Browsing by Author "Kao, Wen-Chung"

Now showing 1 - 3 of 3

Adaptive feature selection for real-time face recognition in portable surveillance systems
(2007)
Kao, Wen-Chung
;
Shen, Chia-Ping
;
Kao, Chih-Chung
;
Hsu, Ming-Chai
;
Wu, Hung-Hsin
Real-time face recognition is a necessary feature in advanced portable surveillance systems. However, the high complexity of available algorithms to objects segmentation and recognition makes it impossible to include such a feature into a portable device. In this paper, we aim at designing a portable surveillance system which can take MPEG audio/video currently with recognizing human faces based on a digital camera platform. The proposed flow fully utilizes the available intermediate data passing from standard video compression flow in a digital camera. An efficient face recognition approach based on adaptive feature extraction and support vector machines (SVMs) are proposed to address the performance issues. The experimental result shows that the recognition speed running on a commercial digital camera platform can achieve 1.216 seconds/frame.
Live Demonstration: An FPGA-Based Continuous Wave Diffuse Optical Tomography System
(2012)
Kang, Shih
;
Wu, Shih-Yang
;
Cheng, Ching-Ju
;
Fang, Wai-Chi
;
Kao, Wen-Chung
This work provides an FPGA-based continuous wave diffuse optical tomography (CW-DOT) system for tumor detection and oxygen concentration measurement. According to user's parameter setting, the proposed system can solve image reconstruction of absorption coefficient at the wavelengths of 735nm and 890nm in analytes, and oxygen concentration through the proposed image reconstruction engine in real-time. Meanwhile, the reconstruction image will be wirelessly transmitted to a remote platform for image display. Also, the whole system comprises front-end circuit for analog data acquiring, digital signal processing and an image display platform as a prototype of a healthcare monitory system.
The new hyperspectral microscopic system for cancer diagnosis
(2011-01-01)
Hsieh, Yao-Fang
;
Mang, Ou-Yang
;
Chiou, Jin-Chern
;
Lin, Yung-Jiun
;
Tsai, Ming-Hsui
Until now, the cancer was examined by diagnosing the pathological changes of tumor. If the examination of cancer can diagnose the tumor before the cell occur the pathological changes, the cure rate of cancer will increase. This research develops a human-machine interface for hyper-spectral microscope. The hyper-spectral microscope can scan the specific area of cell and records the data of spectrum and intensity. These data is helpful to diagnose tumor. This research aims to develop a new system and a human-machine interface to control the hyper-spectral microscope. The interface can control the moving speed of motor, the exposure-time of hyper-spectrum, real-time focus, image of fluorescence, and record the data of spectral intensity and position.