This paper aims to solve the problem with the current image matching algorithm which ignores image information, thus leads to bad robustness of illumination variation and easily causes error matching. Color is an important component for distinction between images. In this paper, we presented a new approach based on color invariant and ORB feature, called C-ORB. It applied color information to the image matching while retaining the ORB's efficiency and performance. Experimental results showed that C-ORB retained the ORB's efficiency, could get more image details, and was more accurate and stable with respect to variations in the photometrical imaging conditions. In conclusion, for recognition and matching of pressworks on mobile terminals like mobile phone and tablet PC, this algorithm can further reduce error matching while retaining the original speed of image recognition.