Browsing by Author "Hong, Jung-Wei"

Now showing 1 - 3 of 3

A fast learning algorithm for robotic emotion recognition
(2007)
Hong, Jung-Wei
;
Han, Meng-Ju
;
Song, Kai-Tai
;
Chang, Fuh-Yu
;
電控工程研究所
The capability of robotic emotion recognition is an important factor for human-robot interaction. In order to facilitate a robot to function in daily live environments, a emotion recognition system needs to accommodate itself to various persons. In this paper, an emotion recognition system that can adapt to new facial data is proposed. The main idea of the proposed learning algorithm is to adjust parameters of SVM hyperplane for learning emotional expressions of a new face. After mapping the input space to Gaussian-kernel space, support vector pursuit learning (SVPL) is applied to retrain the hyperplane in the new feature space. To expedite the retraining procedure, only samples classified incorrectly in previous iteration are combined with critical historical sets to restrain a new SVM classifier. After adjusting hyperplane parameters, the new classifier will recognize previous erroneous facial data. Experimental results show that the proposed system recognize new facial data with high correction rates after fast retraining the hyperplane. Moreover, the proposed method also keeps satisfactory recognition rate of old facial samples.
Development of the Robot of Living Aid: RoLA
(2008)
Song, Kai-Tai
;
Tsai, Chi-Yi
;
Huang, Fu-Sheng
;
Hong, Jung-Wei
;
Lin, Chen-Yang
With increasing number of aging people, taking care of the elderly will become more and more important for future society, especially for those elderly living alone. This paper presents an autonomous mobile robot Rola (Robot of LivingAid), which can handle certain emergency conditions in a home setting to help the elderly through multi-modal sensing and control functions. The implemented functions include visual tracking, video transmission, location aware, navigation, body pose recognition and emergency call out. Rola can accommodate smoothly to the movement of a user through face tracking and performs robot-assisted video conferencing. Rola follows the elderly in the living room using the developed RF-based location aware system. It avoids obstacles in a narrow space employing a laser scanner. Further, Rola can help the elderly as he/she falls down at home. This accidental situation can be detected with a tri-axial accelerometer mounted on the waist of the elderly. It approaches to the elderly by the help of location-aware system and provides timely help through automatic call out and wireless video transmission.
Online learning design of an image-based facial expression recognition system
(2010-07-01)
Song, Kai-Tai
;
Han, Meng-Ju
;
Hong, Jung-Wei
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In order to serve people and support them in daily life, a domestic or service robot needs to accommodate itself to various individuals. Emotional and intelligent human-robot interaction plays an important role for a robot to gain attention of its users. Facial expression recognition is a key factor in interactive robotic applications. In this paper, an image-based facial expression recognition system that adapts online to a new face is proposed. The main idea of the proposed learning algorithm is to adjust parameters of the support vector machine (SVM) hyperplane for learning facial expressions of a new face. After mapping the input space to Gaussian-kernel space, support vector pursuit learning (SVPL) is employed to retrain the hyperplane in the new feature space. To expedite the retraining step, we propose to retrain a new SVM classifier by using only samples classified incorrectly in previous iteration in combination with critical historical sets. After adjusting the hyperplane parameters, the new classifier will recognize more effectively previous unrecognizable facial datasets. Experiments of using an embedded imaging system show that the proposed system recognizes new facial datasets with a recognition rate of 92.7%. Furthermore, it also maintains a satisfactory recognition rate of 82.6% of old facial samples.