• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.109.2-109
• /
• 2001

In the PCB assembly lines, as components become more complex and smaller, the conventional inspection method using traditional ICT and function test show their limitations in application. The automatic optical inspection(AOI) gradually becomes the alternative in the PCB assembly line. In Particular, the PCB inspection machines need more reliable and flexible object recognition algorithms for high inspection accuracy. The conventional AOI machines use the algorithmic approaches such as template matching, Fourier analysis, edge analysis, geometric feature recognition or optical character recognition (OCR), which mostly require much of teaching time and expertise of human operators. To solve this problem, in this paper, a statistical learning based part recognition method is proposed. The performance of the ...

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.5
• /
• pp.58-65
• /
• 2016

Recent frequent occurrence of urban sinkhole serves as a momentum of the periodic inspection of sewer pipelines. Sewer inspection using a CCTV device needs a lot of time and efforts. Many of previous studies which reduce the laborious tasks are mainly interested in the developments of image processing S/W and inspection H/W. However there has been no attempt to find meaningful information from the existing CCTV images stored by the sewer maintenance manager. This study adopts a cross-correlation based image processing method and extracts location data of sewer inspection device from CCTV images. As a result of the analysis of time-location relation, it shows strong correlation between the device's stand times and the sewer damages. In case of using this method to investigate sewer inspection CCTV images, it will save the investigator's efforts and improve the sewer maintenance efficiency and reliability.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.14 no.4
• /
• pp.309-316
• /
• 2008

This article discusses the legal character and admissible scope of inspection and police questioning of a vessel with force in comparison with the systems of the US and Japan. The author focuses on the factual differences between vessels and cars which justifies the varying standard. A ship at sea may easily slip away and destroy evidence while authorities attempt to get a warrant. Thus, a warrantless boarding and safety inspection could be validated because of the exigent circumstances of the sea.

• Journal of Families and Better Life
• /
• v.25 no.2 s.86
• /
• pp.1-12
• /
• 2007

This is an investigative study to consider children's COA by parent's problem drinking and their psychological-social character by the COA. According to the results of this study, almost half of the children's COA, among those who have problem drinking parents, demonstrated high dangerous lever in the lower factors, such as emotional character, personnel relative character, and co-dependent character. Results of the inspection into the differences between the psyrhological-social characters, according to the danger lever of the children's COA, suggested the children's danger lever is higher, the self-efficiency and adaptable flexibility, which are the psychological-social characters, are lower, and there are no special differences in the social-support.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.444-449
• /
• 1996

The semiconductor, which is precision product, requires many inspection processes. The surface conditions of the semiconductor chip affect on the functions of the semiconductors. The defects of the chip surface are cracks or voids. As general inspection method requires many inspection procedure, the inspection system which searches immediately and precisely the defects of the semiconductor chip surface is required. We suggest the detection algorithm for inspecting the surface defects of the semiconductor surface. The proposed algorithm first regards the semiconductor surface as random texture and point spread function, and secondly presents the character of texture by linear estimation theorem. This paper assumes that the gray level of each pixel of an image is estimated from a weighted sum of gray levels of its neighbor pixels by linear estimation theorem. The weight coefficients are determined so that the mean square error is minimized. The obtained estimation window(two-dimensional estimation window) characterizes the surface texture of semiconductor and is used to discriminate the defects of semiconductor surface.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.9-14
• /
• 2018

The vision system is a device for acquiring images and analyzing and discriminating inspection areas. Demand for use in the automation process has increased, and the introduction of a vision-based inspection system has emerged as a very important issue. These vision systems are used for everyday life and used as inspection equipment in production processes. Image processing technology is actively being studied. However, there is little research on the area definition for extracting objects such as character recognition or semiconductor packages. In this paper, define a region of interest and perform edge extraction to prevent the user from judging noise as an edge. We propose a noise-robust alignment correction model that can extract the edge of a region to be inspected using the distribution of edges in a specific region even if noise exists in the image. Through the proposed model, it is expected that the product production efficiency will be improved if it is applied to production field such as character recognition of tire or inspection of semiconductor packages.

• Nuclear Engineering and Technology
• /
• v.25 no.3
• /
• pp.424-429
• /
• 1993

Numeric characters are printed at the end part of nuclear fuel rod containing nuclear pellets. Fuel rods are discriminated and managed systematically by these characters in the process of producing fuel assembly. The characters are also used to examine manufacturing process of fuel rods in the survey of burnup efficiency as well as in inspection of irradiated fuel rod. Therefore automatic character recognition is one of the most important technologies in automatic manufacture of fuel assembly. In this study, character recognition system is developed. In the developed system, mesh feature extracted from each character written in the fuel rod has been compared with reference feature value stored in database, and the character is thus identified. In the result of experiment, 95.83 percent recognition rate is achievable.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.245-254
• /
• 2002

IC package marking inspection system using machine vision locates and identifies the target elements from input image, and decides the quality of marking by comparing the extracted target elements with the standard patterns. This paper proposes an adaptive multi-level thresholding (AMLT) method which is suitable for a series of operations such as locating the target IC package, extracting the characters, and detecting the Pinl dimple. It also proposes a dynamic matching unit selection (DMUS) method which is robust to noises as well as effective to catch out the local marking errors. The main idea of the AMLT method is to restrict the inputs of Otsu's thresholding algorithm within a specified area and a partial range of gray values. Doing so, it can adapt to the specific domain. The DMUS method dynamically selects the matching unit according to the result of character extraction and layout analysis. Therefore, in spite of the various erroneous situation occurred in the process of character extraction and layout analysis, it can select minimal matching unit in any environment. In an experiment with 280 IC package images of eight types, the correct extracting rate of IC package and Pinl dimple was 100% and the correct decision rate of marking quality was 98.8%. This result shows that the proposed methods are effective to IC package marking inspection.