Bundit Thipakorn

Learn More
This article describes a method of an off-line signature recognition by using parameterize Hough transform. From human nature, signatures are performed very fast by the person, and hence have a lot of straight-line segments within them. The faster that a person signs their name, the more straight lines will be present in their signature. To detect the(More)
This paper proposes a quantitative target approximation (qTA) model for simulating tone and intonation. Based on two theoretical models: the target approximation model (Y. Xu and Q.E. Wang, 2001) and the PENTA model (Y. Xu, 2005), the qTA model additionally incorporates several assumptions related to the underlying articulatory mechanisms, including (1)(More)
In this paper we report results of applying the quantitative target approximation model (qTA) [7] to simulate function-specific F0 contours in Mandarin. The qTA model is based on a set of assumptions about the biophysical and neural control mechanisms of pitch production. To simulate F0 contours for tone and focus, we extracted qTA parameters that are(More)
Our current understanding of how emotions are expressed in speech is still very limited. Part of the difficulty has been the lack of understanding of the underlying mechanisms. Here we report the findings of a somewhat unconventional investigation of emotional speech. Instead of looking for direct acoustic correlates of multiple emotions, we tested a(More)
During the interaction of a collaborative learning team, students usually participate in a variety of roles such as leader, follower and isolator, etc. These roles should be recognized and monitored carefully, especially the team leader, so that the collaboration might be engineered and supported appropriately. Identifying emergent leadership roles in a(More)
The classification of semantic human images is an active problem in interpreting multimedia images. Many researchers have attempted to improve the semantic model by using semantic action concepts. Although previous techniques, such as keyword definition and using content features of human action, have been applied, most results indicate that human images(More)