Variance projection function and its application to eye detection for human face recognition

Feng, Guocan; Yuen, Pong C.

doi:10.1016/s0167-8655(98)00065-8

Cited by 144 publications

(60 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feng and Yuen [9] used intensity, the direction of the line joining the centers of the eyes, the response of convolving an eye variance filter with the face image, and the variance projection function (VPF) technique to detect eyes [10]. Zhou and Geng [11] extended the idea of VPF to the generalized projection function (GPF) and showed with experimental results that the hybrid projection function (HPF), a special case of GPF, is better than VPF and integral projection function (IPF) for eye detection.…”

Section: Previous Workmentioning

confidence: 99%

An Efficient Method for Eye Detection in Color Images using Morphological Operations

Moazzam¹,

Muntarina²,

Sultana³

et al. 2014

IJCA

View full text Add to dashboard Cite

This paper presents an efficient method for detecting human eye in a full frontal face color image. Eye regions are characterized by low illumination, high density edges and high contrast as compared to other parts in frontal face image. This method uses basic color image processing and morphological operation to detect eyes. Using color based training algorithm, this technique first extracts skin region of the input image. Then morphological operation is applied for detection of eye boundary and light source reflection of eye, also known as eye dot. It gives finite number of eye candidates from which noise is subsequently removed. For full frontal face images, this method is found highly efficient and accurate for eye detection.

show abstract

Section: Previous Workmentioning

confidence: 99%

An Efficient Method for Eye Detection in Color Images using Morphological Operations

Moazzam¹,

Muntarina²,

Sultana³

et al. 2014

IJCA

View full text Add to dashboard Cite

show abstract

“…In this paper principal component analysis (PCA), generalized projections (GP), and image moment methods and some variations of those algorithms, are implemented as feature selection algorithms of the analysis that follows. All of these meth-ods have been used previously in the context of gesture recognition [32,2,21,2,21,28,29,34,9,16,10,11]. However, there seems to be lack of direct, head-to-head comparisons between both feature selection techniques and statistical testing methods as a function of image resolution and pre-processing methods in the recognition field.…”

Section: Feature Selectionmentioning

confidence: 99%

Enhanced Gesture Recognition Performance through Improved Pre-Processing

Grosek¹,

Shi²,

Kutz³

2013

IJCA

View full text Add to dashboard Cite

Gesture recognition is analyzed on a set of static hand gestures in the context of designing robust, real-time pre-processing techniques for applications in hand-held electronics. A comparative case study that uses various combinations of algorithms across the steps of the recognition process is made, revealing the fact that many method combinations can produce highly accurate results, even at low resolutions, given the right kind of pre-processing. The pre-processing includes the hand segmentation and normalization done before feature extraction. Indeed, pre-processing has by far the greatest effect on the overall accuracy, robustness, and speed of the gesture recognition process, significantly outweighing the influence of feature-extraction and classification. Even at image resolutions as low as 8×8 pixels, accuracies of 99% are achieved using a simple PCA feature selection scheme and a LDA classification method. These results suggest the priority and advantages of focusing on developing robust and efficient pre-processing methods.

show abstract

“…To detect the eye corner, a variance project function (VPF) is employed [14]. This method is based on the observation that some eye landmarks such as eye corners have relatively high contrast which can be detected effectively by the VPF.…”

Section: B Eye Corner Detectionmentioning

confidence: 99%

Easy-setup eye movement recording system for human-computer interaction

Phung¹,

Trần²,

Hara³

et al. 2008

2008 IEEE International Conference on Research, Innovation and Vision for the Future in Computing and Communication Technologie

View full text Add to dashboard Cite

Abstract-Tracking the movement of human eyes is expected to yield natural and convenient applications based on humancomputer interaction (HCI). To implement an effective eyetracking system, eye movements must be recorded without placing any restriction on the user's behavior or user discomfort. This paper describes an eye movement recording system that offers free-head, simple configuration. It does not require the user to wear anything on her head, and she can move her head freely. Instead of using a computer, the system uses a visual digital signal processor (DSP) camera to detect the position of eye corner, the center of pupil and then calculate the eye movement. Evaluation tests show that the sampling rate of the system can be 300 Hz and the accuracy is about 1.8 .

show abstract

Variance projection function and its application to eye detection for human face recognition

Cited by 144 publications

References 22 publications

An Efficient Method for Eye Detection in Color Images using Morphological Operations

An Efficient Method for Eye Detection in Color Images using Morphological Operations

Enhanced Gesture Recognition Performance through Improved Pre-Processing

Easy-setup eye movement recording system for human-computer interaction

Contact Info

Product

Resources

About