Search

Abstract When applying deep learning and image processing techniques for bridge crack detection, the obtained images in real-world scenarios have severe image degradation problem. This study focuses on restoring low-illumination bridge crack images corrupted by noise to improve the accuracy of subsequent crack detection and semantic segmentation. The proposed algorithm consists of a deep CNN denoiser and a normalized flow-based brightness enhancement module. By taking the noise spectrum as an input, the deep CNN denoiser restores image at a broad range of noise levels. The normalized flow module, employs a conditional encoder and a reversible network to map the distribution of normally exposed images to a Gaussian distribution, effectively improving the image brightness. Extensive experiments have demonstrated the approach can usefully recover low-illumination images corrupted by noise compared to the state-of-the-art methods. Furthermore, the algorithm presented in this study can also be applied to other image quality restoration with high generalization and robust abilities. And the semantic segmentation accuracy of the restored image is significantly improved.

Sex determination of silkworm pupae is important for silkworm industry. Multivariate analysis methods have been widely applied in hyperspectral imaging spectroscopy for classification. However, these methods require essential steps containing spectra preprocessing or feature extraction, which were not easy determined. Convolutional neural networks (CNNs), which have been employed in image recognition, could effectively learn interpretable presentations of the sample without the need of ad-hoc preprocessing steps. The species of silkworm pupae are usually up to hundreds. Conventional classifiers based on one species of silkworm pupae could not give high performance when explored to other species that not participating in the model building, resulting in bad generalization ability. In this study, a CNN model was trained to automatically identify the sex of silkworm pupae from different years and species based on the hyperspectral spectra. The results were compared with the frequently used conventional machine classifiers including support vector machine (SVM) and K nearest neighbors (KNN). The results showed that CNN outperformed SVM and KNN in terms of accuracy when applied to the raw spectra with 98.03%. However, the performance of CNN decreased to 95.09% when combined with the preprocessed data. Then principal component analysis (PCA) was adopted to reduce data dimensionality and extract features. CNN gave higher accuracy than SVM and KNN based on PCA. The discussion section revealed that CNN had high generalization ability that could classify silkworm pupae from different species with a rather well performance. It demonstrated that HSI technology in combination with CNN was useful in determining the sex of silkworm pupae.

As for machine vision-based intelligent system in the application of discriminating and sorting the sex of silkworm pupae, the tail gonad was the unique physiological feature. However, motion blur, resulting from the live silkworm pupa’s writhing motion at the moment of capturing image, could lose textures and structures (such as edge and tail gonad etc.) dramatically, which casted great challenges for sex identification. To increase the image quality and relieve the difficulty of discrimination caused by motion blur, an effective approach that including three stages was proposed in this work. In the image prediction stage, first sharp edges were acquired by using filtering techniques. Then the initial blur kernel was computed with Gaussian prior. The coarse version latent image was deconvoluted in the Fourier domain. In the kernel refinement stage, the Radon transform was applied to estimate the accurate kernel. In the final restoration step, a TV-L1 deconvolution model was carried out to obtain a better result. The experimental results showed that benefiting from the prediction step and kernel refinement step, the kernel was more accurate and the recovered image contained much more textures. It revealed that the proposed method was useful in removing the motion blur. Furthermore, the method could also be applied to other fields. [ABSTRACT FROM AUTHOR]