http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Robust Three-step facial landmark localization under the complicated condition via ASM and POEM
( Weisheng Li ),( Lai Peng ),( Lifang Zhou ) 한국인터넷정보학회 2015 KSII Transactions on Internet and Information Syst Vol.9 No.9
To avoid influences caused by pose, illumination and facial expression variations, we propose a robust three-step algorithm based on ASM and POEM for facial landmark localization. Firstly, Model Selection Factor is utilized to achieve a pose-free initialized shape. Then, we use the global shape model of ASM to describe the whole face and the texture model POEM to adjust the position of each landmark. Thirdly, a second localization is presented to discriminatively refine the subtle shape variation for some organs and contours. Experiments are conducted in four main face datasets, and the results demonstrate that the proposed method accurately localizes facial landmarks and outperforms other state-of-the-art methods.
Near-infrared face recognition by fusion of E-GV-LBP and FKNN
( Weisheng Li ),( Lidou Wang ) 한국인터넷정보학회 2015 KSII Transactions on Internet and Information Syst Vol.9 No.1
To solve the problem of face recognition with complex changes and further improve the efficiency, a new near-infrared face recognition algorithm which fuses E-GV-LBP and FKNN algorithm is proposed. Firstly, it transforms near infrared face image by Gabor wavelet. Then, it extracts LBP coding feature that contains space, scale and direction information. Finally, this paper introduces an improved FKNN algorithm which is based on spatial domain. The proposed approach has brought face recognition more quickly and accurately. The experiment results show that the new algorithm has improved the recognition accuracy and computing time under the near-infrared light and other complex changes. In addition, this method can be used for face recognition under visible light as well.
Binary Hashing CNN Features for Action Recognition
( Weisheng Li ),( Chen Feng ),( Bin Xiao ),( Yanquan Chen ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.9
The purpose of this work is to solve the problem of representing an entire video using Convolutional Neural Network (CNN) features for human action recognition. Recently, due to insufficient GPU memory, it has been difficult to take the whole video as the input of the CNN for end-to-end learning. A typical method is to use sampled video frames as inputs and corresponding labels as supervision. One major issue of this popular approach is that the local samples may not contain the information indicated by the global labels and sufficient motion information. To address this issue, we propose a binary hashing method to enhance the local feature extractors. First, we extract the local features and aggregate them into global features using maximum/minimum pooling. Second, we use the binary hashing method to capture the motion features. Finally, we concatenate the hashing features with global features using different normalization methods to train the classifier. Experimental results on the JHMDB and MPII-Cooking datasets show that, for these new local features, binary hashing mapping on the sparsely sampled features led to significant performance improvements.
Robust human tracking via key face information
( Weisheng Li ),( Xinyi Li ),( Lifang Zhou ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.10
Tracking human body is an important problem in computer vision field. Tracking failures caused by occlusion can lead to wrong rectification of the target position. In this paper, a robust human tracking algorithm is proposed to address the problem of occlusion, rotation and improve the tracking accuracy. It is based on Tracking-Learning-Detection framework. The key auxiliary information is used in the framework which motivated by the fact that a tracking target is usually embedded in the context that provides useful information. First, face localization method is utilized to find key face location information. Second, the relative position relationship is established between the auxiliary information and the target location. With the relevant model, the key face information will get the current target position when a target has disappeared. Thus, the target can be stably tracked even when it is partially or fully occluded. Experiments are conducted in various challenging videos. In conjunction with online update, the results demonstrate that the proposed method outperforms the traditional TLD algorithm, and it has a relatively better tracking performance than other state-of-the-art methods.
Text Recognition in Mobile Images using Perspective Correction and Text Segmentation
Weisheng Wu,Jian Liu,Lei Li 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.10
It is significant that adopt text recognition at mobile devices to care human’s health. We observed that although OCR is very suit for recognizing scanned documents, it has poor performation on mobile photoes, which suffer from unequal lighting, clutter, skew, or poor image quality. Therefore, a new algorithm is proposed that take a series of measures to deal with these tough situations of mobile images. This work includes three main steps. Firstly we adopt perspective correction to rectify the distortion of an image. Secondly we use filter to further eliminate the effect of noisy in image. Finally we apply text segmentation to effective measure each text row of image. Compared to OCR text recogniztion success rate 34.7%, the success rate of our method is 65.8%. Experimental results show that the proposed algorithm greatly improves the accuracy of text recognition.
Weisheng Chen,Li Zhang 제어·로봇·시스템학회 2010 International Journal of Control, Automation, and Vol.8 No.2
First of all, an adaptive iterative learning control strategy is developed for a class of nonlinearly parameterized systems with two unknown time-varying parameters and one unknown time-varying delay. The proposed control law includes a PID-type feedback term in time domain and an adaptive learning term used to estimate the unknown time-varying vector in iteration domain. By constructing a Lyapunov-Krasovskii-like composite energy function, we prove the stability of the closed-loop system and the convergence of the tracking error. Then, the design idea is further extended to a broader class of systems with mixed parameters in which the unknown time-invariant vector is estimated by a PI-type learning law in time domain. The simulation results, for a time-delay chaotic system, confirm the effectiveness of the proposed control scheme.
Detecting small lung tumors in mouse models by refractive-index microradiology
Chien, Chia-Chi,Zhang, Guilin,Hwu, Y.,Liu, Ping,Yue, Weisheng,Sun, Jianqi,Li, Yan,Xue, Hongjie,Xu, Lisa X.,Wang, Chang Hai,Chen, Nanyow,Lu, Chien Hung,Lee, Ting-Kuo,Yang, Yuh-Cheng,Lu, Yen-Ta,Ching, Y Springer-Verlag 2011 ANALYTICAL AND BIOANALYTICAL CHEMISTRY Vol.401 No.3