Biomedical subjects

Craig Chin

Publications and source records attributed to Craig Chin.

3 recordsLinked to original sources

PubMed2006

Biometric identification using 3D face scans.

Biometrics is an emerging area of bioengineering that pursues the characterization of a person by means of something that the person is or produces. Face recognition is a particularly attractive biometric challenge. Most of the face recognition research performed in the past used 2D intensity images. However, algorithms based on 2D images are not robust to changes of illumination in the environment or orientation of the subject. The ability to acquire 3D scans of human faces removes those ambiguities, since they capture the exact geometry of the subject, invariant to illumination and orientation changes. Unencumbered by those limitations, research in 3D face recognition is now beginning to address a different source of error in biometric recognition: facial geometry deformation caused by facial expressions, which can make 3D algorithms which treat 3D faces as rigid surfaces fail. In this paper, a 3D face recognition framework is proposed to tackle this problem. The framework is composed of three subsystems: expression recognition system, expressional face recognition system and neutral face recognition system. In particular, a system for the recognition of faces with one type of expression (smile) and neutral faces was implemented and tested on a database of 30 subjects. The results proved the feasibility of this framework.

Algorithms↗

PubMed2005

Hands-free human computer interaction via an electromyogram-based classification algorithm.

A four-electrode system for hands-free computer cursor control, based on the digital processing of Electromyogram (EMG) signals is proposed. The electrodes are located over the right frontalis, the procerus, the left temporalis and the right temporalis muscles in the head. This system is meant to enable individuals paralyzed from the neck down (e.g., due to Spinal Cord Injury) to interact with computers using point-and-click graphic interfaces. The intention is to translate electromyograms derived from muscle contractions associated with specific facial movements into five cursor actions, namely: Left, Right, Up, Down and Left-click. This translation is accomplished by a digital signal processing classification algorithm that takes advantage of the divergent spectral nature of the EMG signals produced by the frontalis, temporalis, and procerus muscles, respectively. The effectiveness of the algorithm is evaluated by comparing its performance to that of a previously developed three-electrode EMG-based algorithm, using Matlab simulations. The results indicate that the algorithm classifies with great accuracy and provides a marked improvement over the previous three-electrode system.

Algorithms↗

PubMed2005

User stress detection in human-computer interactions.

The emerging research area of Affective Computing seeks to advance the field of Human-Computer Interaction (HCI) by enabling computers to interact with users in ways appropriate to their affective states. Affect recognition, including the use of psychophysiologcal measures (e.g. heart rate), facial expressions, speech recognition etc. to derive an assessment of user affective state based on factors from the current task context, is an important foundation required for the development of Affective Computing. Our research focuses on the use of three physiological signals: Blood Volume Pulse (BVP), Galvanic Skin Response (GSR) and Pupil Diameter (PD), to automatically monitor the level of stress in computer users. This paper reports on the hardware and software instrumentation development and signal processing approach used to detect the stress level of a subject interacting with a computer, within the framework of a specific experimental task, which is called the 'Stroop Test'. For this experiment, a computer game was implemented and adapted to make the subject experience the Stroop Effect, evoked by the mismatch between the font color and the meaning of a certain word (name of a color) displayed, while his/her BVP, GSR and PD signals were continuously recorded. Several data processing techniques were applied to extract effective attributes of the stress level of the subjects throughout the experiment. Current results indicate that there exists interesting similarity among changes in those three signals and the shift in the emotional states when stress stimuli are applied to the interaction environment.

Adult↗