Paper Info
Title
Drowsiness Recognition Using the Least Correlated LBPH
Abstract
In recent years, the drowsiness recognition is widely applied to the driver alerting or distance learning. The drowsiness recognition system is constructed on the basis of the recognition of eye states. The conventional methods for recognizing the eye states are often influenced by the illumination variations or hair/glasses occlusion. In this paper, we propose a new image feature called "least correlated LBP histogram (LC-LBPH)" to generate a high discriminate image features for recognizing the eye states robustly. Then, the method of independent component analysis (ICA) is applied to derive the low-dimensional and statistical independent feature vectors. Finally, support vector machines (SVM) are trained to recognize the eye states. Furthermore, we design four rules to classify three eye transition patterns which define the normal (consciousness), drowsiness, and sleeping situations. Experimental results show that the eye-state recognition rate is about 0.08 seconds per frame and the drowsiness recognition accuracy approaches 98%.
Year
DOI
Venue
2012
10.1109/IIH-MSP.2012.44
IIH-MSP
Keywords
Field
DocType
driver alerting,eye,sleeping situations,statistical independent feature vector,illumination variations,new image feature,eye-state recognition rate,high discriminate image feature,lc-lbph,drowsiness recognition,svm,drowsiness recognition system,lbph,independent component analysis,eye state,eye transition pattern,correlated lbph,feature extraction,image classification,support vector machine,hair-glasses occlusion,normal situations,eye states recognition,object recognition,drowsiness recognition accuracy approach,distance learning,low-dimensional feature vectors,high discriminate image features,least correlated lbp histogram,statistical independent feature vectors,ica,light,support vector machines,correlation methods,least correlated lbph,eye transition pattern classification,vectors,face recognition,iris recognition,image recognition,accuracy
Computer vision,Iris recognition,Facial recognition system,Feature vector,Pattern recognition,Computer science,Feature (computer vision),Support vector machine,Feature extraction,Artificial intelligence,Contextual image classification,Cognitive neuroscience of visual object recognition
Conference
ISBN
Citations 
PageRank 
978-1-4673-1741-2
0
0.34
References 
Authors
6
2
Name
Order
Citations
PageRank
Cheng-Chang Lien112813.15
Peirong Lin211.04