Off-line handwritten numeral recognition is a very difficult task. It is hard to achieve high recognition results using a single set of features and a single classifier, since hand...
Kyoung Min Kim, Joong Jo Park, Young Gi Song, In-C...
The two main plagues of image restoration are oscillations and smoothing. Traditional image restoration techniques prevent parasitic oscillations by resorting to smooth regulariza...
In this paper, we propose a robust multi-layer background subtraction technique which takes advantages of local texture features represented by local binary patterns (LBP) and pho...
We present in this paper a method for implementing moment functions in a CMOS retina for shape recognition applications. The method is based on the use of binary patterns and it a...
Olivier Aubreton, Lew Fock Chong Lew Yan Voon, Guy...
We propose a new set of rotationally and translationally invariant features for image or pattern recognition and classification. The new features are cubic polynomials in the pix...