Deep Face-Iris Recognition Using Robust Image Segmentation and Hyperparameter Tuning

Brown, Dane

doi:10.1007/978-981-16-3728-5_19

Cited by 5 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the identification of critical anatomical landmarks, a facial mesh is generated. The face mesh is built using delaunay triangulation so that no landmark is within the circumcircle of any triangle [25]. The leftward-posing mesh is brought into a frontal orientation, as seen in Figure 2.…”

Section: Matching Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Biometric face recognition method using graphics processing unit system

Alshiha

Al-Neama

Al-Qubaa

2023

IJEECS

View full text Add to dashboard Cite

The expansion of biometric applications and databases is worrying. Processing extensive or sophisticated biometric data results in longer wait times, which might restrict application usefulness. This work focuses on accelerating the processing of biometric data and proposes a parallel method of data processing that exceeds the capabilities of a central processing unit (CPU). The combination of the graphics processing unit (GPU) and compute unified device architecture (CUDA) results in at least three times the processing speed of a published accurate and secure multimodal biometric system. The GPU-assisted approach beats the CPU-only implementation when saturating the CPU-only performance with more people than the available thread count. The GPU-assisted solution is also proven to have the same accuracy as the original system, indicating accuracy and processing performance improvements in the demanding big data environment.

show abstract

Section: Matching Featuresmentioning

confidence: 99%

“…The studies [25]- [27] have been shown to work well together to maximize inter-class variance for image-based biometrics. The LoG filter eliminates undesirable characteristics in the low and high-frequency spectrum before boosting the remaining features, thus improving the mean signal.…”

Section: Extracting Featuresmentioning

confidence: 99%

Biometric face recognition method using graphics processing unit system

Alshiha

Al-Neama

Al-Qubaa

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…These characteristics also show its broad applicability on the edge and mobile devices. Brown (2022) proposes a DCNN of a bimodal system for enhancing security. The DCNN processes face and iris biometrics from a single image.…”

Section: Deep Cnn Architecturesmentioning

confidence: 99%

Face Recognition Using Deep Convolutional Neural Networks: A Survey

2023

Proceedings of the 17 Th International Conference on Interfaces and Human Computer Interaction 2023 (IHCI 2023), the 17th Inter

View full text Add to dashboard Cite

Face recognition technology uses Deep Convolutional Neural Network (DCNN) to extract biometric features for identity authentication. It has been used in various application domains, including military, law enforcement, finance, public security, and other daily life applications. This paper reviews the updated progress of DCNN architectures used for face recognition. It also explores pretrained models along with training datasets that exist. Furthermore, some face recognition applications are summarized. The limitations and further research directions are pointed. Although face recognition is an emerging technique, it raises security concerns.

show abstract