IEEE Transactions on Pattern Analysis and Machine Intelligence · 1997 · 2.9K citations · 37 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionFace RecognitionFeature DetectionGraph-based LearningObject RecognitionPattern RecognitionSignal ProcessingFace Feature ExtractionFace IdentificationGraph-based Pattern RecognitionImage Feature ExtractionLabeled Graph RepresentationsPhase InformationRotationsWavelet Transform
The system differs from the preceding one (Lades et al., 1993) in three respects. We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled Gabor‑wavelet graphs, and new face images are extracted via elastic graph matching using phase‑based node positioning, object‑adapted graphs for depth rotation, and a novel bunch‑graph data structure, with similarity computed by a simple function.
We present a system for recognizing human faces from single images out of a large database containing one image per person. Faces are represented by labeled graphs, based on a Gabor wavelet transform. Image graphs of new faces are extracted by an elastic graph matching process and can be compared by a simple similarity function. The system differs from the preceding one (Lades et al., 1993) in three respects. Phase information is used for accurate node positioning. Object-adapted graphs are used to handle large rotations in depth. Image graph extraction is based on a novel data structure, the bunch graph, which is constructed from a small get of sample image graphs.
37
Matthew Turk, Alex Pentland · Journal of Cognitive Neuroscience · 1991 · 13.8K citations · Full text
Human and machine recognition of faces: a survey
Rama Chellappa, Charles L. Wilson, Saad Sirohey · Proceedings of the IEEE · 1995 · 2.5K citations