Learning to identify and track faces in image sequences

Edwards, Gillian; Taylor, Chris; Cootes, T. F.

doi:10.1109/iccv.1998.710737

Cited by 37 publications

(32 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Methods for detecting the eyes include the use of gradient flow fields [37], color-based techniques for detection of the eye sclera [5], horizontal gradient maps of a skin-colored region [48,51], and pupil detection using infrared or other special lighting [2,31,40,54]. References [1,7,13,17,18,21,38,40,50] explain various face and head tracking techniques previously employed. Temporal differencing is often used to segment moving regions of interest from a stable background [15,16].…”

Section: Introductionmentioning

confidence: 99%

Communication via eye blinks and eyebrow raises: video-based human-computer interfaces

Grauman

Betke

Lombardi

et al. 2003

Universal Access in the Information Society

154

100

View full text Add to dashboard Cite

Abstract. Two video-based human-computer interaction tools are introduced that can activate a binary switch and issue a selection command. "BlinkLink," as the first tool is called, automatically detects a user's eye blinks and accurately measures their durations. The system is intended to provide an alternate input modality to allow people with severe disabilities to access a computer. Voluntary long blinks trigger mouse clicks, while involuntary short blinks are ignored. The system enables communication using "blink patterns:" sequences of long and short blinks which are interpreted as semiotic messages. The second tool, "EyebrowClicker," automatically detects when a user raises his or her eyebrows and then triggers a mouse click. Both systems can initialize themselves, track the eyes at frame rate, and recover in the event of errors. No special lighting is required. The systems have been tested with interactive games and a spelling program. Results demonstrate overall detection accuracy of 95.6% for BlinkLink and 89.0% for EyebrowClicker.

show abstract

Section: Introductionmentioning

confidence: 99%

Communication via eye blinks and eyebrow raises: video-based human-computer interfaces

Grauman

Betke

Lombardi

et al. 2003

Universal Access in the Information Society

154

100

View full text Add to dashboard Cite

show abstract

“…For example, the appearance of a long-nosed person varies with pose change in a different way to the appearance of a short-nosed person. Edwards et al [4] showed that this second order effect appeared as a linear correlation between the identity and non-identity parameters during tracking. Given enough measurements (greater than the number of parameters) from a sequence, multivariate linear regression allows the identity parameters, d to be explained as a constant 'corrected' identity dC plus some confounding information caused by the variation in non-identity parameters:…”

Section: Tracking Schemementioning

confidence: 99%

“…This provides the basis for a principled method of integrating evidence of identity over a sequence. A further enhancement [4,13,14] exploits the knowledge that identity must be fixed over a sequence, leading to a tracking and identification scheme based on independent Kalman Filtering of the identity and non-identity components of a video sequence.…”

Section: Introductionmentioning

confidence: 99%

Improving Indentification Performance by Integrating Evidence From Evidence

Park¹,

Kim²,

Cheong³

2016

The Journal of Korea Institute of Information, Electronics, and

View full text Add to dashboard Cite

We present a quantitative evaluation of an algorithm for model-based face recognition. The algorithm actively learns how individual faces vary through video sequences, providing on-line suppression of confounding factors such as expression, lighting and pose. By actively decoupling sources of image variation, the algorithm provides a framework in which identity evidence can be integrated over a sequence. We demonstrate that face recognition can be considerably improved by the analysis of video sequences. The method presented is widely applicable in many multi-class interpretation problems.

show abstract

“…After training phase of this method with 40 images, it is able to locate 35 faces in 40 test images. The ASM approach has also been extended with two Kalman filters to estimate the shape-free intensity parameters and to track faces in image sequences [13].…”

Section: Researches Using This Approachmentioning

confidence: 99%

“…This does not present a problem for authentication applications with the constraint that a human face must be in an upright position. However, in order to be widely applicable to photo albums [13] and automatic video management systems [14], eye detection methods must be able to detect human eyes even in rotated faces.…”

Section: Support Vector Machinesmentioning

confidence: 99%