Accurate and rapid measurement of the notch of vehicle accessories produced in real time on the assembly line is an important way to reduce labor cost and improve production efficiency. The current dimension measurement algorithms pay attention to the extraction of edge high-precision contour which needs complex parameter adjustment and despise the extraction of contour corner information. It is difficult to be used in industrial real-time detection environment because of its large amount of calculation, easy to be disturbed by the environment and weak robustness. In order to realize the noncontact, high-precision and wide application range of notch length measurement based on machine vision, an algorithm is proposed to extract corner points with contour point features and contour edges with geometric restrictions, so as to finally obtain the length of notch. The algorithm uses moments to estimate the centroid coordinates and overall direction of the accessory, and calculates the distance to the centroid and the offset angle from the overall direction for each side of the accessory one by one. The results show that compared with the traditional corner extraction and line detection algorithms, the algorithm can extract the accessory corner and the notch length more accurately. The average processing time for the accessory image with a resolution of 200 pixels (vertical) × 600 pixels (horizontal) is 15 milliseconds, and the notch length can still be extracted for the slight shaking generated in the manufacturing process. The relative error of the extracted notch length is less than 1%, which is suitable for the industrial field environment with high requirements for real-time and robustness. It has the characteristics of strong adaptability and low cost.
As the core component of the photovoltaic system, the quality of solar cells determines the conversion efficiency of electric energy. Some strategies have been proposed to detect the crack of solar cells, but most of them can not detect the crack efficiently. This paper proposed a new two-stage method for microcrack detection in polycrystalline images based on contrastive learning. First, the input picture without a label is learned by SimCLR to obtain the representation of the image. In the second stage, the linear classifier is trained based on the fixed encoder and the representation. In the comparative experiment, unsupervised contrastive learning is compared with cross-entropy training and supervised contrastive learning. The experimental results show that the linear classifier trained on unsupervised representation achieves a top-1 accuracy of 78.39%, which is 7.42% higher than the supervised contrastive learning method, compared with supervised learning, the results are comparable.
KEYWORDS: Databases, Spatial analysis, Image segmentation, Fourier transforms, Visualization, Control systems, Human vision and color perception, Tolerancing, Detection and tracking algorithms, Binary data
Recently, a number of graph-based approaches have been proposed to detect salient regions in images. Although the graph is essential for these approaches, the graph construction method has not been studied in much detail. We propose a graph construction method that makes better use of multiple Gestalt principles. Specifically, spatial proximity, color similarity, and texture similarity between image regions are employed to choose different edges of the graph. Furthermore, the confliction among multiple Gestalt principles is solved using a primal rank support vector machines algorithm to compute the edge weights. Our experimental results on various salient region detection databases with comparisons to representative approaches demonstrate that the proposed graph construction method helps to detect salient objects in images.
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.