matlab-调用摄像头人脸识别

时间:2024-03-03 20:49:10

----------------------------边学边写边学习-------------------------------------

版本:2014a

 

调用摄像头

a = imaqhwinfo

如果出现下面的警告说明你没安装扩展工具。
警告: No Image Acquisition adaptors found. Image acquisition adaptors may be available as downloadable support packages. Open Support Package Installer to install additional vendors.

这时候Support Package Installer在MATLAB里面有下划线,然后你点开它,MATLAB会提供大概13个软件包,这时候选择OS Generic Video Interface下载安装就OK了 (要求注册账号,随便用个邮箱注册下就可以了,不需要付费)。

(matlab查看摄像头详细信息 请看 https://blog.csdn.net/hmg25/article/details/4126122 

 

下面就是调用笔记本电脑摄像头并打开图像

(%如果使用USB摄像头,一般为2,笔记本自带摄像头为1)

vidDevice = imaq.VideoDevice(\'winvideo\', 1, \'YUY2_640x480\', ...
    \'ROI\', [1 1 640 480], ...
    \'ReturnedColorSpace\', \'rgb\' );
preview(vidDevice);

 

人脸检测我们用的是matlab的机器视觉工具箱(瞬间觉得matlab真心强大)

VJ算法的目的是检测人脸,但是其思想同样可以用于检测其他物体,只需进行训练即可。
VJ算法在Matlab里面实现的时候,已经训练好了正脸、侧脸、上半身、眼睛、嘴、鼻子,这些都是可以直接检测,不需训练,直接调用CascadeObjectDetector函数即可。

下面是检测人脸和上半身的例子

    % Example 1:  Face detection
      % ----------------------------        
      faceDetector = vision.CascadeObjectDetector; % Default: finds faces 

      I = imread(\'visionteam.jpg\');
      bboxes = step(faceDetector, I); % Detect faces

      % Annotate detected faces
      IFaces = insertObjectAnnotation(I, \'rectangle\', bboxes, \'Face\');   
      figure, imshow(IFaces), title(\'Detected faces\'); 

      % Example 2: Upper body detection
      % --------------------------------------       
      bodyDetector = vision.CascadeObjectDetector(\'UpperBody\');    
      bodyDetector.MinSize = [60 60];
      bodyDetector.MergeThreshold = 10;

      I2 = imread(\'visionteam.jpg\');
      bboxBody = step(bodyDetector, I2); % Detect upper bodies

      % Annotate detected upper bodies   
      IBody = insertObjectAnnotation(I2, \'rectangle\', ...
                                     bboxBody, \'Upper Body\');
      figure, imshow(IBody), title(\'Detected upper bodies\');

  

至于调用摄像头进行人脸识别,肯定是 调用摄像头的过程中对每一帧图像分别进行识别,然后再在图像中框出来。

这就要求 速度 要足够快。所以检测的时候就要压缩你图像的像素了。

下面放代码

faceDetector = vision.CascadeObjectDetector(); %enable viola jones algorithm
bbox = [100 100 100 100];
vidDevice = imaq.VideoDevice(\'winvideo\', 1, \'YUY2_640x480\', ...
    \'ROI\', [1 1 640 480], ...
    \'ReturnedColorSpace\', \'rgb\' );
%set(vidDevice.DeviceProperties, \'FrameRate\', \'30\');
boxInserter = vision.ShapeInserter(\'BorderColor\',\'Custom\',...
    \'CustomBorderColor\',[255 255 0]);
textInserter = vision.TextInserter(\'%d\',\'LocationSource\',\'Input port\',\'Color\',[255,255, 0],\'FontSize\',12);
nFrame =300;
vidInfo = imaqhwinfo(vidDevice);
vidHeight = vidInfo.MaxHeight;
vidWidth = vidInfo.MaxWidth;
videoPlayer = vision.VideoPlayer(\'Position\',[300 100 640+30 480+30]);

for k = 1:nFrame % start recording with 300 frames
    %tic; % timer start
    videoFrame = step(vidDevice); % enable the image capture by webcam
    bbox = 4 * faceDetector.step(imresize(videoFrame, 1/4)); % boost video\'s fps
    videoOut = step(boxInserter, videoFrame, bbox); % highlight the boxes of face at video
    %release(boxInserter);
    step(videoPlayer, videoOut); % display the video live in video player
end

  一共执行了300帧,下面放图。