2022
DOI: 10.12928/telkomnika.v20i4.23759
|View full text |Cite
|
Sign up to set email alerts
|

Towards more accurate and efficient human iris recognition model using deep learning technology

Abstract: In this study, an end-to-end human iris recognition system is presented to automatically identify individuals for high level of security purposes. The deep learning technology based new 2D convolutional neural network (CNN) model is introduced for extracting the features and classifying the iris patterns. Firstly, the iris dataset is collected, preprocessed and augmented. The dataset are expanded and enhanced using data augmentation, histogram equalization (HE) and contrast-limited adaptive histogram equalizat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
16
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
3

Relationship

0
6

Authors

Journals

citations
Cited by 15 publications
(16 citation statements)
references
References 23 publications
0
16
0
Order By: Relevance
“…So, the earliest triplet-loss task is comprehensive, and cites as ETL. See eq (5), and Masked-Distance (MMSD) method, termed as eq (6):…”
Section: Feature Extraction Stagementioning
confidence: 99%
See 3 more Smart Citations
“…So, the earliest triplet-loss task is comprehensive, and cites as ETL. See eq (5), and Masked-Distance (MMSD) method, termed as eq (6):…”
Section: Feature Extraction Stagementioning
confidence: 99%
“…Iris recognition method using CNN [5] In this method, the learning based 2D-CNN model is classified images of eye-iris based eye features were extracted. Iris dataset is gathered, enhanced using histogram equalization (HE) schema with contrast limited adaptive equalization (CLAHE) schemas, and augmented.…”
Section: 3mentioning
confidence: 99%
See 2 more Smart Citations
“…This work proposed DL approach based on convolution neural networks (CNN) technique for classification and early detection for COVID-19 based upon chest X-rays (CXRs) as datasets. CNN architecture consists of various kinds of the layers (which are: convolutional layer, pooling layer, flatten, and fully connected layer) [14], [15] each type is responsible for specific action. The convolutional layer is the first layer which is utilized for the extraction of different features from input images followed by pooling layer that has been used in order to reduce the convolved feature map size to cut computational cost, while fully connected layer is used for classification [16].…”
Section: Introductionmentioning
confidence: 99%