Menu
I'd like to know if you are aware of any algorithm to detect low-resolution faces in an image. The image could have any resolution and the faces resolution could be as low as 10x10 or 15x15. I am using OpenCV but I don't think the Haar classifiers provided allow me to work with resolutions so small. Are there any other alternative? Thanks
687
The Eigen faces Algorithm is the most commonly used methods in the field of facial recognition.
OpenCV. OpenCV is the most popular library for computer vision. Originally written in C/C++, it now provides bindings for Python. OpenCV uses machine learning algorithms to search for faces within a picture.
The AdaBoost-based face detection algorithm is an algorithm that is based on integral image, cascade classifier and AdaBoost algorithm. The basic idea is as following: First it uses the integral image to calculate face's Haar-like features quickly.
You can detect the faces in the image using method detectMultiScale() of the class named CascadeClassifier. This method accepts an object of the class Mat holding the input image and an object of the class MatOfRect to store the detected faces.
The Eigenface technique is (IIRC) known to work fairly well on low-resolution images. Human faces have a distinct pattern to them that's still visible at low quality, and I believe that using a sliding window technique in conjunction with this algorithm might produce good results.
153
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
