Decision Fusion for Patch-Based Face Recognition

Topcu, Berkay; Erdoğan, Hakan

doi:10.1109/icpr.2010.333

Cited by 16 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance in Table 2, 4, the performance of RS is low on Yale and PIE database which contain amount of local deformations such as facial expressions, glasses or no glasses, etc. To overcome this, local sub-region based methods were proposed such as the semi-random subspace (Semi-RS) [19] and the decision fusion for patch based method (DF) [15]. From Table 2 and Table 5, we can see that Semi-RS and DF outperform RS, respectively.…”

Section: Comparison With Existing Methodsmentioning

confidence: 99%

“…An early attempt [8] divided each face image into six elliptical sub-regions and learned a local probabilistic model for recognition. Topcu et al [15] proposed an alternative way of partitioning face regions into equal-sized small patches. Features extracted from each patch are classified separately and the recognition results are combined by a weighted sum rule.…”

Section: Ensemble Learning For Sss Face Recognitionmentioning

confidence: 99%

“…The SSS face recognition is conducted on all databases compared with four typical methods including: decision-tree based ensemble (DT) [14], random subspace method (RS) [16], semirandom subspace method (Semi-RS) [19], and the decision fusion for patch based method (DF) [15]. We implemented DT and RS ourselves and tuned the best performance for a fair comparison.…”

Section: Experimental Settingmentioning

confidence: 99%

“…We implemented DT and RS ourselves and tuned the best performance for a fair comparison. Recognition results of Semi-RS and DF on part of databases are referred to [19], [15] directly. For SSS problem, a random subset with p images per subject is taken with labels to form the training set.…”

Section: Experimental Settingmentioning

confidence: 99%

“…According to the definition of base classifiers, existing ensemble methods are mainly classified into three categories: (1) decision tree based ensemble [6,17]; (2) random subspace, semi-random subspace [16,19]; (3) image partitioning based sub-pattern ensemble [7,8,15].…”

Section: Ensemble Learning For Sss Face Recognitionmentioning

confidence: 99%

See 4 more Smart Citations

Small Sample Size Face Recognition using Random Quad-Tree based Ensemble Algorithm

Zhang¹,

Liang²,

Matsuyama³

2013

5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013)

View full text Add to dashboard Cite

Certain applications such as person re-identification in camera network, surveillance photo verification, forensic identification etc. suffer from a small sample size (SSS) problem severely. Conventional face recognition methods face a great challenge on SSS as the trained feature space is overfitted to the small training set. Interest in combination of multiple base classifiers to solve the SSS problem has sparked renewed research efforts in ensemble methods. In this paper, we propose a novel Random Quad-Tree based ensemble algorithm (R-QT) to address the SSS problem. In contrast to other methods confining the ideas on limited data, R-QT enlarges the training data to obtain more diverse base classifiers. Moreover, R-QT encodes not only discriminant features but also the geometric information across the face region, which further improves the recognition accuracy. Results on five standard face databases demonstrate the effectiveness of the proposed method.

show abstract

Section: Comparison With Existing Methodsmentioning

confidence: 99%

Section: Ensemble Learning For Sss Face Recognitionmentioning

confidence: 99%

Section: Experimental Settingmentioning

confidence: 99%

Section: Experimental Settingmentioning

confidence: 99%

Section: Ensemble Learning For Sss Face Recognitionmentioning

confidence: 99%

See 3 more Smart Citations

Small Sample Size Face Recognition using Random Quad-Tree based Ensemble Algorithm

Zhang¹,

Liang²,

Matsuyama³

2013

5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013)

View full text Add to dashboard Cite

show abstract

Performance Evaluation of Weighted Entropy Based Fusion Technique for Face Recognition with Different Pre-processing Techniques

Raghavan

Ahmadi

2021

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

On the Effects of Illumination Normalization with LBP-Based Watchlist Screening

Amara

Granger

Hadid

2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. Still-to-video face recognition (FR) is an important function in several video surveillance applications like watchlist screening, where faces captured over a network of video cameras are matched against reference stills belonging to target individuals. Screening of faces against a watchlist is a challenging problem due to variations in capturing conditions (e.g., pose and illumination), to camera inter-operability, and to the limited number of reference stills. In holistic approaches to FR, Local Binary Pattern (LBP) descriptors are often considered to represent facial captures and reference stills. Despite their efficiency, LBP descriptors are known as being sensitive to illumination changes. In this paper, the performance of still-to-video FR is compared when different passive illumination normalization techniques are applied prior to LBP feature extraction. This study focuses on representative retinex, self-quotient, diffusion, filtering, means de-noising, retina, wavelet and frequency-based techniques that are suitable for fast and accurate face screening. Experimental results obtained with videos from the Chokepoint dataset indicate that, although Multi-Scale Weberfaces and Tan and Triggs techniques tend to outperform others, the benefits of these techniques varies considerably according to the individual and illumination conditions. Results suggest that a combination of these techniques should be selected dynamically based on changing capture conditions.

show abstract

Decision Fusion for Patch-Based Face Recognition

Cited by 16 publications

References 12 publications

Small Sample Size Face Recognition using Random Quad-Tree based Ensemble Algorithm

Small Sample Size Face Recognition using Random Quad-Tree based Ensemble Algorithm

Performance Evaluation of Weighted Entropy Based Fusion Technique for Face Recognition with Different Pre-processing Techniques

On the Effects of Illumination Normalization with LBP-Based Watchlist Screening

Contact Info

Product

Resources

About