{"id":5174,"date":"2014-03-14T09:00:40","date_gmt":"2014-03-14T13:00:40","guid":{"rendered":"https:\/\/blogs.mathworks.com\/pick\/?p=5174"},"modified":"2014-03-14T08:27:43","modified_gmt":"2014-03-14T12:27:43","slug":"detecting-faces-in-images","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/pick\/2014\/03\/14\/detecting-faces-in-images\/","title":{"rendered":"Detecting Faces in Images"},"content":{"rendered":"

Brett<\/a>'s Pick this week is more of a challenge than a \"Pick\".<\/p>

If I were to search the MATLAB Central File Exchange for \"face detection\" (with the quotation marks) I would get a dazzling--and somewhat overwhelming--array of 44 hits<\/a>. Trying to detect faces (or anything else*) in images seems to me a reasonable thing to want to do, and in my mind typifies the challenges that the Computer Vision System Toolbox<\/a> was made to address. In fact, I shudder to think of what classical \"image processing\" code designed to detect faces might look like.<\/p>

But how do we navigate the 44 files on the File Exchange that facilitate that detection process? Where do we start? I can sort the results by number of downloads, by rating, by relevancy, ....<\/p>

\"\" <\/p>

Some of those downloads seem to have great potential. But where does one start?<\/p>

For this post, I'm going to go \"out-of-model\" and focus not on a submitted File Exchange file, but on core capabilities of the Computer Vision System Toolbox. This Toolbox has a \"Cascade Object Detector\"<\/a> that facilitates out-of-the-box detection of faces, eyes, noses, mouths, and upper bodies. In fact, there are two in-product face detectors, and \"FrontalFaceCART\" (frontal face detection using \"Classification And Regression Tree\" analysis) is the default tool behavior.<\/p>

Using the detectors in the Computer Vision System Toolbox is stunningly simple; we simply instantiate an instance<\/a> of the cascade object detector and, for visualization purposes, a vision.ShapeInserter:<\/p>

faceDetector = vision.CascadeObjectDetector;\r\nshapeInserter = vision.ShapeInserter('BorderColor'<\/span>,'Custom'<\/span>,'CustomBorderColor'<\/span>,[0 255 255]);\r\n<\/pre>
We then read input image:<\/p>
I = imread('visionteam.jpg'<\/span>);\r\nimshow(I);shg;\r\n<\/pre>\"\" 
Then we simply \"step\" the instantiated objects on the image of interest. The CascadeObjectDetector returns the bounding boxes of the detected objects, and the ShapeInserter delimits them in the image:<\/p>
bbox = step(faceDetector, I);\r\n% Draw boxes around detected faces and display results<\/span>\r\nI_faces = step(shapeInserter, I, int32(bbox));\r\nimshow(I_faces), title('Detected faces'<\/span>);\r\n<\/pre>\"\" 
Detecting faces using MathWorks' functionality is trivially easy. It requires MATLAB, the Image Processing Toolbox, and the Computer Vision System Toolbox, and a few readily reproducible lines of code.<\/p>
Swag to the first person who shows me how to detect faces in \"visionteam.jpg\" with a File Exchange submission!<\/i><\/b><\/p>
By the way, you can readily train MATLAB to find objects that are not in the \"pre-trained\" list above. For that, you might find these tools useful:<\/p>