Menu
In school we learned about a method called 'eigenfaces' of applying PCA to many images to do face recognition. I was wondering, what is the approach most commonly used today to do face recognition?
I am hoping to do face recognition based on many images of different sizes and different views. Thanks
966
It begins with detection - distinguishing human faces from other objects in the image - and then works on identification of those detected faces. The state of the art tables for this task are contained mainly in the consistent parts of the task : the face verification and face identification tasks.
Three-dimensional face recognition technique uses 3D sensors to capture information about the shape of a face. This information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose, and chin.
It works by identifying and measuring facial features in an image. Facial recognition can identify human faces in images or videos, determine if the face in two images belongs to the same person, or search for a face among a large collection of existing images.
Eigenface is one of most famous classic method for face recognition. If you talk about recent popular method, you can check Robust Face Recognition via Sparse Representation, John Wright, Allen Yang, Arvind Ganesh, Shankar Sastry, and Yi Ma, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2009.
According to your description of your target, you may take a look at recognition multiple images (image set). I personally maintain a literature of classification based on image set. You can also check out my latest paper Face Recognition using Sparse Approximated Nearest Points between Image Sets, Yiqun Hu, Ajmal S. Mian and Robyn Owens, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI).
However, I have to say that face recognition techniques for an controlled environment is quite mature, the challenges still remain for the uncontrolled environment, where face images are not aligned, the view angles are different and the lighting conditions are dramatically different.
81
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
