Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers
DOI: 10.1109/acssc.1994.471664
|View full text |Cite
|
Sign up to set email alerts
|

Face locating and tracking for human-computer interaction

Abstract: E ective Human-to-Human communication involves both auditory and visual modalities, providing robustness and naturalness in realistic communication situations. Recent e orts at our lab are aimed at providing such multimodal capabilities for humanmachine communication. Most of the visual modalities require a stable image of a speaker's face. In this paper we propose a connectionist face t r acker that manipulates camera orientation and zoom, to kee p a p erson's face l o c ated at all times. The system operates… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
37
0
1

Publication Types

Select...
4
3
3

Relationship

0
10

Authors

Journals

citations
Cited by 73 publications
(38 citation statements)
references
References 1 publication
0
37
0
1
Order By: Relevance
“…The second type of solutions, which contains image-based methods, is based on scanning the image through a window to find the face candidates. The methods in this category generally use template matching, support vector machines (SVM), or neural networks [13,17]. Image-based methods are popular in tracking due to their robustness.…”
Section: Related Workmentioning
confidence: 99%
“…The second type of solutions, which contains image-based methods, is based on scanning the image through a window to find the face candidates. The methods in this category generally use template matching, support vector machines (SVM), or neural networks [13,17]. Image-based methods are popular in tracking due to their robustness.…”
Section: Related Workmentioning
confidence: 99%
“…In critical care patients there is the possibility of paler skin due to their severe illness. However, measurements have shown that paler skin has almost the same chromaticity as yellowish or dark skin [34][35][36] thus presenting no further significant difficulty. Skin can also show up more white than usual due to changes in light, but this effect is normalized out by taking colour ratios and is shown to have minimal effect on skin detection [36][37][38].…”
Section: Skin Recognitionmentioning
confidence: 99%
“…To find robots in a camera image, our approach first filters the image using Gaussian color filters tuned to the colors of the markers (see e.g., [34]). The center of the colors are then obtained by local smoothing, and thresholding is applied to determine whether or not a robot can be seen in the image.…”
Section: Detectionmentioning
confidence: 99%