0

我写了一个代码，在matlab中对多个图像执行模板的互相关。这个代码是为了跟踪一个单元格在多个帧中的移动，代码有点交互，首先用户从第一个选择图像模板框架比他/她运行程序来执行互相关，我已经定义了一个感兴趣的区域，代码必须在其中找到这个模板。我的问题是如何在互相关检测到并在所有帧中定位后获取单元格位置的 x 和 y 坐标

 format long
fontSize = 10;
file_name = 'stack0001.tif';  %TIFF Stack
image_info = imfinfo(file_name);
numImg = length(image_info) %Number of images in stack
rgbImage = imread(file_name,'Index', 1);
[sub_rgbImage,rect_rgbImage] = imcrop(rgbImage);
figure,
imshow(sub_rgbImage)
title({'Template Image ' ;'to Search For'});
h=figure;
 for i1=1:numImg %Read Each Frame
    fprintf('Now correlating frame #%d with frame #%d\n',1,i1);

    rect_A= [247.5 134.5 35 81]; % region to look for object
    A=imread(file_name,'Index', i1);%read the following image from image loop (in tiff stack)
    sub_A = imcrop(A,rect_A); % Region of Interest
    figure,
    imshow(sub_A); % Show region of Interest
    axis on;

    % Search the red channel for a match.
    correlationOutput = normxcorr2(sub_rgbImage(:,:,1), sub_A(:,:,1));
    x=size(correlationOutput, 2);
    y=size(correlationOutput, 1);
    h=figure;
    set(h,'visible','off');
    figure, surf(correlationOutput),shading flat;


    h=figure;
    set(h,'visible','off');
    figure('Position', [300 300 300 300]);
    imshow(correlationOutput, []);
    sprintf('Normalized Cross Correlation Output of frame #%d and #%d\n',i1,i1+1);
    title('Cross Correlation');
    %Offset between the images found by correlation

    [maxCorrValue, maxIndex] = max(abs(correlationOutput(:)))
    [ypeak,xpeak] = ind2sub(size(correlationOutput),maxIndex(1))
    corr_offset = [(ypeak-size(sub_rgbImage,1)) 
                       (xpeak-size(sub_rgbImage,2))] ;


    %relative offset between position of subimages
    rect_offset = [(rect_A(1)- rect_rgbImage(1))
                   (rect_A(2)- rect_rgbImage(2))]

    %total offset
    offset = rect_offset+corr_offset;
    xoffset= offset(1)
    yoffset= offset(2)


end
4

1 回答 1

0

如果可以将其转换为二进制图像，则可以找到边界。也许通过对背景进行阈值化并创建细胞的二进制图像。然后您可以使用 regionprops 方法来访问图像中连接组件的属性。或者您可以使用 bwboundaries 并知道轮廓像素身份而不是质心。

于 2013-10-05T18:33:01.347 回答