Robust Heterogeneous Discriminative Analysis for Single Sample Per Person Face Recognition

Pang, Meng; Cheung, Yiu-ming; Wang, Binghui; Liu, Risheng

doi:10.1145/3132847.3133096

Cited by 7 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed method we got the percentage recognition rate as 96.01 for the FERET database as compared to the existing techniques presented by Meng Pang et al, [20], Zhijie Tang et al, [21] and Yuqi Pan and Mingyan Jiang [22] as listed in Table 5. Further, for the NIR database the proposed method achieves the percentage recognition rate as 84.5 when compared to the existing method developed by Faten Omri et al [23], who got the recognition rate as 60 percent.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Face recognition using Fusion of DTCWT and FDCT Features

2020

IJETER

View full text Add to dashboard Cite

The growth of automation in our daily life needs prime requirement of security. Biometric recognition or identification is one of the most important system for security and surveillance related activities compared to conventional techniques like ID cards, Personal Identification Number (PIN) and password. The biometric system security can be increased by combining multiple feature extraction algorithms rather than considering single feature extractor. The proposed work incorporates multi scale resolution techniques for extracting facial image features. The system independently incorporates Dual tree complex wavelet transform (DTCWT) technique to extract one set of features coefficients and Fast Discrete Curvelet Transform (FDCT) via wrapping to extract another set of face image features. The extracted features from both the techniques are multiplied and normalized to obtain final features. In order to classify the test feature with trained set of features Euclidean distance (ED) classifier is used. The system performance is evaluated for different face databases like FERET, L-space k, NIR and JAFFE. The values of False Acceptance Rate (FAR), False Rejection Rate (FRR), Total Success Rate (TSR) and Equal Error Rate (EER) were measured and it is found that the proposed system yields better recognition rate with minimal Equal Error Rate when compared to existing techniques.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In this work, Face recognition using the combination of DTCWT and FDCT features in different angular orientations and Euclidean Distance classifier has been proposed [20] 87.25…”

Section: Discussionmentioning

confidence: 99%

Hybrid Face recognition using Fusion of DTCWT and FDCT Features

2020

IJETER

View full text Add to dashboard Cite

show abstract

“…At first, we test the homogeneous FR framework with variations in illumination, and pose. We compared the proposed LFRP with several other state-of-the-art methods, namely G-face [10], W-face [11], LQP [36], ELDP [55], MSLDE [9], SLBFLE [25], DA-JL [48], RSLCR [49], ANI [50], LOGO [51], LGH [65], RHDA [66] and deep learning methods (CNN + Center Loss [38], CNN + Range Loss [39], Deep Face [40], Sphere Face [67], Cos Face [68], and Arc Face [69]). Mostly the original available codes are used to implement the methods, which are mentioned above.…”

Section: Results On Homogeneous Face Recognition Databasesmentioning

confidence: 99%

Local-Friis-Radiation-Pattern (LFRP) for Face Recognition

Roy¹,

Koley²

2021

Sens Imaging

View full text Add to dashboard Cite

In forensic science, various circumstances and requirements give rise to the need for the development of the inter-modality face recognition system to reinforce law and order. In this paper, a novel methodology called Local-Friis-Radiation-Pattern (LFRP) for both homogeneous (visible face images with variations like illumination, pose, and makeup) and heterogeneous (near-infrared (NIR)-visible (VIS) and sketch-photo images) face recognition is proposed. LFRP incorporates the renowned Friis equation of antenna radiation and extends it to image pixels to establish a relation among the pixels residing in a local neighbourhood. Here, we present a robust local image descriptor called the LFPR to effectively capture the illumination-invariant, and modality-invariant facial features. Recognition results on CASIA NIR-VIS 2.0, CUFSF, LFW, CMU-PIE, Extended Yale B, TUFTS VMU, YMU, and MIW databases indicate the superiority and efficiency of the proposed scheme in terms of common feature representation under varying illumination, pose and modality. Moreover, experimental findings reveal that the proposed LFRP is robust against face recognition under non-permanent facial cosmetics (makeup). On the more, a predefined convolutional neural network architecture has been incorporated to improve and compare the proposed LFRP feature map with other state-of-the-art deep learning based methods.

show abstract

“…Recently, it undergoes a large reformation from hand-crafted features to automatic deep features. The Convolutional Neural Networks (CNNs) [28]- [31] reveal a huge advantage on feature representations, and therefore they dominate the person Re-ID field.…”

Section: Related Workmentioning

confidence: 99%

Local Heterogeneous Features for Person Re-Identification in Harsh Environments

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Local features could learn semantic information for pedestrian images and they are very important for person re-identification (Re-ID) in harsh environments. However, most approaches only optimize one kind of local feature, which results in incomplete local features. In this paper, we propose Local Heterogeneous Features (LHF) to extract discriminative local features from three aspects. To this end, we utilize three kinds of losses to learn three kinds of local features, i.e., local discriminative features, local relative features, local compact features. As for local discriminative features, we split the attention maps into three horizontal sub-regions and perform the classification operation. Then, we divide the attention maps into two horizontal sub-regions, and we synchronously apply the triplet loss and center loss to learn local relative features and local compact features. Finally, we utilize local discriminative features to represent pedestrian. We evaluate LHF on public person Re-ID datasets and prove LHF is meaningful for local feature learning.INDEX TERMS Person re-identification, local heterogeneous features, harsh environments.

show abstract

Robust Heterogeneous Discriminative Analysis for Single Sample Per Person Face Recognition

Cited by 7 publications

References 14 publications

Hybrid Face recognition using Fusion of DTCWT and FDCT Features

Hybrid Face recognition using Fusion of DTCWT and FDCT Features

Local-Friis-Radiation-Pattern (LFRP) for Face Recognition

Local Heterogeneous Features for Person Re-Identification in Harsh Environments

Contact Info

Product

Resources

About