A novel method based on the curvelet transform and active contour method to automatically detect the ice edge in Synthetic Aperture Radar (SAR) imagery is proposed. The method utilizes the location of high curvelet coefficients to determine regions in the image likely to contain the ice edge. Using an ice edge from passive microwave sea ice concentration for initialization, these regions are then joined using the active contour method to obtain the final ice edge. The method is evaluated on four dual polarization SAR scenes of the Labrador sea. Through comparison of the ice edge with that from image analysis charts, it is demonstrated that the proposed method can detect the ice edge effectively in SAR images. This is particularly relevant when the marginal ice zone is diffuse or the ice is thin, and using the definition of ice edge from the passive microwave ice concentration would underestimate the ice edge location. It is expected that the method may be useful for operations in marginal ice zones, such as offshore drilling, where a high resolution estimate of the ice edge location is required. It could also be useful as a first guess for an ice analyst, or for the assimilation of SAR data.
Automatic vision inspection technology shows a high potential for quality inspection, and has drawn great interest in micro-armature manufacturing. Given that the inspection process is highly influenced by the lack of real standardization and efficiency performed with the human eye, thus, it is necessary to develop an automatic defect detection process. In this work, an elaborated vision system for the defect inspection of micro-armatures used in smartphones was developed. It consists of two parts, the front-end module and the deep convolution neural networks (DCNNs) module, which are responsible for different areas. The front-end module runs first and the DCNNs module will not run if the output of the front-end module is negative. To verify the application of this system, an apparatus consisting of an objective table, control panel, and a camera connected to a Personal Computer (PC) was used to simulate an industrial position of production. The results indicate that the developed vision system is capable of defect detection of micro-armatures.Recently, deep convolutional neural networks (DCNNs) have been proved to be important methods in visual detection. However, some classical methods should still be considered. Literature [6] mentioned above is an example. For instance, in order to get better parameters, a suitable smart manufacturing strategy for real industrial conditions was proposed. The results of this dataset showed that the Adaboost ensembles provided the highest accuracy and were more easily optimized than ANNs [7]. Obviously, for now, there are some limitations with using classical methods alone or using DCNNs directly. For classical methods, for example, they usually come with high complexity of programming and less tolerance to data variability. With regard to the DCNNs, a large number of samples are needed for network training and the iterative optimization of parameters is partly a black-box operation [8].In the industrial applications, part defects in the samples can be easily identified with a picture by the classical computer vision method. Therefore, we do not need to feed the whole picture into the network for discrimination, which can reduce the number of features to be identified. As a result, the network is easier to converge. Therefore, by combining the classical image recognition method and DCNNs, the landing speed of deep learning technology in industrial applications can be effectively improved.In this work, an intelligent detection system that combined the classical computer vision method and DCNNs was designed to automatically detect the quality defects of micro-motor armatures. Firstly, the quality, excluding the region of copper wire crossing (ROC), is decided based on the classical computer vision technology. If the first result is positive, the ROC will be extracted and sent to the DCNNs for identification. If the result is still positive, the image is a defect-free sample, otherwise the whole image is labeled defective. In the experiments, this system works very fast and presen...
In this paper, a complete system based on computer vision and deep learning is proposed for surface inspection of the armatures in a vibration motor with miniature volume. A device for imaging and positioning was designed in order to obtain the images of the surface of the armatures. The images obtained by the device were divided into a training set and a test set. With continuous experimental exploration and improvement, the most efficient deep-network model was designed. The results show that the model leads to high accuracy on both the training set and the test set. In addition, we proposed a training method to make the network designed by us perform better. To guarantee the quality of the motor, a double-branch discrimination mechanism was also proposed. In order to verify the reliability of the system, experimental verification was conducted on the production line, and a satisfactory discrimination performance was reached. The results indicate that the proposed detection system for the armatures based on computer vision and deep learning is stable and reliable for armature production lines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with đź’™ for researchers
Part of the Research Solutions Family.