Browsing by Author "Chou, Kuan-Yu"

Now showing 1 - 4 of 4

Face Recognition Based on Sparse Representation Applied to Mobile Device
(2014)
Chou, Kuan-Yu
;
Huang, Guan-Ming
;
Tseng, Hao-Chien
;
Chen, Yon-Ping
;
電控工程研究所
This paper develops an Android face recognition application for users on mobile device, and applies it in the face verification system of Samsung Galaxy SII smart phone. The developed face recognition application includes three parts, the face detection using the Viola-Jones face detection program, the feature extraction implemented by the eigenface features, and the face recognition based on the sparse representation of L2 norm minimization. Different to general learning methods, the developed application does not require a tremendous amount of time in data training and can achieve a high recognition rate even higher than 99%, for examples 99.2% for the Sheffield face database, 99.4% for the Cohn-Kanade face database and 96.5% for ORL face database. Finally, the face verification application proposed for the Samsung Galaxy SII smart phone indeed successfully verifies a face just in one second which makes it a real-time application.
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning
(2019-11-01)
Chou, Kuan-Yu
;
Yang, Shu-Ting
;
Chen, Yon-Ping
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The maximum power point tracking (MPPT) technique is often used in photovoltaic (PV) systems to extract the maximum power in various environmental conditions. The perturbation and observation (P&O) method is one of the most well-known MPPT methods; however, it may face problems of large oscillations around maximum power point (MPP) or low-tracking efficiency. In this paper, two reinforcement learning-based maximum power point tracking (RL MPPT) methods are proposed by the use of the Q-learning algorithm. One constructs the Q-table and the other adopts the Q-network. These two proposed methods do not require the information of an actual PV module in advance and can track the MPP through offline training in two phases, the learning phase and the tracking phase. From the experimental results, both the reinforcement learning-based Q-table maximum power point tracking (RL-QT MPPT) and the reinforcement learning-based Q-network maximum power point tracking (RL-QN MPPT) methods have smaller ripples and faster tracking speeds when compared with the P&O method. In addition, for these two proposed methods, the RL-QT MPPT method performs with smaller oscillation and the RL-QN MPPT method achieves higher average power.
Multi-task Cascaded and Densely Connected Convolutional Networks Applied to Human Face Detection and Facial Expression Recognition System
(2019-01-01)
Chou, Kuan-Yu
;
Cheng, Yi-Wen
;
Chen, Wei-Ren
;
Chen, Yon-Ping
;
電控工程研究所
Face detection and recognition is an important issue and a difficult task in computer vision and human-computer interaction. Recently, with the development of deep learning, several related technologies have been proposed for face detection and facial expression recognition (FER), and the outstanding convolutional neural networks are the most common used in this field. This thesis applies the multi-task cascade convolutional neural network to face detection, and then designs the real-time FER system based on densely connected convolution network (DenseNet). The system first scales the input image to an image pyramid, and then uses the hierarchical network to determine whether a candidate window includes a human face. If a face exists, then send the candidate window to the FER system. Since DenseNet possesses the property of feature reuse, it can effectively reduce the amount of parameters and computation efforts, beneficial to develop the real-time system. In order to capture the variation of facial muscle in different expressions, this architecture adopts convolution operations with a stride 1 and tries different numbers of dense blocks. Through experiments, the proposed system can achieve real-time recognition in 30FPS and with recognition accuracy better than human eyes.
Real-Time Fingerspelling Recognition System Design Based on RGB-D Image Information
(2014)
Chou, Kuan-Yu
;
Chuang, Hui-Chi
;
Chiu, Meng-Tzu
;
Chen, Yon-Ping
;
電控工程研究所
This paper provides a fingerspelling recognition system with high accuracy rate based on RGB-D image. The system are separated into three parts, including hand region detection, hand feature extraction, and fingerspelling recognition. For the hand regions detection, the regions of hand and face are first obtained by skin color detection and connect component labeling (CCL), and then the hand, the region-of-interest (ROI), is determined by the feature point extraction based on distance transform. Followed is the hand feature extraction which consists of the hand structure and the hand texture. From the feature points of ROI, the locations of palm and fingertips, palm direction, and finger vectors are formed as the hand structure. In addition to the hand structure, this paper adopts the LBP operator to generate the hand texture to deal with the fingerspelling not recognizable by the hand structure. Finally, the extracted hand features are sent into the fingerspelling recognition system, which is built with several different neural network classifiers. The experimental results show that this system is an effective real-time recognition system whose accuracy is higher than 80% for most of the fingerspelling in American Sign Language (ASL).