4X4 Census Transform
This is an incremental improvement for computer vision researchers and practitioners seeking better image processing techniques.
The paper tackles the problem of improving image texture crispness and contrast in computer vision by proposing a 4X4 Census Transform (4X4CT) that uses a sixteen-pixel kernel with four overlapped 3X3 groups, resulting in preliminary experiments showing enhanced image quality compared to the traditional 3X3 CT.
This paper proposes a 4X4 Census Transform (4X4CT) to encourage further research in computer vision and visual computing. Unlike the traditional 3X3 CT which uses a nine pixels kernel, the proposed 4X4CT uses a sixteen pixels kernel with four overlapped groups of 3X3 kernel size. In each overlapping group, a reference input pixel profits from its nearest eight pixels to produce an eight bits binary string convertible to a grayscale integer of the 4X4CT's output pixel. Preliminary experiments demonstrated more image textural crispness and contrast than the CT as well as alternativeness to enable meaningful solutions to be achieved.