Multisensor biometric evidence fusion of face and palmprint for person authentication using Particle Swarm Optimisation (PSO)

Raghavendra, R.; Rao, Ashok; Kumar, G. Hemantha

doi:10.1504/ijbm.2010.030414

Cited by 14 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We then discuss the efficacy of the proposed scheme against state-of-the-art scheme mentioned in [4], [2], [11], [7] and [1]. Finally, comparison of different level of fusions like sensor level fusion proposed in [12], match score level fusion proposed in [1] [13] are also presented.…”

Section: Resultsmentioning

confidence: 99%

“…In case of match score level fusion, a weighted SUM rule [1] is employed by considering its outstanding performance and weights are computed as mentioned in [13] by considering its robustness in assigning the weights for match scores. In case of sensor level fusion, we employ the most recent scheme for combining the face and palmprint at sensor level as mentioned in [12]. From Figure 4 and Table III it can be noted that, feature level fusion outperforms other level's of fusion by showing a improvement of 6%.…”

Section: Resultsmentioning

confidence: 99%

“…We conduct extensive experiments on a multimodal biometric database [1] of 250 users to prove the efficacy of the proposed scheme. Further, we also compare the proposed scheme with state-of-the-art feature fusion schemes mentioned in [4], [2], [11], [7], [1] and also with two different level of fusions like sensor level fusion [12] and match score level fusion [13]. The comparative performance of the proposed scheme against all other schemes are presented in terms of verification and statically validated with 90% confidence interval.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PSO Based Framework for Weighted Feature Level Fusion of Face and Palmprint

Raghavendra¹

2012

2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing

Self Cite

View full text Add to dashboard Cite

The multimodal biometric systems are gaining popularity because of accurate and reliable identification of the person. In this paper, we present a novel weighting scheme using variants of Particle Swarm Optimization (PSO) for efficient feature level fusion of face and palmprint. The face and palmprint images are represented using Log Gabor features which are then concatenated to form a fused feature vector space. We first employ floating PSO to compute the weights for each of these features qualitatively; then, binary PSO is employed to select the most discriminant features from fused feature space. Extensive experiments are carried out on a multimodal biometric database of 250 users. We compare the proposed scheme with available state-of-the-art feature level fusion schemes. Further, we also the present a comparative analysis of three widely used levels of fusion like sensor, feature and match score level. The experimental results show that the proposed scheme outperforms the state-of-the-art schemes.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PSO Based Framework for Weighted Feature Level Fusion of Face and Palmprint

Raghavendra¹

2012

2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this section, we experimentally evaluate the performance of SA-LFDA and other dimensionality reduction methods on a typical image classification task-face recognition (Guan and Zhuang, 2011;Bartkowiak, 2010;Raghavendra and Rao, 2010;Rani et al, 2008).…”

Section: Methodsmentioning

confidence: 99%

Self-adaptive local Fisher discriminant analysis for semi-supervised image recognition

Wang

Jia-ju

et al. 2012

IJBM

View full text Add to dashboard Cite

In this paper, we present a self-adaptive semi-supervised dimension reduction framework for image class recognition. Compared with the Semi-supervised Local Fisher Discriminant Analysis (SELF), whose classification performance is significantly influenced by some parameters -Neighbour size k of every labelled sample, Affinity Matrix A = {Aij} and Trade-off parameter β, our sparse algorithm is developed based on the distribution of the data set, which is much more adaptive to data set themselves. To develop a more tractable and practical approach, we in particular impose neighourhood structure constraint on the labelled samples in the minimum reconstruction criterion and develop a quadratic optimisation technique to approximately estimate the affine matrix used in the Local Fisher Discriminant Analysis (LFDA). We also give a novel approach to estimate the β automatically. Our experiments on semi-supervised face recognition task demonstrate that the proposed method is more robust and efficient in dealing with the semi-supervised problems in face recognition when compared with the related SELF methods.

show abstract

“…Another project [29], combined multiple faces captured from a single camera using a mosaic method in order to enhance the recognition rate. In another research [30], the sensor data from the face and palm-print was fused by particle swarm optimization. The Kernel Direct Discriminant Analysis features were extracted from the fused data and the nearest neighbour classifier was used for their classification.…”

Section: Sensor Level Fusionmentioning

confidence: 99%

Confidence Based Rank Level Fusion for Multimodal Biometric Systems

Talebi

Gavrilova

2015

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

In recent years, the inevitable need for reliable biometric identity management systems in applications such as border crossing, welfare distribution, and accessing critical facilities has drawn researchers' attention to the area of biometric. The intrinsic limitations of unimodal biometric systems such as non-universality, sensitivity to noisy sensor data, inter and intra class variations and spoof attacks have resulted in significant attention toward multimodal biometric systems. An important aspect of a multimodal biometric system is the fusion of information from multiple biometric sources. This thesis focuses on using the notion of Resemblance Probability Distributions to calculate confidence measures for different biometric matchers and use these confidence measures in the fusion module to improve the identification rate of the system. This thesis approaches the problem of low inter class variation and low quality data by proposing Rank List Reinforcement and Confidence-based Ranked List Selection methods.

show abstract

Multisensor biometric evidence fusion of face and palmprint for person authentication using Particle Swarm Optimisation (PSO)

Cited by 14 publications

References 16 publications

PSO Based Framework for Weighted Feature Level Fusion of Face and Palmprint

PSO Based Framework for Weighted Feature Level Fusion of Face and Palmprint

Self-adaptive local Fisher discriminant analysis for semi-supervised image recognition

Confidence Based Rank Level Fusion for Multimodal Biometric Systems

Contact Info

Product

Resources

About