In the manufacture of ceramic resonators, defects on surfaces can directly affect the working stability of resonator products. Due to extreme scarcity of abnormal resonator image samples containing defect textures, traditional computer vision algorithms have difficulty learning the key data distribution characteristics of abnormal resonators, leading to poor detection results. To solve this problem, this paper proposes a resonator defect detection method based on single image generation and deep learning classification. By training SinGAN model on a single real resonator defect image, we learn the spatial and textural features on the image and then we can utilize the trained model to create seemingly realistic fake surface crack images from several sketch map drawings, therefore effectively increasing the number of abnormal resonator samples. We train a YOLOv3 object detection model on the enlarged dataset only containing fake abnormal resonator samples and try to detect cracks on new real defect resonators. Experiments show that our proposed method has better image generation quality compared with previous methods and the YOLOv3 model bounds the real cracks successfully, proving that using a single defect sample to detect more and more defective images is feasible. More importantly, our method can be commonly used in classification and detection tasks of industrial products which have a similar data distribution.
Mura is a phenomenon in which the displays have various uneven display defects. The band-shaped Mura has the characteristics of irregular shape and different sizes. And the new shapes and sizes of Mura may appear at any time during the inspection process. Therefore, traditional image algorithms are difficult to detect the band-shaped Mura anomaly. In response to the above problems, this paper proposes the Res-unetGAN network, which is an unsupervised anomaly detection method based on generative adversarial network. We design resnet50 as the encoding network of the generator to obtain the latent feature vectors. To improve the quality of reconstructed samples, we combine the skipconnection structure into the generator to guide the decoder. The discriminator is a convolutional neural network based on the Depthwise Separable Convolution. The purpose is to distinguish between normal samples and reconstructed samples, and form a game process with the generator. The network only needs normal screen samples during the training process. In the test, since the Mura sample has not been trained, the reconstruction error score of the Mura sample will be higher. After repeated experiments on the band-shaped Mura data set, the highest auc of 0.995 was obtained, which is better than several models for comparison.
Large scale stencil images used for surface mount technology (SMT) always have more than ten thousand closed graphics(stencil holes). It is difficult to find corresponding information from those graphics in stencil image registration. Here, we propose a novel method which is based on two-node tree, differed from traditional ones. The two-node tree is special, which has only two nodes in a layer. It functions as selecting feature points. The set of feature points with the erroneous can find the most reasonable projection transformation model by the simplified RANSAC algorithm. We adopt different types of defective stencil images to verify the proposed method. Experimental results fully show its robustness and high-tolerant rate.
By exploiting those novel transport phenomena at nanoscale, the nanochannel system has shown electrically maneuverable conductance, suggesting the potential usage as neuromorphic devices. However, several critical features of biological synapses, i.e., the memorable and gradual conductance modulation, were seldom reported in the system. In this work by imposing room-temperature ion liquid (IL) and KCl solution into the two ends of nanochannel system, we demonstrate that this electrical manipulation of nanochannel conductance becomes nonvolatile and capable of mimicking the analog behaviors of synapses. The mechanism of gradual conductance tuning is identified as the voltage-induced movement of the interface between the immiscible RTIL and KCl solution according tofluorescencetechnique.
In this paper, we designed a compact Mie scattering lidar system for ocean-atmospheric horizontal visibility measuring and an algorithm used for obtaining the visibility of the aerosol. The effective range of our lidar system was from 300 m to 3 km with a 7.5-m horizontal range resolution and a 1-min time resolution. To reduce the uncertainty caused by using slope method which based on the hypothesis that either molecule or aerosol components exist in the atmosphere, we used the two-component fitting method to retrieve the aerosol extinction coefficient and the calculated the visibility based on Koschmieder’s theory. The whole system was powered by electricity supply which made it easy mounting on a ship or observation station by the sea. Lots of experiments were conducted laboratory to ensure the veracity and stability. In 2016 summer, we joined the cruise survey in China Bo-Hai and Huang-Hai Sea. Site experiments were carried out on the research vessel ‘Dongfanghong 2’. The results showed that the visibility values obtained by our system were in good agreement with the value set by the visibility meter and our lidar system was able to achieve visibility measuring under different weather conditions.
Since the stencil image used for surface mount technology (SMT) always has various defects such as less holes and burrs in the laser processing and imaging, it is indispensable to detect those flaws with high accuracy. An automatic registration lies at the root of identifying defects. In this paper, a novel automatic registration algorithm for stencil images is proposed. According to the distribution probability density of the coordinates of gravity center points in a stencil image, the adaptive parameter DBSCAN clustering algorithm is adopted to classify those points. As a result, we could find corresponding gravity center points (feature points) in the stencil image and its standard design file respectively. A transformation matrix between the stencil image and its standard design file is obtained by the feature points. Experiments have shown that this automatic registration algorithm can be well adapted to the stencil images with random defects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.