Identifying twins based on ocular region features using deep representations

Gautam, Gunjan; Raj, Aditya; Mukhopadhyay, Susanta

doi:10.1007/s10489-019-01562-w

Cited by 20 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional performance validation metrics used are CCR, training loss and the AUROC curve. (Gautam et al, 2019). (Gautam et al, 2019).…”

Section: Resultsmentioning

confidence: 99%

“…Figure 4: AUROC Performance on every framework for each CV fold. Reprinted from (Gautam et al, 2019).…”

Section: Resultsmentioning

confidence: 99%

“…These multi-scale filters are averaged instead of contatenated for the sake of keeping computatinal costs at bay, since the difference between one and the other did not suppose a significant difference in accuracy. (Gautam et al, 2019).…”

Section: Mcnn-siamese Frameworkmentioning

confidence: 99%

“…More specifically, in this survey we will tackle in section 2 twin identification, one of the biggest problems with ocular recognition, applying deep learning (Gautam et al, 2019). In section 3, an improved method to prevent fingerprint spoofing is discussed, potentially solving this biometric system's biggest drawback (Arora and Bhatia, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning in Biometrics: A Survey

López

2019

ADCAIJ

View full text Add to dashboard Cite

Deep learning; biometrics; fingerprint; ocular recognition; convolutional neural networks; electrocardiogram Deep learning has been established in the last few years as the gold standard for data processing, achieving peak performance in image, text and audio understanding. At the same time, digital security is of utmost importance in this day and age, where everyone could get into our personal devices like cellphones or laptops, where we store our most valuable information. One of the possible ways to prevent this is via advanced and personalized security: biometrics. In this survey, it is considered how the scientific advances in the field of deep learning are applied to biometrics in order to enhance the protection of our data. Firstly, a study will be conducted on tackling ocular identification of twins using deep learning. Then, an improved method for avoiding fingerprint spoofing will be presented, thus solving this method's biggest issue. Finally, a brand new method for biometric identification is proposed based on the usage of the user's electrocardiogram. On every one of these methods, the results manage to top the standard alternative performances.

show abstract

“…Additional performance validation metrics used are CCR, training loss and the AUROC curve. (Gautam et al, 2019). (Gautam et al, 2019).…”

Section: Resultsmentioning

confidence: 99%

“…Figure 4: AUROC Performance on every framework for each CV fold. Reprinted from (Gautam et al, 2019).…”

Section: Resultsmentioning

confidence: 99%

Section: Mcnn-siamese Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning in Biometrics: A Survey

López

2019

ADCAIJ

View full text Add to dashboard Cite

show abstract

“…The concept of Siamese Network was first proposed by Bromley et al [ 6 ] in 1993 to solve signature matching problems. Later many researchers used Siamese architecture for various applications such as image matching for face recognition [ 23 ], person reidentification [ 11 ], sketch image to original image matching in critical surveillance scenario [ 38 ], visual object recognition [ 39 ] and twins identification [ 13 ].…”

Section: Literature Reviewmentioning

confidence: 99%

One shot learning approach for cross spectrum periocular verification

Kumari

Seeja

2023

Multimed Tools Appl

View full text Add to dashboard Cite

The use of face mask during the COVID-19 pandemic has increased the popularity of the periocular biometrics in surveillance applications. Despite of the rapid advancements in this area, matching images over cross spectrum is still a challenging problem. Reason may be two-fold 1) variations in image illumination 2) small size of available data sets and/or class imbalance problem. This paper proposes Siamese architecture based convolutional neural networks which works on the concept of one-shot classification. In one shot classification, network requires a single training example from each class to train the complete model which may lead to reduce the need of large dataset as well as doesn’t matter whether the dataset is imbalance. The proposed architectures comprise of identical subnetworks with shared weights whose performance is assessed on three publicly available databases namely IMP, UTIRIS and PolyU with four different loss functions namely Binary cross entropy loss, Hinge loss, contrastive loss and Triplet loss. In order to mitigate the inherent illumination variations of cross spectrum images CLAHE was used to preprocess images. Extensive experiments show that the proposed Siamese CNN model with triplet loss function outperforms the states of the art periocular verification methods for cross, mono and multi spectral periocular image matching.

show abstract

T2L2: A Tiny Three Linear Layers Model for Service Mashup Creation

Liu

Zhu

et al. 2021

Service-Oriented Computing

View full text Add to dashboard Cite

Identifying twins based on ocular region features using deep representations

Cited by 20 publications

References 42 publications

Deep Learning in Biometrics: A Survey

Deep Learning in Biometrics: A Survey

One shot learning approach for cross spectrum periocular verification

T2L2: A Tiny Three Linear Layers Model for Service Mashup Creation

Contact Info

Product

Resources

About