Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Symbol-relation grammars: a formalism for graphical languages
Information and Computation
A hidden markov model-based approach for face detection and recognition
A hidden markov model-based approach for face detection and recognition
Face recognition: A literature survey
ACM Computing Surveys (CSUR)
Robust Real-Time Face Detection
International Journal of Computer Vision
Ch OpenCV for interactive open architecture computer vision
Advances in Engineering Software
Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Learning Bayesian Networks
A stochastic grammar of images
Foundations and Trends® in Computer Graphics and Vision
Towards a general vision system based on symbol-relation grammars and Bayesian networks
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Object recognition based on visual grammars and Bayesian networks
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
| Hi-index | 0.00 |
Several methods have been developed for face detection with certain success, however these tend to fail under difficult conditions such as partial occlusions and changes in orientation and illumination. We propose a novel technique for face detection based on a visual grammar. We define a symbol relational grammar for faces, representing the visual elements of a face and their spatial relations. This grammar is transformed into a Bayesian network (BN) structure and its parameters are obtained from data, i.e., positive and negative examples of faces. Then the BN is used for face detection via probabilistic inference, using as evidence a set of weak detectors for different face components. We evaluated our method on a set of sample images of faces under difficult conditions, and contrasted it with a simplified model without relations, and the AdaBoost face detector. The results show a significant improvement when using our method.