Color-Ciratefi: A color-based RST-invariant template matching algorithm

Template matching is a technique widely used for finding patterns in digital images. An efficient template matching algorithm should be able to detect template instances that have undergone geometric transformations. Similarly, a color template matching should be able to deal with color constancy problem. Recently we have proposed a new grayscale template matching algorithm named Ciratefi, invariant to rotation, scale, translation, brightness and contrast. In this paper we introduce the Color-Ciratefi that takes into account the color information. We use a new similarity metric in the CIELAB space to obtain invariance to brightness and contrast changes. Experiments show that Color-Ciratefi is more accurate than C-color-SIFT, the well-known SIFT algorithm that uses a set of color invariants. In conventional computers, Color-Ciratefi is slower than C-color-SIFT. However Color-Ciratefi is more suitable than C-color-SIFT to be implemented in highly parallel architectures like FPGA, because it repeats exactly the same set of operations for each pixel.