• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.1
• /
• pp.82-88
• /
• 2005

The damage inspection of container surface is performed by the expert inspectors at the container terminal gate of harbor. In this paper, we substitute the expert's capability with the damage inspection system using the artificial intelligent control algorithm and vision system, so we can improve the work environment and effectively decrease the inspection time and cost. Firstly, using six CCD cameras attached to the terminal gate, whole container is partially captured according to eleven sensors aligned with the entering direction of container. Captured partial images are inspected by the fuzzy system which the expert's technology is embedded. Next, we compose partial images to be a complete container image through the correlation coefficient method. Complete container image is saved to solve future troublesome problems. In this paper, the effectiveness of the proposed system was verified through the field test.

• Journal of Ocean Engineering and Technology
• /
• v.32 no.3
• /
• pp.158-165
• /
• 2018

Generally, container ships contain cargo holds with cell guides that serve to increase the container loading and unloading efficiency, minimize the space loss, and fix containers during the voyage. This paper describes a new quality management system for the cell guides of container ships (the so-called Trim Cell Guide system). The main functions of this system are the trimming of the point cloud obtained using a 3D scanner and an inspection simulation for cell guide quality. In other words, the raw point cloud of cell guides after construction is measured using a 3D scanner. Here, the raw point cloud contains a lot of noise and unnecessary information. Using the GUI interface supported by the system, the raw point cloud can be trimmed. The trimmed point cloud is used in a simulation for cell guide quality inspection. The RANSAC (Random Sample Consensus) algorithm is used for the transverse section representation of a cell guide at a certain height and applied for the calculation of the intervals between the cell guides and container. When the container hits the cell guides during the inspection simulation, the container is rotated horizontally and checked again for a possible collision. It focuses on a system that can be simulated with the same inspection process as in a shipyard. For a practicality review, we compared the precision data gained from an inspection simulation with the measured data. As a result, it was confirmed that these values were within approximately ${\pm}2mm$.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1684-1688
• /
• 2005

In this paper, authentication technologies for X-ray inspection images in container merchandises are introduced and a method of authentication for X-ray inspection images is proposed. Until now, X-ray images of container merchandises have been managed without any authentication of inspection results and environments, it means that there was no any action for protection of illegal copy and counterfeiting of X-ray images from inspection results. Here, authentication identifies that who did inspect container X-ray images and, whether the container X-ray images were counterfeited or not. Our proposed algorithm indicates to put important information about X-ray inspection results on an X-ray image without affecting quality of the original image. Therefore, this paper will be useful in determining an appropriate technology and system specification for authentication of X-ray inspection images. As a result of experiment, we find that the information can be embedded to X-ray image without large degradation of image quality. Our proposed algorithm has high detection ratio by Quality 20 of JPEG attack.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.3
• /
• pp.1035-1039
• /
• 2010

Activation products generated by photoneutrons in concrete shielding wall around electron linac were estimated for a high energy X-ray container cargo inspection system. Monte carlo code, MCNPX2.5.0 was used for reference system of 9MeV fixed type dual-direction container cargo inspection system installed at major harbors in Korea. Activation products inventory generated by photoneutron (n,$\gamma$) reaction are estimated, and then radiation dose rate is calculated from the results.

• The monthly packaging world
• /
• s.252
• /
• pp.45-49
• /
• 2014

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2004.11a
• /
• pp.254-254
• /
• 2004

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1298-1304
• /
• 2019

Since the 9·11 terror attack in 2001, the Maritime Logistics Security System has been strengthened and required X-ray image for every imported cargos from manufacturing countries to United States. For scanning cargos, the container inspection systems use high energy X-rays for examination of contents of a container to check the nuclear, explosive, dangerous and illegal materials. Nowadays, the X-ray cargo scanners are established and used by global technologies for inspection of suspected cargos in the customs agency but these technologies have not been localized and developed sufficiently. In this paper, we propose the X-ray array detector system which is a core component of the container scanning system. For implementation of X-ray array detector, the analog and digital signal processing units are fabricated with integrated hardware, FPGA logics and GUI software for real-time X-ray images. The implemented system is superior in terms of resolution and power consumption compared to the existing products currently used in ports.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2003.05a
• /
• pp.365.1-365.1
• /
• 2003

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1711-1717
• /
• 2020

X-ray of up to 9MeV are used for container inspection. X-ray intensity must be maintained stably regardless of changes in time. If dose is not constant, it may affect the image quality, and as a result, may affect the inspection of abnormal cargo. Therefore, to acquire high-quality images, continuous dose monitoring is required. In this study, the ion-chamber based device was developed for monitoring the dose change in high-energy x-ray. And to estimate the performance of signal-processing device change according to the environmental change, the output changing due to the change of temperature and humidity was observed. In addition, verification of the device was performed by measuring the output change. As a result of the measurement, there was no significant difference in performance due to changes in temperature and humidity, and the change in output according to the change in exposure was linear. Therefore, it was found that the developed device is suitable for the dose monitoring of high-energy x-ray.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.474-478
• /
• 2024

In this paper, we proposes a deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers. The proposed deep learning network is specifically designed for pharmaceutical containers by using data produced in real manufacturing environments, leading to more accurate quality inspection. Additionally, the use of an inline-capable deep learning network allows for an increase in inspection speed. The development of the deep learning network for quality inspection in the multi-camera inline inspection system consists of three steps. First, a dataset of approximately 10,000 images is constructed from the production site using one line camera for foreign substance inspection and three area cameras for dimensional inspection. Second, the pharmaceutical container data is preprocessed by designating regions of interest (ROI) in areas where defects are likely to occur, tailored for foreign substance and dimensional inspections. Third, the preprocessed data is used to train the deep learning network. The network improves inference speed by reducing the number of channels and eliminating the use of linear layers, while accuracy is enhanced by applying PReLU and residual learning. This results in the creation of four deep learning modules tailored to the dataset built from the four cameras. The performance of the proposed deep learning network for quality inspection in the multi-camera inline inspection system for pharmaceutical containers was evaluated through experiments conducted by a certified testing agency. The results show that the deep learning modules achieved a classification accuracy of 99.4%, exceeding the world-class level of 95%, and an average classification speed of 0.947 seconds, which is superior to the world-class level of 1 second. Therefore, the effectiveness of the proposed deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers has been demonstrated.