【光电智造】MATLAB机器视觉工具箱的应用

% 读取图像I = imread('lena.png');
% 显示图像imshow(I);

% 缩放图像J = imresize(I, 0.5);
% 旋转图像K = imrotate(I, 45);
% 裁剪图像L = imcrop(I, [100, 100, 200, 200]);
% 显示结果figuresubplot(2,2,1),imshow(I),title('原始图像');subplot(2,2,2),imshow(J),title('缩放图像');subplot(2,2,3),imshow(K),title('旋转图像');subplot(2,2,4),imshow(L),title('裁剪图像');

% 提取SURF特征points = detectSURFFeatures(I);features = extractFeatures(I, points);
% 提取HOG特征[hog, visualization] = extractHOGFeatures(I, 'CellSize', [8 8]);
% 提取LBP特征lbpFeatures = extractLBPFeatures(I);
% 显示结果figuresubplot(2,2,1),imshow(I),title('原始图像');subplot(2,2,2),imshow(I); hold on; plot(points.selectStrongest(50));title('SURF特征');subplot(2,2,3),imshow(visualization),title('HOG特征');subplot(2,2,4),bar(lbpFeatures),title('LBP特征');

% 训练分类器positiveInstances = objectDetectorTrainingData(gTruth);negativeFolder = fullfile(matlabroot, 'toolbox', 'vision', 'visiondata', 'nonObjectImages');negativeImages = imageDatastore(negativeFolder);trainCascadeObjectDetector('detector.xml', positiveInstances, negativeFolder, 'FalseAlarmRate', 0.1, 'NumCascadeStages', 5);
% 加载分类器detector = vision.CascadeObjectDetector('detector.xml');
% 检测目标bbox = step(detector, I);
% 显示结果figureimshow(I); hold on;for i = 1:size(bbox,1)    rectangle('Position', bbox(i,:), 'EdgeColor', 'r', 'LineWidth', 2);endtitle('检测结果');

% 读取图像I1 = imread('image1.png');I2 = imread('image2.png');
% 提取SURF特征points1 = detectSURFFeatures(I1);points2 = detectSURFFeatures(I2);features1 = extractFeatures(I1, points1);features2 = extractFeatures(I2, points2);
% 匹配特征indexPairs = matchFeatures(features1, features2);
% 选择最佳匹配matchedPoints1 = points1(indexPairs(:,1), :);matchedPoints2 = points2(indexPairs(:,2), :);[tform, inlierPoints1, inlierPoints2] = estimateGeometricTransform(matchedPoints1, matchedPoints2, 'affine');
% 图像配准outputView = imref2d(size(I1));I2Registered = imwarp(I2, tform, 'OutputView', outputView);
% 显示结果figureimshowpair(I1, I2Registered, 'blend');title('图像配准');

% 读取图像I1 = imread('image1.png');I2 = imread('image2.png');
% 提取SURF特征points1 = detectSURFFeatures(I1);points2 = detectSURFFeatures(I2);features1 = extractFeatures(I1, points1);features2 = extractFeatures(I2, points2);
% 匹配特征indexPairs = matchFeatures(features1, features2);
% 选择最佳匹配matchedPoints1 = points1(indexPairs(:,1), :);matchedPoints2 = points2(indexPairs(:,2), :);[tform, inlierPoints1, inlierPoints2] = estimateGeometricTransform(matchedPoints1, matchedPoints2, 'affine');
% 三维重建worldPoints = triangulate(inlierPoints1, inlierPoints2, tform);ptCloud = pointCloud(worldPoints);pcshow(ptCloud);
% 显示结果title('三维重建');

% 读取视频video = VideoReader('traffic.avi');
% 创建点跟踪器tracker = vision.PointTracker('MaxBidirectionalError', 2);
% 选择第一帧图像中的初始点frame = readFrame(video);points = detectMinEigenFeatures(rgb2gray(frame), 'ROI', [100, 100, 300, 300]);points = points.Location;initialize(tracker, points, frame);
% 跟踪目标while hasFrame(video)    frame = readFrame(video);    [points, isFound] = step(tracker, frame);    visiblePoints = points(isFound, :);    oldInliers = oldPoints(isFound, :);    if size(visiblePoints, 1) >= 2        [tform, oldInliers, visiblePoints] = estimateGeometricTransform(oldInliers, visiblePoints, 'similarity');        bbox = [min(visiblePoints) max(visiblePoints) -
min(visiblePoints)];frame = insertShape(frame, 'Rectangle', bbox, 'LineWidth', 2);oldPoints = visiblePoints;setPoints(tracker, oldPoints);endimshow(frame);end

% 读取图像faceDetector = vision.CascadeObjectDetector();I = imread('faces.jpg');
% 检测人脸bbox = step(faceDetector, I);
% 显示结果figureimshow(I); hold on;for i = 1:size(bbox,1)    rectangle('Position', bbox(i,:), 'EdgeColor', 'r', 'LineWidth', 2);endtitle('检测结果');
% 训练分类器imds = imageDatastore('FaceDatabase', 'IncludeSubfolders', true, 'LabelSource', 'foldernames');[trainingSet, testSet] = splitEachLabel(imds, 0.8, 'randomize');bag = bagOfFeatures(trainingSet);categoryClassifier = trainImageCategoryClassifier(trainingSet, bag);confMatrix = evaluate(categoryClassifier, testSet);
% 测试分类器I = imread('test.jpg');[labelIdx, scores] = predict(categoryClassifier, I);label = categoryClassifier.Labels(labelIdx);
% 显示结果figureimshow(I); title(char(label));

% 读取图像I = imread('text.png');
% 进行文字识别results = ocr(I);
% 显示结果figureimshow(I); hold on;for i = 1:length(results.Words)    text(results.WordBoundingBoxes(i,1), results.WordBoundingBoxes(i,2), results.Words{i}, 'FontSize', 20, 'Color', 'r', 'HorizontalAlignment', 'left', 'VerticalAlignment', 'top');endtitle('文字识别结果');

% 读取图像I = imread('coins.png');
% 进行图像分割bw = imbinarize(I);D = -bwdist(~bw);D(~bw) = -Inf;L = watershed(D);rgb = label2rgb(L, 'jet', 'w', 'shuffle');
% 显示结果figureimshow(rgb); title('图像分割结果');

% 读取视频video = VideoReader('shaky.avi');
% 创建光流估计器opticFlow = opticalFlowFarneback('PyrScale', 0.5, 'NumLevels', 4, 'NumIterations', 2, 'PolyN', 7, 'PolySigma', 1.5, 'FastPyramids', true);
% 对每一帧图像进行稳定while hasFrame(video)    frame = readFrame(video);    flow = estimateFlow(opticFlow, rgb2gray(frame));    [x, y] = meshgrid(1:size(frame,2), 1:size(frame,1));    warpedFrame = interp2(x, y, double(frame), x+flow.Vx, y+flow.Vy);    tform = vision.GeometricTransformEstimator('Transform', 'Affine');    [tform, intermediatePoints] = step(tform, reshape([x(:) y(:)], [], 2), reshape([x(:)+flow.Vx(:) y(:)+flow.Vy(:)], [], 2));    stabilizedFrame = imwarp(frame, affine2d(tform.T), 'OutputView', imref2d(size(frame)));    imshow(stabilizedFrame);end