Abstract | ||
---|---|---|
In this paper, a multi-stage face detection method using hybrid neural networks is presented. The method consists of three stages: preprocessing, feature extraction and pattern classification. We introduce an adaptive filtering technique which is based on a skin-color analysis using fuzzy min-max(FMM) neural networks. A modified convolutional neural network(CNN) is used to extract translation invariant feature maps for face detection. We present an extended version of fuzzy min-max (FMM) neural network which can be used not only for feature analysis but also for pattern classification. Two kinds of relevance factors between features and pattern classes are defined to analyze the saliency of features. These measures can be utilized to select more relevant features for the skin-color filtering process as well as the face detection process. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11816102_76 | ICIC |
Keywords | Field | DocType |
face detection,hybrid neural network,feature analysis,feature extraction,neural network,fuzzy min-max,pattern classification,face detection process,multi-stage face detection method,robust real-time face detection,modified convolutional neural network,adaptive filter,real time | Pattern recognition,Feature (computer vision),Computer science,Convolutional neural network,Fuzzy logic,Feature extraction,Time delay neural network,Artificial intelligence,Face detection,Artificial neural network,Machine learning,Pattern recognition (psychology) | Conference |
Volume | ISSN | ISBN |
4115 | 0302-9743 | 3-540-37277-6 |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ho-Joon Kim | 1 | 41 | 6.48 |
Juho Lee | 2 | 8 | 1.82 |
Hyun-Seung Yang | 3 | 49 | 6.48 |