Back to Search
Start Over
An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network
- Source :
- Sensors, Volume 21, Issue 11, Sensors, Vol 21, Iss 3721, p 3721 (2021), Sensors (Basel, Switzerland)
- Publication Year :
- 2021
- Publisher :
- Multidisciplinary Digital Publishing Institute, 2021.
-
Abstract
- Recently, deep learning approaches, especially convolutional neural networks (CNNs), have attracted extensive attention in iris recognition. Though CNN-based approaches realize automatic feature extraction and achieve outstanding performance, they usually require more training samples and higher computational complexity than the classic methods. This work focuses on training a novel condensed 2-channel (2-ch) CNN with few training samples for efficient and accurate iris identification and verification. A multi-branch CNN with three well-designed online augmentation schemes and radial attention layers is first proposed as a high-performance basic iris classifier. Then, both branch pruning and channel pruning are achieved by analyzing the weight distribution of the model. Finally, fast finetuning is optionally applied, which can significantly improve the performance of the pruned CNN while alleviating the computational burden. In addition, we further investigate the encoding ability of 2-ch CNN and propose an efficient iris recognition scheme suitable for large database application scenarios. Moreover, the gradient-based analysis results indicate that the proposed algorithm is robust to various image contaminations. We comprehensively evaluated our algorithm on three publicly available iris databases for which the results proved satisfactory for real-time iris recognition.
- Subjects :
- Computational complexity theory
Computer science
Iris recognition
Feature extraction
0211 other engineering and technologies
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Iris
convolutional neural network
02 engineering and technology
TP1-1185
Biochemistry
Convolutional neural network
Article
Analytical Chemistry
iris recognition
Encoding (memory)
Classifier (linguistics)
online augmentation
0202 electrical engineering, electronic engineering, information engineering
Attention
Pruning (decision trees)
Electrical and Electronic Engineering
Instrumentation
021110 strategic, defence & security studies
network pruning
business.industry
Deep learning
Chemical technology
deep learning
Recognition, Psychology
Atomic and Molecular Physics, and Optics
020201 artificial intelligence & image processing
Artificial intelligence
Neural Networks, Computer
business
Algorithm
Algorithms
Subjects
Details
- Language :
- English
- ISSN :
- 14248220
- Database :
- OpenAIRE
- Journal :
- Sensors
- Accession number :
- edsair.doi.dedup.....4bf69506864e0bd0cb704b58a2d5dc26
- Full Text :
- https://doi.org/10.3390/s21113721