Papers by Keyword: Face

Abstract: Emotions play an important role in human life. Extracting human emotions is important because it conveys nonverbal communication cues that play an important role in interpersonal relations. In recent years, facial emotion detection has received massive attention, and many businesses have already utilized this technology to get real-time analytics and feedback from customers to help their business grow. Currently, we have to manually find playlists according to our mood, and it's time-consuming and stressful. Therefore, this process is made automated and simple in this project by proposing a recommendation system for emotion recognition that is capable of detecting the users' emotions and suggesting playlists that can improve their mood. Implementation of the proposed recommender system is performed using Caffemodel to detect faces and the MLP Classifier to detect facial emotions based on the KDEF dataset.

Abstract: The purpose of multiple biometric fusion is to improve the recognition performance by utilizing their complementary. In this paper, the feature fusion recognition method of multi-view face and gait in video is studied, and a adaptive decision fusion method is proposed. The results showed that the adaptive fusion features carry the most discriminating power compared to any individual biometric and other static fusion rules like Max and Sum.

Abstract: Boosted features developed using face signatures in combination with Gentle Adaboost algorithm offer alternative features for face authentication and face recognition. Face signatures are face representations extracted from Trace transform and Gentle Adaboost is used to enhance the performance of the features extracted from the face signatures. In this paper, we demonstrate the usefulness of the constructed features with experiments on BANCA database.

Abstract: An efficient facial representation is a crucial step for successful and effective performance of cognitive tasks such as object recognition, fixation, facial recognition system, etc. This paper demonstrates the use of Gabor wavelets transform for efficient facial representation and recognition. Facial recognition is influenced by several factors such as shape, reflectance, pose, occlusion and illumination which make it even more difficult. Gabor wavelet transform is used for facial features vector construction due to its powerful representation of the behavior of receptive fields in human visual system (HVS). The method is based on selecting peaks (high-energized points) of the Gabor wavelet responses as feature points. This paper work introduces the use of Gabor wavelets transform for efficient facial representation and recognition. Compare to predefined graph nodes of elastic graph matching, the approach used in this paper has better representative capability for Gabor wavelets transform. The feature points are automatically extracted using the local characteristics of each individual face in order to decrease the effect of occluded features. Based on the experiment, the proposed method performs better compared to the graph matching and eigenface based methods. The feature points are automatically extracted using the local characteristics of each individual face in order to decrease the effect of occluded features. The proposed system is validated using four different face databases of ORL, FERRET, Purdue and Stirling database.

Abstract: Analyzing the defects of two-dimensional facial expression recognition algorithm, this paper proposes a new three-dimensional facial expression recognition algorithm. The algorithm is tested in JAFFE facial expression database. The results show that the proposed algorithm dynamically determines the size of the local neighborhood according to the manifold structure, effectively solves the problem of facial expression recognition, and has good recognition rate.

Abstract: The complex parts, like block engine or inside panel door, represent a real challenge for 3D modeling with modern parametric 3D CAD systems if we intend to reuse the modeling for future modifications. The complexity of the part generates a large number of parameters and parametrical dependencies that is difficult to manage and even difficult to change for modifying the part, often, for big changes, making it easier to remodeling the part from the beginning. In this paper is presented a new method of parametric and hierarchical 3D modeling that allows easy future modifications of the part. This paper also presents the implementation of this new method in Catia V5 and the validation for a number of CAD models.

Abstract: The research on monitoring and predicting drivers’ fatigue state has remarkable effect on prevention of traffic accidents, using the CCD image sensor camera as the image acquisition device of driver’s face and the 940nm infrared emitting diode as the light supplementary device and 3-points light supplementary had been utilized, the light supplementary system had been optimized by the experiment of infrared light supplementary which proceeded by means of combining the orthogonal experiment and expert fuzzy evaluation. The research result makes great sense to the monitoring of drivers’ fatigue state and traffic safety