Search

The weld penetration rate is an important evaluation criterion for welding quality. However, it is difficult to identify the weld penetration state during GTAW welding process. This paper presents a new penetration recognition method based on time and spectrum images of arc sound using deep learning for DC GTAW welding. The time domain and spectrum images of the three penetration states from the non-periodic arc sound were used as the dataset for the penetration prediction model. VGG16, AlexNet, and custom convolutional neural network (CNN) were used to extract image features, and softmax was used to classify images for penetration recognition. The influence of image feature extraction networks, input methods, and different sampling methods on the recognition accuracy was deeply analyzed. The results show that the overall validation accuracy of the proposed model is approximately 96.2%. Particularly, the validation accuracy of the model in the excessive penetration state is approximately 100%. This study provides a new and feasible method for the online detection of weld penetration during the GTAW welding process.

Dynamic scene deblurring is a significant technique in the field of computer vision. The multi-scale strategy has been successfully extended to the deep end-to-end learning-based deblurring task. Its expensive computation gives birth to the multi-patch framework. The success of the multi-patch framework benefits from the local residual information passed across the hierarchy. One problem is that the finest levels rarely contribute to their residuals so that the contributions of the finest levels to their residuals are excluded by coarser levels, which limits the deblurring performance. To this end, we substitute the nested module blocks, whose powerful and complex representation ability is utilized to improve the deblurring performance, for the building blocks of the encoder-decoders in the multi-patch network. Additionally, the attention mechanism is introduced to enable the network to differentiate blur across the whole blurry image from dynamic scene, thereby further improving the ability to handle the motion object blur. Our modification boosts the contributions of the finest levels to their residuals and enables the network to learn different weights for feature information extracted from spatially-varying blur image. Extensive experiments show that the improved network achieves competitive performance on the GoPro dataset according to PSNR and SSIM.

In this paper, we propose a new framework for banknote classification based on quaternion wavelet transform (QWT) and deep convolutional neural network. Firstly, the QWT is applied to describe the phase and magnitude of different banknote images which has inherent directional sensitivity and multi-scale framework. Then we design a deep convolutional neural network which is trained on banknote images along with the magnitude and phase of quaternion wavelet coefficients. We assign the neural weights on the output probabilities of deep convolutional neural network and update these weights by utilizing the back propagation algorithm. Finally, the trained networks with decision of a weighted sum and the magnitude and the phase of quaternion wavelet networks are utilized for banknote image classification. The performance of our algorithm is experimentally verified on a variety of banknote databases. Experimental results show that the proposed algorithm achieves superior performance compared with other state-of-the-art banknote classification algorithms. The proposed algorithm can also satisfy the real-time requirements of the banknote sorting system.

Image rain removal is extremely important since rain streaks can severely degrade the visibility which can decrease accuracy of many current computer vision algorithms. However, many deep-learning methods cannot adapt to the rain streak removal of different density labels, meanwhile retain the background details. To address this problem, we propose a novel image rain removal algorithm (CAAN) based on deep cascaded network and dual-channel attention mechanism. As contextual information is very crucial for rain removal, hence firstly the dilated convolution kernels of different scale branches are used to extract features of different rain streak sizes. Then we applied residual attention module (LMSRAM) to guide the learned features to be discriminative and beneficial. Specifically, a novel cascaded sub-network is developed to propagate information from lower to higher layers and decrease the loss of detailed information. Finally, the dual channel attention mechanism is used to make feature fusion efficiently. The experimental results demonstrate that the proposed method achieves the state-of-the-art results compared to the prevailing methods in terms of both quantitative metrics and visual quality. The source code of our proposed CAAN can download from the personal website. https://github.com/baiyihan/CAAN.

A new method of banknote image retrieval is proposed by using new set of rotated quaternion wavelet filters (RQWF) and standard quaternion wavelet transform (QWT) jointly. The robust and rotationally invariant features are extracted from QWT and RQWF decomposed sub-bands of banknote image. Three different sets of databases are used to demonstrate the effectiveness of the proposed method. The experimental results show that the proposed method improves the recognition rate from 78.79% to 91.22% on (16000 images) database D1, form 74.08% to 94.62% on (20000 images) database D2 and from 76.44% to 88.78% on (10000 images) database D3. The proposed method can also obtain a reasonable level of computational complexity.