SUMMARYThis paper describes a lipreading system using a color extraction method and several eigenspace techniques. To detect a precise mouth position, the system first finds the rough position of the mouth by the color extraction method and then determines the precise position using an eigentemplate technique. To describe the mouth shape change, we developed an eigen waveform technique. The detected precise mouth position improves the accuracy of the eigen waveform, which results in a high recognition rate. We constructed an automatic lipreading system and an experiment revealed that this system recognizes 85% of 35 words and 69% of 100 words.

Approach to speed control using temperature characteristics of ultrasonic motor ~~ 50 [Idlz] 1 10 [Vm,] 0.5 [kgf-cm] 1 .0 [W] 200 [rpml 1 .O [kgf-cm] 1 .O [kgf-cm] 263-328 IK1 Abstract-Ultrasonic motors have some special unique features, such as high-torque under low-speed operation, compact size, and no electromagnetic noise. Ultrasonic motors would be expected to apply an element of the artificial muscle. The driving principle of the ultrasonic motor is based on friction force between a rotor and a stator. Therefore, it is difficult to drive the ultrasonic motor at a constant speed, because the generation of heat by friction changes the friction force. In this study, we proposed speed controllers of the ultrasonic motor, considering the temperature rise of the ultrasonic motor. From the results, these methods were proved the most effective for the speed control of the ultrasonic motor in experiments.

No abstract

No abstract

A real-time monitoring method of heart rate (HR) from face images using Real-time Pulse Extraction Method (RPEM) is described and corroborated for the theoretical efficacy by investigating fundamental mechanisms through three kinds of experiments; (i) measurement of light reflection from face covered by copper film, (ii) spectroscopy measurement and (iii) simultaneous measurement of face images and laser speckle images. The investigation indicated the main causes of brightness change are both the green light absorption variation by the blood volume changes and the face surface reflection variation by pulsatory face movements. RPEM removes the motion noise from the green light absorption variation and the effectiveness is ensured by comparing with the pulse wave of the ear photoplethysmography. We also applied RPEM to continuous real-time HR monitoring of seven participants during office work under noncontrolled condition, and achieved HR measured rate of 44 % to the number of referential ECG beats while face is detected, with RMSE = 6.7 bpm as an average result of five days.