The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
With emerging demand for large-scale video analysis, the Motion Picture Experts Group (MPEG) initiated the Compact Descriptor for Video Analysis (CDVA) standardization in 2014. In this work, we develop novel deep-learning features and incorporate them into the well-established CDVA evaluation framework to study its effectiveness in video analysis. In particular, we propose a Nested Invariance Pooling...
Driver's fatigue is one of the major causes of traffic accidents, particularly for drivers of large vehicles (such as buses and heavy trucks) due to prolonged driving periods and boredom in working conditions. In this paper, we propose a vision-based fatigue detection system for bus driver monitoring, which is easy and flexible for deployment in buses and large vehicles. The system consists of modules...
This paper summarizes the recent development of illumination compensation for face recognition. Then a new method is proposed by extracting illumination invariant features in contourlet transform domain based on human visual perception mechanism. The experimental results on Yale B and CMU PIE face databases demonstrate that it is effective and competitive.
From an observation on the joint distribution of similarity scores obtained by our proposed similarity calculation method, we propose a novel measurement for verifying the invalid testing images in face recognition. The new measurement shows improved performance over traditional residuals-based decision measurement and robustness to partial occlusion.
This paper firstly shows the entire picture of a promising research area, face recognition. Then a new face recognition method is proposed, mainly based on the combination of wavelet transform and local hybrid projection entropy (LHPE). Some classical image processing methods are included to constitute a cascade framework. The experimental results on Yale face database and Yale B face database show...
In previous works, we have applied the modified PUM method in face recognition and demonstrated the effectiveness of this method for deal with partial occlusion and distortion. Based on the similitude between the face features and iris features, this paper proposes a new method for person recognition by the combining of iris and face. This new method combines the iris and face features as a new feature...
Given uncertain status reports or notes come from multi-sensor, identity fusion further makes them integrate information and jointly determine the observed entities. This paper discusses an improved data fusion approach to multi-biometric feature, including face, fingerprint and iris image. The approach is called improved multiple biometric data fusion algorithm, based on the eigen-face and the Gabor...
This paper investigates the problem of face recognition with partially occluded images without assuming prior information about the distortion, and with only a single training image or a small number of training images for each class to be identified. A new approach is presented, which is an extension of our previous posterior union model. The new approach is formulated by using a similarity measure...
The posterior union decision-based neural network (PUD-BNN) has been proposed in our previous work for dealing with face recognition task subject to partial occlusion and distortion. However, one difficult of this method is inaccurate to model classes with only a single, or a small number of training samples. In this paper, we proposed an extern approach to tackle above problem by two strategies....
In this paper, we introduce a face recognition approach based on the contourlet transform and support vector machine, which takes technological advantages of both support vector machine and the contourlet transform for feature extraction. The contributions of this paper include the following aspects: (1) support vector machine is successfully applied to face recognition by using the contourlet transform...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.