This paper presents an experimental computer vision system which aids the identification of individual Great Whites (Carcharodon carcharias) based on digital imagery. We propose a methodology that uses the jagged pattern of the rear (trailing) side of the first dorsal fin as a machine-recognizable biometric identifier for differentiating between individual sharks. The system takes as input high-quality, high-resolution images of a side view of the fin. Note that data of this kind can be routinely acquired during boat trips to the species’ natural habitats. After applying histogram equalization to an input image, the software detects the fin area using the Viola-Jones object recognition framework. The system provides an option to improve on this automated detection by manual, watershed-aided fin segmentation. Subsequently, Lowe’s Scale-Invariant Feature Transform (SIFT) is applied to the fin segment yielding a set of biometrically significant, local visual features. These features are filtered using RANSAC and Geometric Histogramming before being matched iteratively against a database of known shark profiles stored as KD-Trees of SIFT descriptors. Ordering by application-tailored distance measures finally produces a ranked list of best matches between the shark in the input image and the entries of the database. Experiments on a small sample database of n=100 individuals were conducted in order to produce a preliminary benchmark that describes the system’s performance. Results showed that in 86% of cases the system ranked the correct individual within the top ten of matches, whilst the exact individual could be pinpointed in 46% of cases. Acknowledging the need for further system improvements, we conclude that the experimental prototype presented constitutes a promising step towards a non-invasive biometric tool for an automatic photo identification of individual Great Whites in the field.