Enhancing 3D-Air Signature by Pen Tip Tail Trajectory Awareness: Dataset and Featuring by Novel Spatio-temporal CNN
This work addresses authentication security through air signatures, but appears incremental as it builds on existing 3D trajectory methods with a new dataset and CNN architecture.
The researchers tackled the problem of 3D air signature recognition by developing a new pen tool and stereo camera system to capture pen tip and tail trajectories, and proposed a novel 2D spatio-temporal CNN called SliT-CNN for feature extraction. They collected a dataset from 45 signers with skilled forgeries, and benchmarking showed their method's effectiveness, though specific accuracy numbers were not provided in the abstract.
This work proposes a novel process of using pen tip and tail 3D trajectory for air signature. To acquire the trajectories we developed a new pen tool and a stereo camera was used. We proposed SliT-CNN, a novel 2D spatial-temporal convolutional neural network (CNN) for better featuring of the air signature. In addition, we also collected an air signature dataset from $45$ signers. Skilled forgery signatures per user are also collected. A detailed benchmarking of the proposed dataset using existing techniques and proposed CNN on existing and proposed dataset exhibit the effectiveness of our methodology.