Adaptive weighted fusion: A novel fusion approach for image classification

Xu, Yong; Lu, Yuwu

doi:10.1016/j.neucom.2015.05.070

Cited by 65 publications

(16 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jing and Zhang [3] proposed a face and palmprint recognition approach based on discrete cosine transform (DCT) and linear discrimination technique, a twodimensional (2D) separability judgment was used to select appropriate DCT frequency bands with favourable linear separability. Xu and Lu [4] explored the fusion of five different face and palmprint databases based on a method named adaptive weighted fusion approach; this approach can automatically set optimal weights for every test sample. Noor et al [5] investigated a multimodal speaker identification system based on wavelet analysis and neural networks to identify a speaker from his voice, the system improved the identification rate by 15% as compared with the classical Mel frequency cepstral-coefficients).…”

Section: Related Workmentioning

confidence: 99%

Multimodal biometric recognition using human ear and palmprint

Hezil

Boukrouche

2017

IET biom.

View full text Add to dashboard Cite

Combining multiple human trait features is a proven and effective strategy for biometric-based personal identification. In this study, the authors investigate the fusion of two biometric modalities, i.e. ear and palmprint, at feature-level. Ear and palmprint patterns are characterised by a rich and stable structure, which provides a large amount of information to discriminate individuals. Local texture descriptors, namely local binary patterns, weber local descriptor, and binarised statistical image features, were used to extract the discriminant features for robust human identification. The authors' extensive experimental analysis based on the benchmark IIT Delhi-2 ear and IIT Delhi palmprint databases confirmed that the proposed multimodal biometric system is able to increase recognition rates compared with that produced by single-modal biometrics, attaining a recognition rate of 100%.

show abstract

Section: Related Workmentioning

confidence: 99%

Multimodal biometric recognition using human ear and palmprint

Hezil

Boukrouche

2017

IET biom.

View full text Add to dashboard Cite

show abstract

“…We would like to point out that a similar weight setting algorithm was proposed in [27], which is the first completely adaptive weighted fusion algorithm and obtained an almost perfect fusion result. However, the algorithm in [27] can fuse only two kinds of scores.…”

Section: Algorithm To Integrate Original Images and Virtual Imagesmentioning

confidence: 99%

Virtual Samples Construction Using Image-Block-Stretching for Face Recognition

Zhao

Chen

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Face recognition encounters the problem that multiple samples of the same object may be very different owing to the deformation of appearances. To synthesizing reasonable virtual samples is a good way to solve it. In this paper, we introduce the idea of image-block-stretching to generate virtual images for deformable faces. It allows the neighbored image blocks to be stretching randomly to reflect possible variations of the appearance of faces. We demonstrate that virtual images obtained using image-block-stretching and original images are complementary in representing faces. Extensive classification experiments on face databases show that the proposed virtual image scheme is very competent and can be combined with a number of classifiers, such as the sparse representation classification, to achieve surprising accuracy improvement.

show abstract

“…Actually, different tasks have different weights because they have different discrimination capabilities, so the idea of equal weights has certain shortcomings. As a remedy, this paper uses the adaptive weighting algorithm proposed in [50] to obtain the optimal weights for different features. For the reconstructed error vectors of different types of features, the adaptive weights are solved and used for linear fusion.…”

Section: Introductionmentioning

confidence: 99%

Combination of Joint Representation and Adaptive Weighting for Multiple Features with Application to SAR Target Recognition

Wang

2021

Scientific Programming

View full text Add to dashboard Cite

For the synthetic aperture radar (SAR) target recognition problem, a method combining multifeature joint classification and adaptive weighting is proposed with innovations in fusion strategies. Zernike moments, nonnegative matrix factorization (NMF), and monogenic signal are employed as the feature extraction algorithms to describe the characteristics of original SAR images with three corresponding feature vectors. Based on the joint sparse representation model, the three types of features are jointly represented. For the reconstruction error vectors from different features, an adaptive weighting algorithm is used for decision fusion. That is, the weights are adaptively obtained under the framework of linear fusion to achieve a good fusion result. Finally, the target label is determined according to the fused error vector. Experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset under the standard operating condition (SOC) and four extended operating conditions (EOC), i.e., configuration variants, depression angle variances, noise interference, and partial occlusion. The results verify the effectiveness and robustness of the proposed method.

show abstract

Adaptive weighted fusion: A novel fusion approach for image classification

Cited by 65 publications

References 50 publications

Multimodal biometric recognition using human ear and palmprint

Multimodal biometric recognition using human ear and palmprint

Virtual Samples Construction Using Image-Block-Stretching for Face Recognition

Combination of Joint Representation and Adaptive Weighting for Multiple Features with Application to SAR Target Recognition

Contact Info

Product

Resources

About