Latent fingerprint segmentation using ridge template correlation

Even with the high accuracy of automated fingerprint identification in matching plain to rolled prints, latent to rolled print matching continues to require human input. Latent prints are those that are lifted from a surface, typically at a crime scene, whereas plain prints are obtained under supervision with quality control. In comparison to plain or rolled prints, latent prints are usually of poor quality and have a small fingerprint surface area, making it difficult to extract a large number of features reliably. Manually processing latent prints is time consuming, so efforts are being made to speed up the process through partial automation. One of the first steps is image segmentation, which is the separation of the foreground (fingerprint region) from the background. Traditional automated methods for segmentation are designed for backgrounds with random noise and perform poorly on structured/textured backgrounds, resulting in many spurious minutiae, thus inhibiting the matching process. This paper presents a novel approach for improving the performance of segmentation in latent prints, with and emphasis on structured backgrounds. The results show that the proposed method reduces the average detected fingerprint area from 60.7% of the total image to 33.6% while maintaining the rate of true minutiae in the fingerprint region; in effect, low-quality portions of the print are being removed from consideration. In a separate test, the rate of true minutiae labelled as background was reduced from 1.41% to 0.29% while maintaining the same average fingerprint region size in comparison to a traditional segmentation method. The results were obtained using a database of 258 latent fingerprint images with ground truth minutiae.