A Fingerprint Image Enhancement Algorithm Based on Stretching Transfer Function

Authors:

Abstract
In this paper, a fingerprint image enhancement algorithm based on the stretching transfer function is proposed. The Otsu method is used to generate the threshold, which divides the fingerprint image grayscale roughly into two parts. The width of grayscale distribution can be controlled by adjusting the parameter of the stretching transfer function. The contrast of the input fingerprint image will be enhanced by the function, highlight image layers and make the ridge and valley lines clearer. The function could also retain the fingerprint image information in transformation process, thus lays a solid foundation for the accuracy and reliability of the fingerprint characteristic value extraction in the next step. The treatment effect of the algorithm is obviously better than that of histogram equalization algorithm; the superiority also lies in the smaller amount of calculation and the faster processing speed which effectively avoids manual intervention. It can be used for the occasion with limited computing resources and high real-time requirements. Besides, the ability to control the contrast of output image by only changing a single parameter provides users with regulations and choices in biometric.