Fast image clustering based on compressed camera fingerprints

Every camera sensor leaves unique traces on the acquired images that can be thought of as a camera fingerprint. This work presents an efficient algorithm for clustering images based on their camera fingerprints. The algorithm performs a fast preliminary clustering based on a compressed representation of the camera fingerprints, then it refines the initial clusters using full-size fingerprints. The efficiency of the method is further improved by scanning the images according to a ranking index that depends on fingerprint estimation quality. The results confirm that the proposed method achieves a performance comparable to the state of the art approaches, with a significantly lower computational complexity, especially on large datasets. The method can also handle cases in which the number of clusters is much larger than the average size of the clusters.