Deep learning based remote sensing image scene classification methods are the current mainstream, and enough labeled samples are very important for their performance.Considering the fact that manual labeling of samples requires high labor and time cost, lots of methods have been proposed to automatically generate pseudo samples from real samples, however, existing methods can not directly sift the pseudo samples from the perspective of model training. To address this problem, a generating and sifting pseudo labeled samples scheme is proposed in this paper. First of all, the existing SinGAN is used to generate multiple groups of pseudo samples from the real samples. Afterwards, the proposed quantitative sifting measure which can evaluate both the authenticity and diversity from the perspective of model training is employed to select the best pseudo samples from the multiple generated pseudo samples. Finally, the selected pseudo samples and real samples are used to pretrain and finetune the deep scene classification network (DSCN) respectively. Moreover, the focal loss which is originally proposed for object detection is adopted to replace the traditional cross entropy loss in this paper. A designed quantitative evaluation shows that the value of proposed quantitative sifting measure is proportional to the overall accuracy, which validates the effectiveness of proposed quantitative sifting measure. The comprehensive quantitative comparisons on AID and NWPU-RESISC45 datasets in terms of overall accuracy and confusion matrices demonstrate that incorporating the pseudo samples selected by proposed sifting measure and the focal loss can improve the performance of DSCN.
Purpose
An effective machine vision-based method for micro-crack detection of solar cell can economically improve the qualified rate of solar cells. However, how to extract features which have strong generalization and data representation ability at the same time is still an open problem for machine vision-based methods.
Design/methodology/approach
A micro-crack detection method based on adaptive deep features and visual saliency is proposed in this paper. The proposed method can adaptively extract deep features from the input image without any supervised training. Furthermore, considering the fact that micro-cracks can obviously attract visual attention when people look at the solar cell’s surface, the visual saliency is also introduced for the micro-crack detection.
Findings
Comprehensive evaluations are implemented on two existing data sets, where subjective experimental results show that most of the micro-cracks can be detected, and the objective experimental results show that the method proposed in this study has better performance in detecting precision.
Originality/value
First, an adaptive deep features extraction scheme without any supervised training is proposed for micro-crack detection. Second, the visual saliency is introduced for micro-crack detection.
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.