Learning Descriptors Invariance Through Equivalence Relations Within Manifold: A New Approach to Expression Invariant 3D Face Recognition
This work addresses expression-invariant 3D face recognition, which is an incremental improvement for biometric security applications.
The paper tackles the problem of distinguishing identity from expression variations in 3D face recognition by learning descriptor variations through equivalence relations and graph embedding, resulting in enhanced recognition performance on datasets like FRGC v2.0, Bosphorus, and 3D TEC with considerable margins.
This paper presents a unique approach for the dichotomy between useful and adverse variations of key-point descriptors, namely the identity and the expression variations in the descriptor (feature) space. The descriptors variations are learned from training examples. Based on the labels of the training data, the equivalence relations among the descriptors are established. Both types of descriptor variations are represented by a graph embedded in the descriptor manifold. The invariant recognition is then conducted as a graph search problem. A heuristic graph search algorithm suitable for the recognition under this setup was devised. The proposed approach was tests on the FRGC v2.0, the Bosphorus and the 3D TEC datasets. It has shown to enhance the recognition performance, under expression variations in particular, by considerable margins.