature) %使用predict函数进行分类