Eye pupil localization with an ensemble of randomized trees

Markuš, Nenad; Frljak, Miroslav; Pandžić, Igor S.; Ahlberg, Jörgen; Forchheimer, Robert

doi:10.1016/j.patcog.2013.08.008

Cited by 90 publications

(72 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To handle scale variations without introducing prior information, we introduce a new voting space to better estimate the global maximum of the eye-pupil location by merging the Hough spaces resulting from each scale. In addition, we show that with a smaller set of trees than [17] we can obtain similar, or even better results. We also show that this method can be extended to different regression problems.…”

Section: Related Workmentioning

confidence: 66%

“…[17,21,22] present the most relevant methods where the main principle is to detect the face using the Viola Jones method [24], extract rough regions around the eyes using anthropomorphic relations then estimate the spatial position of the pupil on the image space.…”

Section: Related Workmentioning

confidence: 99%

“…Markus et al [17] ignore geometric assumptions, they use a machine-learning approach by training a cascaded ensembles of trees to learn the mapping between eyes images appearances and 2D pupil locations. Each ensemble processes a given scale i and represents the input of the following ensemble relative to the scale i − 1 up to the final output (the number of scales defines the number of ensembles).…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Real-time eye pupil localization using Hough regression forest

Kacete

Royan

Séguier

et al. 2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Eyes are one of the most salient features of the human face, and the location of the pupil allows access to important information which can be used in several computer vision applications. Several commercial eye-trackers can estimate with good accuracy the pupil location, but need complex hardware specifications and a controlled user environment (high eye image resolution, good illumination, small head pose variations) making these solutions difficult to use in an arbitrary environment. In this paper, we present an approach based on Hough randomized regression trees. We demonstrate, by several evaluations on challenging public datasets that our approach is very robust to illumination, scale, eye movements and high head pose variations and yields a significant improvement compared to a wide range of state-of-the-art methods..

show abstract

Section: Related Workmentioning

confidence: 66%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Real-time eye pupil localization using Hough regression forest

Kacete

Royan

Séguier

et al. 2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…Hansen et al [10] give a nice overview of current methods. On single still images there are fewer works and all are limited to frontal pose or need-calibrated settings [8,13].…”

Section: Prior Workmentioning

confidence: 99%

Pose Normalization for Eye Gaze Estimation and Facial Attribute Description from Still Images

Egger

Schönborn

Förster

et al. 2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Our goal is to obtain an eye gaze estimation and a face description based on attributes (e.g. glasses, beard or thick lips) from still images. An attribute-based face description reflects human vocabulary and is therefore adequate as face description. Head pose and eye gaze play an important role in human interaction and are a key element to extract interaction information from still images. Pose variation is a major challenge when analyzing them. Most current approaches for facial image analysis are not explicitly pose-invariant. To obtain a poseinvariant representation, we have to account the three dimensional nature of a face. A 3D Morphable Model (3DMM) of faces is used to obtain a dense 3D reconstruction of the face in the image. This Analysis-bySynthesis approach provides model parameters which contain an explicit face description and a dense model to image correspondence. However, the fit is restricted to the model space and cannot explain all variations. Our model only contains straight gaze directions and lacks high detail textural features. To overcome this limitations, we use the obtained correspondence in a discriminative approach. The dense correspondence is used to extract a pose-normalized version of the input image. The warped image contains all information from the original image and preserves gaze and detailed textural information. On the pose-normalized representation we train a regression function to obtain gaze estimation and attribute description. We provide results for pose-invariant gaze estimation on still images on the UUlm Head Pose and Gaze Database and attribute description on the Multi-PIE database. To the best of our knowledge, this is the first pose-invariant approach to estimate gaze from unconstrained still images.

show abstract

“…Next, they extend the method by using SIFT features for each pupil candidate and match such features with examples from a database before obtaining a final decision. The approach in [12] is based on an ensemble of randomized regression trees.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Robust Eye Gaze Estimation

Wiśniewska

Rezaei

Klette

2014

Computer Vision and Graphics

View full text Add to dashboard Cite

Abstract. Eye gaze detection under challenging lighting conditions is a non-trivial task. Pixel intensity and the shades around the eye region may change depending on the time of day, location, or due to artificial lighting. This paper introduces a lighting-adaptive solution for robust eye gaze detection. First, we propose a binarization and cropping technique to limit our region of interest. Then we develop a gradient-based method for eye-pupil detection; and finally, we introduce an adaptive eye-corner detection technique that altogether lead to robust eye gaze estimation. Experimental results show the outperformance of the proposed method compared with related techniques.

show abstract

Eye pupil localization with an ensemble of randomized trees

Cited by 90 publications

References 34 publications

Real-time eye pupil localization using Hough regression forest

Real-time eye pupil localization using Hough regression forest

Pose Normalization for Eye Gaze Estimation and Facial Attribute Description from Still Images

Robust Eye Gaze Estimation

Contact Info

Product

Resources

About