No abstract

An end-to-end sea fog removal network using multiple scattering model was proposed. In this network, the atmospheric multiple scattering model was re-formulated and used for sea fog removal. Compared with the atmospheric single scattering model, the atmospheric multiple scattering model could more comprehensively consider the effect of multiple scattering, which was important to the dense fog scenes, such as in ocean scene. Therefore, we used the atmospheric multiple scattering model to avoid image blurring. The model can directly generate the dehazing results, and unify the three parameters of the transmission map, the atmospheric light and the blur kernel into one formula. The latest smooth dilation and sub-pixel techniques were used in the network model. The latest techniques can avoid the gridding artifacts and the halo artifacts, the multi-scale sub-network was used to consider the features of multi-scale. In addition, multiple loss functions were used in end-to-end network. In the experimental results, the model was superior to the state-of-the-art models in terms of quantitatively and qualitatively.

An unsupervised single-image dehazing method using a multiple scattering model is proposed. The method uses an undegraded atmospheric multiple scattering model and unsupervised learning to implement dehazing on single real-world image. The atmospheric multiple scattering model can avoid the influence of multiple scattering on the image and the unsupervised neural network can avoid the intensive operation on the data set. In this method, three unsupervised learning branches and a blur kernel estimation module estimate the scene radiation layer, transmission layer, atmospheric light layer, and blur kernel layer, respectively. In addition, the unsupervised loss function is constructed by prior knowledge to constrain the unsupervised branches. Finally, the output of the three unsupervised branches and the blur kernel estimation module synthesizes the haze image in a self-supervised way. A large number of experiments show that the proposed method has good performance in image dehazing compared with the six most advanced dehazing methods.

Automatic detection of surface defects in electronic panels is receiving increasing attention in the quality control of products. The surface defect detection of electronic panels is different from other target detection scenarios and is a meaningful and challenging problem. Its main manifestation is that surface defects of electronic panels usually exhibit extreme irregularity and small target characteristics, which bring great difficulties to the task of surface defect target detection including feature extraction and so on. The traditional methods can only detect a very small number of defect classes under specific detection conditions. And due to the weak robustness of these methods, they cannot be applied in real production scenarios on a large scale. Based on this, this paper applies the target detection technique under deep learning to the surface defect detection scenario of electronic panels for the first time. At the same time, in order to make the designed target detection network applicable to the electronic panel surface defect detection scenario and to enhance the interpretability of the designed target detection network in terms of computer mechanism. We design a deformable convolution module with a convolutional self-attentive module to learn the offset and a dual detection head incorporating the SE (Squeeze-and-Excitation) mechanism for the irregular characteristics of electronic panel surface defects and the small target characteristics, respectively. Finally, we carried out a series of experiments on our own electronic panel defect data set, including comparison with the most advanced target detection algorithms and a series of ablation experiments against our proposed method. The final experimental results prove that our method not only has better interpretability, but also has better metric performance, in which the map_0.5 metric reaches 78.257%, which is an increase of 13.506 percentage points over YOLOV5 and 33.457 percentage points higher than Retinanet. The results prove the proposed method is effective.

During the production of electronic panels, surface defects will inevitably appear. How to quickly and accurately detect these defects is very important to improve product quality. However, some problems such as high cost and low accuracy are still prominent when existing manual detection and traditional techniques are used to solve such problems. Therefore, more and more computer vision techniques are proposed to solve such problems, but the current application of deep learning-based object detection networks for surface defect detection of electronic panels is in a gap. The analysis found that there are two main reasons for this phenomenon. On the one hand, the surface defects of electronic panels have their unique characteristics such as multi-scale and irregular shape, and the current object detection networks cannot effectively solve these problems. On the other hand, the regression and classification tasks coupled in the current computational mechanism of each network are commonly found to cause the problem of conflict between them, which makes it more difficult to adapt these network models to the detection tasks in this scenario. Based on this, we design a supervised object detection network for electronic panel surface defect detection scenario for the first time. The computational mechanism of this network includes a prediction box generation strategy based on the double branch structure and a detection head design strategy that decouples the regression task from the classification task. In addition, we validated the designed network and the proposed method on our own collected dataset of surface defects in electronic panels. The final results of the comparative and ablation experiments show that our proposed method achieves an average accuracy of 78.897% for 64 surface defect categories, proving that its application to electronic panel surface defect detection scenarios can achieve better results.