My requirement is i need to detect human face from the given cctv image. In the cctv image there will be unnecessary objects which need to be removed.if the obtained face image is blur needs to improve the quality as well
currently we are trying with opencv API, the code as follows
CascadeClassifier cascadeClassifier = new
CascadeClassifier("haarcascade_profileface.xml");
Mat image=Highgui.imread("testing.jpg");
MatOfRect bodyDetections = new MatOfRect();
cascadeClassifier.detectMultiScale(image, bodyDetections);
for (Rect rect : bodyDetections.toArray()) {
BufferedImage croppedImage = originalPic.getSubimage(rect.x,
rect.y,rect.width,rect.height); **unable to detect the body coordinates
here**
}
In the above approach multiple objects of the image are detected as face,which is error.
In the cctvc image if there is only side face how to extract the complete face ?
Pls suggest the best possible way to achieve my requirement.
Thanks IMGen
You may want to look at the new AWS solution
https://aws.amazon.com/blogs/aws/category/amazon-rekognition/