Face Recognition with Patterns of Oriented Edge Magnitudes

Vu, Ngoc-Son; Caplier, Alice

doi:10.1007/978-3-642-15549-9_23

Cited by 81 publications

(63 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GRADIANT system fuses 2 different face recognition systems: patterns of oriented edge magnitudes (POEM) [18] and Gabor jets (Gabor) [19] from a 10 × 10 regular grid using 40 Gabor wavelets with default parametrization [13]. After aligning the face images to 125×140 (POEM) or 85×100 (Gabor) pixels, an adaptation of the retina layer model [20] was used to preprocess them.…”

Section: Fusion Systemsmentioning

confidence: 99%

The 2013 face recognition evaluation in mobile environment

Günther

Costa‐Pazo

Ding

et al. 2013

2013 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

Automatic face recognition in unconstrained environments is a challenging task. To test current trends in face recognition algorithms, we organized an evaluation on face recognition in mobile environment. This paper presents the results of 8 different participants using two verification metrics. Most submitted algorithms rely on one or more of three types of features: local binary patterns, Gabor wavelet responses including Gabor phases, and color information. The best results are obtained from UNILJ-ALP, which fused several image representations and feature types, and UC-HU, which learns optimal features with a convolutional neural network. Additionally, we assess the usability of the algorithms in mobile devices with limited resources.

show abstract

Section: Fusion Systemsmentioning

confidence: 99%

The 2013 face recognition evaluation in mobile environment

Günther

Costa‐Pazo

Ding

et al. 2013

2013 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

show abstract

“…In an attempt in our work to seek the challenge of small pedestrians, the images have been cropped and scaled to 30 × 60 pixels. In [5], the patterns of oriented edge magnitude applied to face recognition show that the best performance is achieved with the number of bins m = 3, which is understandable since, in their application, the main characteristic of a feature vector is discriminability. On the other hand, in human detection, we need a robust model immune to noise with a rich shape description.…”

Section: Training and Results Discussionmentioning

confidence: 98%

“…Our approach is feature-based, inspired by [5], extractor [25]. The LBPs have shown to be efficient in texture classification [29] and face detection and recognition [27].…”

Section: Related Workmentioning

confidence: 99%

“…Against this background, we hereby introduce a novel method for pedestrian detection. Inspired by the patterns of oriented edge magnitudes introduced in [5], that is a spatial multi-resolution descriptor that captures rich information about the original image. It makes use of the gradient magnitude orientations, before applying the local binary patterns (LBP) operator.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Pedestrian Detector on Low-Resolution Images: Gradient LBP Using Patterns of Oriented Edges

Boudissa

Tan

Kim

et al. 2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper introduces a simple algorithm for pedestrian detection on low resolution images. The main objective is to create a successful means for real-time pedestrian detection. While the framework of the system consists of edge orientations combined with the local binary patterns (LBP) feature extractor, a novel way of selecting the threshold is introduced. Using the mean-variance of the background examples this threshold improves significantly the detection rate as well as the processing time. Furthermore, it makes the system robust to uniformly cluttered backgrounds, noise and light variations. The test data is the INRIA pedestrian dataset and for the classification, a support vector machine with a radial basis function (RBF) kernel is used. The system performs at state-of-the-art detection rates while being intuitive as well as very fast which leaves sufficient processing time for further operations such as tracking and danger estimation.

show abstract

“…Also, some successful LBP variants including Three-Patch based LBP (TPLBP), Four-Patch based LBP (FPLBP) [33], Patterns of Oriented Magnitude (POEM) [30] have been used recently for face recognition.…”

Section: Related Workmentioning

confidence: 99%

A complementary local feature descriptor for face identification

Choi

Schwartz

Guo

et al. 2012

2012 IEEE Workshop on the Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

In many descriptors, spatial intensity transforms are often packed into a histogram or encoded into binary strings to be insensitive to local misalignment and compact. Discriminative information, however, might be lost during the process as a trade-off. To capture the lost pixel-wise local information, we propose a new feature descriptor, Circular Center Symmetric-Pairs of Pixels (CCS-POP). It concatenates the symmetric pixel differences centered at a pixel position along various orientations with various radii; it is a generalized form of Local Binary Patterns, its variants and Pairs-of-Pixels (POP). Combining CCS-POP with existing descriptors achieves better face identification performance on FRGC Ver. 1.0 and FERET datasets compared to stateof-the-art approaches.

show abstract

Face Recognition with Patterns of Oriented Edge Magnitudes

Cited by 81 publications

References 18 publications

The 2013 face recognition evaluation in mobile environment

The 2013 face recognition evaluation in mobile environment

A Novel Pedestrian Detector on Low-Resolution Images: Gradient LBP Using Patterns of Oriented Edges

A complementary local feature descriptor for face identification

Contact Info

Product

Resources

About