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.
GF-6 is the first optical remote sensing satellite for precision agriculture observations in China. Accurate identification of the cloud in GF-6 helps improve data availability. However, due to the narrow band range contained in GF-6, Fmask version 3.2 for Landsat is not suitable for GF-6. Hence, this paper proposes an improved Fmask based on the spectral-contextual information to solve the inapplicability of Fmask version 3.2 in GF-6. The improvements are divided into the following six aspects. The shortwave infrared (SWIR) in the “Basic Test” is replaced by blue band. The threshold in the original “HOT Test” is modified based on the comprehensive consideration of fog and thin clouds. The bare soil and rock are detected by the relationship between green and near infrared (NIR) bands. The bright buildings are detected by the relationship between the upper and lower quartiles of blue and red bands. The stratus with high humidity and fog_W (fog over water) are distinguished by the ratio of blue and red edge position 1 bands. Temperature probability for land is replaced by the HOT-based cloud probability (LHOT), and SWIR in brightness probability is replaced by NIR. The average cloud pixels accuracy (TPR) of the improved Fmask is 95.51%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.