Abstract | ||
---|---|---|
A method of facial feature points extraction based on improved active appearance model (AAM) with Gabor wavelet features was presented in the paper. After the pre-processing of a standard face detector and lighting compensation, the paper proposed a hybrid AAM by combining the local skin similarity with the original local grey-level appearance model. Moreover, the feature points by the hybrid AAM and their neighbors were considered by a classification problem to further refine the results. Namely, the Gabor feature around the feature points was extracted, trained by linear discriminant analysis (LDA) and classified by K Nearest Neighbor (KNN) to give the precise location of the feature points. Experimental results indicated that facial feature points can be located robustly and precisely by the proposed method. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1016/j.engappai.2010.09.001 | Eng. Appl. of AI |
Keywords | Field | DocType |
feature point,knn,lda,local skin similarity,gabor feature,gabor wavelet feature,skin similarity model,robust facial feature point,hybrid aam,facial feature point,color image,facial feature points extraction,original local grey-level appearance,improved active appearance model,gabor wavelets,active appearance model,k nearest neighbor | k-nearest neighbors algorithm,Computer vision,Pattern recognition,Gabor wavelet,Feature (computer vision),Computer science,Active appearance model,Artificial intelligence,Linear discriminant analysis,Detector,Machine learning | Journal |
Volume | Issue | ISSN |
24 | 1 | Engineering Applications of Artificial Intelligence |
Citations | PageRank | References |
3 | 0.38 | 7 |
Authors | ||
4 |