This work presents an implementation of Neocognitron Neural Network, using a high performance computing architecture based on GPU (Graphics Processing Unit). Neocognitron is an ar...
There usually exist many kinds of variations in face images taken under uncontrolled conditions, such as changes of pose, illumination, expression, etc. Most previous works on fac...
Current two-dimensional image based face recognition systems encounter difficulties with large facial appearance variations due to the pose, illumination and expression changes. ...
Design and implementation of a fast parallel architecture based on an improved principal component analysis (PCA) method called Composite PCA suitable for real-time face recogniti...
Abstract-- In general automatic face classification applications images are captured in natural environments. In these cases, the performance is affected by variations in facial im...