The detection of optic disc and macula is an essential step for ROP (Retinopathy of prematurity) zone segmentation and disease diagnosis. This paper aims to enhance deep learning-based object detection with domain-specific morphological rules. Based on the fundus morphology, we define five morphological rules, i.e., number restriction (maximum number of optic disc and macula is one), size restriction (e.g., optic disc width: 1.05 +/- 0.13 mm), distance restriction (distance between the optic disc and macula/fovea: 4.4 +/- 0.4 mm), angle/slope restriction (optic disc and macula should roughly be positioned in the same horizontal line), position restriction (In OD, the macula is on the left side of the optic disc; vice versa for OS). A case study on 2953 infant fundus images (with 2935 optic disc instances and 2892 macula instances) proves the effectiveness of the proposed method. Without the morphological rules, naïve object detection accuracies of optic disc and macula are 0.955 and 0.719, respectively. With the proposed method, false-positive ROIs (region of interest) are further ruled out, and the accuracy of the macula is raised to 0.811. The IoU (intersection over union) and RCE (relative center error) metrics are also improved.

Fusing low resolution (LR) HSI with high resolution (HR) multispectral image (MSI) is an important technology to obtain HR hypersepctral image (HSI), which is hard to directly acquire due to the hardware limitation. Deep learning (DL) has been applied in HSI-MSI fusion, but the representability of DL networks for multidimensional (i.e., spectral-spatial) features still need improvement. And most DL HSI-MSI fusion networks are in supervised fashion, HR ground truth HSI is required for training, which is unavailable in reality. In this work, we investigate tensor theory, and propose a coupled multilinear network (CMuNet) for unsupervised HSI-MSI fusion, where deep image prior and degradation model can be jointly learned. CMuNet consists of coupled multilinear filtering subnets, it jointly represents the LR HSI and HR MSI as a random code and multidimensional features on spatial and spectral modes. The HR HSI is inferred with the random code, features on spatial modes of HR MSI and features on spectral mode of LR HSI. Experiments on several HSIs demonstrate the effectiveness of the proposed method.

In this study, we investigated the characteristic difference between the two different configurations of the three-dimensional shell–core nanorod LED. We achieve a degree of polarization of 0.545 for tip-free core–shell nanorod LED and 0.188 for tip core–shell nanorod LED by combining the three-dimensional (3D) structure LED with photonic crystal. The ability of low symmetric modes generated by photonic crystals to enhance degree of polarization has been demonstrated through simulations of photonic crystals. In addition, light confinement in GaN-based nanorod structures is induced by total internal reflection at the GaN/air interface. The combination of 3D core–shell nanorod LED and photonic crystals cannot only produce a light source with a high degree of polarization, but also a narrow divergence angle up to 56°. These 3D LEDs may pave the way for future novel optoelectronic components.

Coded aperture snapshot spectral imaging (CASSI) captures the 3-D hyperspectral images (HSI) in the form of 2-D coded images. The dual-camera compressive hyperspectral imaging (DCCHI) can effectively improve the reconstruction quality by adding a parallel complementary panchromatic camera. Several regularization-based methods have been proposed for dual-camera reconstruction. However, the handcrafted priors of these methods are limited in representing the complex intrinsic structure of HSI. In this letter, we propose to learn deep subspace projection prior for dual-camera compressive reconstruction. We first design a deep subspace projection prior regularized dual-camera compressive reconstruction model and minimize it with alternative optimization. Then, we unfold the optimization process into a network. Specifically, the deep subspace projection prior learning leads to features with low-rank characteristics, which could efficiently exploit the spectral correlation of HSI. The dual-camera compressive reconstruction network is learned in an end-to-end manner. Extensive experiments substantiate the performance and efficiency of other start-of-the-art algorithms.

AbstractHigh-speed railway stations adopt track circuits equipped with impedance match bonds to effectively suppress the interference of unbalanced traction currents on the signaling system. Concerning the harsh working environment of the impedance match bonds, the present manual experience method for trouble shoot will inevitably affect the operation efficiency and safety. Under this background, this paper proposes a fault diagnosis method considering the impact of hidden risks on railway safety. This novel method is based on the risk assessment of different hazards to define the types of safety-related faults, selects the radial basis function kernel to establish a support vector machine prediction model, and optimizes the parameters through the differential evolution algorithm. Further, making use of the characteristic under different working scenarios of equipment in data processing, the fault diagnosis of the impedance match bonds is designed. The verification results based on measured data demonstrate that the high-risk fault diagnosis integrated model proposed in this paper can achieve 100% prediction accuracy under the given data set, realize accurate fault identification, and is helpful for safety maintenance and risk management of high-speed railway systems.KeywordsFault diagnosisRisk assessmentHigh-speed railwayImpedance match bondSupport vector machine

Due to the lack of training data and fuzziness of unknown defects, unknown defect detection, which aims to identify no clearly defined defects, is still a challenging task. In practical industrial scenarios, defects on a printed circuit board account generally for a small proportion, so the data sets are highly biased towards no defect class. To this end, unknown defect detection can be treated as an anomaly detection problem. According to this, a semi-supervised learning method is proposed in this study to solve the above-mentioned problems. Inspired by the conditional generative adversarial network, the authors propose an improved end-to-end architecture for detecting unknown defects. The designed architecture is composed of three networks: a generator, a discriminator, and an encoder. Among them, the generator and the discriminator are trained by competing with each other, while collaborating to learn the distribution of underlying concepts in the target class. During training, the authors only train normal samples, and unknown defects do not appear in the process. In the testing phase, unknown defects are detected by calculating the distance between generated samples and real samples under the feature space. Experimental results over several benchmark data sets show the effectiveness of the model and superiority on state-of-the-art approaches.

Defect detection with high precision is of great significance for printed circuit board (PCB) fabrication. Due to the lack of priori knowledge of categories and shape features, detection of unknown defects faces greater challenges than that of common defects. Inspired by similarity measurement, this study proposes a multi-layer deep feature fusion method to calculate the similarity between template and defective circuit board. Compared with conventional methods which divide the whole detection into two independent parts of hand-designed features and similarity measurement, the authors end-to-end model is designed to combine these two parts for joint optimisation. First, the Siamese network is utilised as their backbone architecture for feature extraction of pairwise images. And then the spatial pyramid pooling network is incorporated into the feature maps of each convolutional module to fuse the multi-scale feature vectors. Finally, the discriminative feature embedding and similarity metric are obtained by using the contrastive loss during the training process. Experimental results show that the proposed model has better performance in detecting and locating unknown defects in bare PCB images than traditional similarity measurement methods. Moreover, our method is promising for further improvement of defect detection with less training image pairs and more accurate detection results.

Printed circuit board (PCB) defect detection is one of the primary problems in quality control of the most electronic products. Usually, the industrial PCB imagery has high resolution, but defects take up a small proportion (often only ∼10 pixels in size), which makes it difficult to use traditional machine vision methods. To this end, a novel single shot object detector (SSDT) is proposed for tiny defect detection in PCBs in this study. Specifically, a semantic ascending module, which propagates the semantic property of deep layers to shallow layers, is presented by fusing features of different levels. An attention mechanism is utilised to learn the relationship of the features to be fused across channels and a shuffle module is used to eliminate the aliasing effect after fusion. Moreover, the improved non-maximum suppression is proposed to extenuate the overlap effect for testing the whole PCB image. The proposed detector can rapidly detect tiny defects and the results of SSD and SSDT are further compared not only in PCB defect dataset but also the object detection public dataset PASCAL VOC2007 where SSDT achieves 81.3% mAP, better than SSD (79.5%). In final, the proposed detector is validated to be robust to rotation and blur.

Defects detection is an extremely important part in the production of printed circuit board (PCB) to guarantee the quality and reliability. A widely used and researched method for this task is referential comparison method. However, this method gets poor performance on the situation that PCB moves on the conveyor, due to the lack of ability to register test images with referential images. Therefore, accurate image registration which estimates the affine transformation between the captured test images and the referential images becomes an urgent problem to be solved. In this study, a spatial transformer network is proposed. In particular, a recurrent image registration strategy is introduced to step-by-step register the images in a recurrent progress. Furthermore, a referential part is designed to help training the network. Besides, in order to simulate the real moving PCB images and train the proposed model, a factitious dataset is generated by applying random affine transformations to real PCB images. Experiments show that recurrent spatial transformer network can achieve pixel-level accurate image registration. The defects detection precision of referential comparison method has a great improvement by using the registration algorithm.

National key RD Specialized Research Fund for Strategic and Prospective Industrial Development of Shenzhen City [ZLZBCXLJZI20160729020003]