A weighted fuzzy belief factor-based D-S evidence theory of sensor data fusion method and its application to face recognition

Ghosh, Manas; Dey, Aniruddha; Kahali, Sayan

doi:10.1007/s11042-023-16037-x

Cited by 3 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research [7] suggested taking a more comprehensive approach to offer a more adequate foundation from which to fully comprehend the fusion techniques of wearable sensors. The study [8] aimed to deal with a more thorough examination of the key elements of multisensory uses for human activity identi cation, such as those that have recently been integrated into the area for unsupervised learning and transfer learning.The study [9] described the missing winning class that is absent from the output set of any of the three techniques will now be subject to a vanishing penalty in terms of fuzzy weight. Decision fusion-based face recognition uses these fuzzy weights with vanishing penalties.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Reliable Person Identification Using a Novel Multibiometric Image Sensor Fusion Architecture

Amin,

patel

et al. 2024

Preprint

View full text Add to dashboard Cite

Biometric and multimodal biometric sectors have made major advances in recent years. Usually, forensics, security, and privacy are the three areas where this is exhibited. It is frequently impossible to reach a greater identification rate with unimodal biometric systems, even the best ones. Unimodal biometric systems have several drawbacks, including no universality, a higher rate of false acceptance, and lower rates of true acceptance. Multimodal biometric systems get around these drawbacks. As there are many pieces of evidence for the same identification, a more reliable recognition performance can be attained. The multimodal biometric system that uses iris and fingerprints is the main topic of the work discussed in this paper. The Gabor Filters (GF) are used to extract the unique textual characteristics of the iris and fingerprint. These unimodal characteristics are combined utilizing the Mahalanobis distance technique using a new feature-level fusion method. The system is trained to utilize the retrieved feature using a hybrid random forest classifier with a channel-wise convolutional neural network (HRFC-CWCNN) based learning technique. Using the CASIA iris dataset and genuine fingerprint dataset, the performance of the suggested methods is verified and evaluated against that of other algorithms. It is clear from the simulation outcomes which our method outperforms previous techniques in terms of recognition rate and false rejection rate.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We employ the gradient descent method depicted to update each weight in the design as shown in Eq. (5)(6)(7)(8)(9)(10)(11)(12). 5 Here, γ denotes the learning rate.…”

Section: Feature Extraction Using Mahalanobis Distance Techniquementioning

confidence: 99%