Résumé: Touchscreens are the primary input devices for smartphones and tablets. Although widely used, the output of touchscreen controllers is still limited to the two-dimensional position of the contacting finger. Finger angle (or orientation) estimation from touchscreen images has been studied for enriching touch input. However, only pitch and yaw are usually estimated and estimation error is large. One main reason is that touchscreens provide very limited information of finger. With the development of under-screen fingerprint sensing technology, fingerprint images, which contain more information of finger compared with touchscreen images, can be captured when a finger touches the screen. In this paper, we constructed a dataset with fingerprint images and the corresponding ground truth values of finger angle. We contribute with a network architecture and training strategy that harness the strong dependencies among finger angle, finger region, finger type, and fingerprint ridge orientation to produce a top-performing model for finger angle estimation. The experimental results demonstrate the superiority of our method over previous state-of-the-art methods. The mean absolute errors of the three angles are 6.6 degrees for yaw, 7.1 degrees for pitch, and 9.1 degrees for roll, markedly smaller than previously reported errors. Extensive experiments were conducted to examine important factors including image resolution, image size, and finger type. Evaluations on a set of under-screen fingerprints were also performed to explore feasibility in real-world applications. Code and a subset of the data are publicly available.

Langue: Anglais