OpenCv face detection procedure and Explanation

Hi all, Hope you all are doing all. Today I will explain the face detection procedure used in opencv.

Procedure :

Step1: create cascaded classifier using the training algorithm provided by opencv and get the .xml file.

Step2: load the pre-made .xml file.

Step3: input frame from camera/ input image and convert it to grey scale image.

Step4: use opencv’s ‘CascadeClassifier:: detectMultiScale()’ function to detect faces of different sizes in the input image.

Explanation of CascadeClassifier::detectMultiScale() –

Parameters:

i. image - Matrix of the type CV_8U containing an image where objects are detected.

ii. objects – Vector of rectangles where each rectangle contains the detected object.

iii. scaleFactor – Parameter specifying how much the image size is reduced at each image scale.

iv. minNeighbors – Parameter specifying how many neighbour's each candidate rectangle should have to retain it.

v. minSize – Minimum possible object size. Objects smaller than that are ignored.

vi. maxSize – Maximum possible object size. Objects larger than that are ignored.

•       Basically what ‘CascadeClassifier:: detectMultiScale()’ does is it takes the original image and creates an image pyramid from it, using the resize factor and searches for faces/objects in it. Image pyramid is a multi-scale representation of an image, such that the face detection can be scale-invariant, i.e., detecting large and small faces using the same detection window.

•       This gives the ability of detecting faces/objects at a single model scale, throughout different images scales, meaning that if a detection happens at a specific layer, the  bounding box will be rescaled the same amount as the original image was to reach that pyramid layer.

•       Using this technique you can detect multiple people scales at only a single model scale, which is computationally less expensive than training a model for each possible scale and running those over the single image.

•       To make a good detector you need to train the cascade properly with a good number of sample images. Here is an example-