Biometric identification using augmented database

Lionnie, Regina; Agustina, Ellisa; Sediono, Wahju; Alaydrus, Mudrik

doi:10.12928/telkomnika.v17i1.11713

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the fusion of different biometric has improved the biometric recognition accuracy, image augmentation also plays a vital role in training the models for winning algorithms especially for deep neural networks [20]. A recent research study demonstrates that the biometric recognition using augmented data achieved two times greater accuracies as compared with the data without augmentation [21].…”

Section: Literature Reviewmentioning

confidence: 99%

Analyzing the Effects of Data Augmentation on Single and Multimodal Biometrics

Leghari

Memon

Dhomeja

et al. 2020

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

Now-a-days, in the field of machine learning the data augmentation techniques are common in use, especially with deep neural networks, where a large amount of data is required to train the network. The effectiveness of the data augmentation technique has been analyzed for many applications; however, it has not been analyzed separately for the multimodal biometrics. This research analyzes the effects of data augmentation on single biometric data and multimodal biometric data. In this research, the features from two biometric modalities: fingerprint and signature, have been fused together at the feature level. The primary motivation for fusing biometric data at feature level is to secure the privacy of the user’s biometric data. The results that have been achieved by using data augmentation are presented in this research. The experimental results for the fingerprint recognition, signature recognition and the feature-level fusion of fingerprint with signature have been presented separately. The results show that the accuracy of the training classifier can be enhanced with data augmentation techniques when the size of real data samples is insufficient. This research study explores that how the effectiveness of data augmentation gradually increases with the number of templates for the fused biometric data by making the number of templates double each time until the classifier achieved the accuracy of 99%.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Analyzing the Effects of Data Augmentation on Single and Multimodal Biometrics

Leghari

Memon

Dhomeja

et al. 2020

Mehran Univ. res. j. eng. technol.

View full text Add to dashboard Cite

show abstract

“…These systems depend on storing users' data in the main database linked to several branches. When each electronic payment process is changed or authenticated, user data is verified and compared to the original in the database, and upon verification, the operation is completed successfully [4], [5]. Several studies have focused on security issues without decreasing performance and purchase time.…”

Section: Introductionmentioning

confidence: 99%

Design and develop authentication in electronic payment systems based on IoT and biometric

Talib

Salman

2022

TELKOMNIKA

View full text Add to dashboard Cite

Biometrics is a highly reliable technology where it has become possible to use the characteristics of a person or user (biometrics) along with traditional passwords, and we can even say that it has become an indispensable complement in modern authentication systems today, especially with regard to bank accounts, banks, financial technology (FinTech) internet of things (IoT) devices and all a process related to money and privacy, and biometric methods are multiple and increasing day by day, the most famous of which is (iris, face chart, palm, fingerprint, and others). Biometric systems are immune and immune from modern electronic attacks, such as plagiarism or electronic theft, because the authentication here takes place when all conditions are met. Then the authentication is done and the process is completed, and the aim is to reach the highest levels of accuracy and security and to make the user more comfortable to deal with these modern systems that provide him with many advantages and high privacy.

show abstract

“…In obtaining an effective crop yield count from aerial images, the pre-processing stage must be robust, given the varying light conditions and heights in capturing these images. The application of the colour component in the image segmentation process is also important, especially for detection [9], recognition [10], identification [11,12] and classification [13] of the objects. Previously, several colour spaces have been proposed which include RGB [14], YCbCr [15], HSV [16] and L*A*B* [17].…”

Section: Introductionmentioning

confidence: 99%

Ananas comosus crown image thresholding and crop counting using a colour space transformation scheme

2020

View full text Add to dashboard Cite

The implementation of unmanned aerial vehicle (UAV) technology having image processing capabilities provides an alternative way to observe pineapple crowns captured from aerial images. In the majority of pineapple plantations, an agricultural officer will physically count the crop yield prior to harvesting the Ananas Comosus, also known as pineapple. This process is particularly evident in large plantation areas to accurately identify pineapple numbers. To alleviate this issue, given it is both time-consuming and arduous, automating the process using image processing is suggested. In this study, the possibilities and comparisons between two techniques associated with an image thresholding scheme known as HSV and L*A*B* colour space schemes were implemented. This was followed by determining the threshold by applying an automatic counting (AC) method to count the crop yield. The results of the study found that by applying colour thresholding for segmentation, it improved the low contrast image due to different heights and illumination levels on the acquired colour image. The images that were acquired using a UAV revealed that the best distance for capturing the images was at the height of three (3) metres above ground level. The results also confirm that the HSV colour space provides a more efficient approach with an average error increment of 47.6% when compared to the L*A*B*colour space.

show abstract

Biometric identification using augmented database

Cited by 4 publications

References 9 publications

Analyzing the Effects of Data Augmentation on Single and Multimodal Biometrics

Analyzing the Effects of Data Augmentation on Single and Multimodal Biometrics

Design and develop authentication in electronic payment systems based on IoT and biometric

Ananas comosus crown image thresholding and crop counting using a colour space transformation scheme

Contact Info

Product

Resources

About