Non-touch HCI using Motion gesture

Kinec, RGB-D, Leap motion etc sensor based non-touch human computer interaction interface development. The aim of this research is to identify the human body and hand gesture for understanding the gesture command and non-touch input for computer or robot. Dynamic gesture recognition will be done by gesture feature extraction and machine learning models.

Show more

Parkinson’s Disease Diagnosis

Quantities and reliable kinematic feature extraction for Parkinson’s disease diagnosis using pen-tablet. The purpose of this study is to establish a technological infrastructure with feature extraction and identification algorithm development to generate quantitative, reliable and reasonable evaluation index by utilizing sensor technology, data science and machine learning technology to evaluate cognitive and motor symptoms of neurological diseases.

Show more

Human Activity recognition

Smart watch sensor based human daily movement and motor activity recognition for monitoring the health condition. The aim of this study is to develop machine learning based activity and movement condition recognition using low cost and comfortable data accusation process using smartphone. The collected data will be analyzed for detecting the body abnormality condition for different disease.

Show more

Our mission and vision

Human Gesture and Activity Pattern Processing for HCI (Human Computer Interaction)

Pattern Recognition, Human Computer Interaction, Computer Vision, Image Processing, Machine Intelligence, His research interests include pattern recognition, character recognition, image processing, and computer vision. He is currently researching the following advanced fields: pen-based interaction system, real-time system, oriental character processing, mobile computing, computer education, human recognition, and machine intelligence.