Practical Method for Evaluating the Performance of a Biometric Algorithm

Djara, Tahirou; Sobabe, Abdou-Aziz; Agbomahéna, Macaire; Vianou, Antoine

doi:10.1007/978-3-030-05198-3_11

Cited by 3 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have obtained these images from the work of Djara et al [16] who have described the image acquisition process. Djara et al [2] have developed a non-Contact Biometric Fingerprint Software (CBFS) for the acquisition and processing of our images.…”

Section: Database and Materialsmentioning

confidence: 99%

“…Biometrics has become one of the most important solutions in terms of ensuring computer systems security. Biometrics is a global technique aimed at establishing a person's identity by measuring a morphological (such as the face), biological (such as DNA, genetic heritage) and/or behavioural (such as a signature) feature [2] [3] [4] [5]. Among all biometrics, fingerprints are the most convenient human feature, widely used for the purpose of identifying individuals [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fingerprint Recognition Using a Transfer Learning Method

Assouma,

Djara,

Sanya

et al. 2023

IJMIP

View full text Add to dashboard Cite

Individuals' recognition has been the major concern of many computer science scholars. This paper highlights the development of a biometric fingerprint recognition system using an artificial intelligence method. The methodology used is structured into three main steps: fingerprint image acquisition, feature extraction and comparison or matching. Firstly, we use non-contact fingerprint images for training the recognition model to allow the developed system to work without contact. Secondly, we used a database of nineteen individuals each having fifteen fingerprint images acquired without contact. To perform the transfer learning, we have exploited the MobileNets model while adapting its architecture to the new task of contactless fingerprint classification. After training the new model obtained, we performed it evaluation through a confusion matrix. This evaluation reveals that the developed method confuses one individual out of 19, i.e. a confusion rate of 5.26%. This rate testifies to the efficiency of the method used for non-contact fingerprint recognition.

show abstract

Section: Database and Materialsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fingerprint Recognition Using a Transfer Learning Method

Assouma,

Djara,

Sanya

et al. 2023

IJMIP

View full text Add to dashboard Cite

show abstract

“…is the probability that the test user is given the feature vector . Assuming that soft biometric variables are independent [25], (7) becomes:…”

Section: Extension Of the Adapted Sequential Fusion Approachmentioning

confidence: 99%

“…To capitalize on the two principles described above through (7) to (21), we propose a new score-level fusion architecture (see Fig. 11) that we call the adapted sequential fusion strategy.…”

Section: Fig 10: Graphical Representation Of the Sprtmentioning

confidence: 99%

Incorporating Metadata in Multibiometric Score-Level Fusion: an Optimized Architecture

2019

IJITEE

View full text Add to dashboard Cite

 This manuscript presents a review on multibiometrics using ancillary information, in addition to the main biometric data. The proposed method involves taking non-biometric information into account in the biometric recognition process to improve system performance. This ancillary information can come from the user (the skin color), the sensor (the camera flash, etc.) or the operating environment (the ambient noise). Moreover, the paper presents an extension of the adapted sequential fusion framework through a complete description of the method used for the score-level fusion architecture presented at the IEEE BioSmart 2019 Proceedings. An optimized score-level fusion architecture is proposed. An introduction of new concepts (namely "biochemical features" and "multi origin biometrics") is also made. The first part of the paper highlights the various biometric systems developed up to now, their architecture and characteristics. Then, the manuscript discussed about multibiometrics through its advantages, its diversity and the different levels of fusion. An attention was paid to the score-level fusion before addressing the consideration of ancillary information (or metadata) in multibiometrics. Dealing with the affective computing, the influence of emotion on the performance of biometric systems is explored. Finally, a typology of biometric adaptation is discussed.As an application, the proposed methodology will implement a multibiometric system using the face, contactless fingerprint and skin color. A single sensor will be used (a camera) with two shots while the skin color will be extracted automatically from the facial image.

show abstract