• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.184-186
• /
• 2004

This paper is about vision system that exhibits automatic examination of the conditions of shaft's worm. The system is composed of three part : image acquisition, vision algorithm, and user interface. The image acquisition part is composed of motor control, illumination and optics. The vision algorithm examines the parts by labeling algorithm using shaft image. User interface is divided into two parts, user interface for feature registering with control value settings and user interface for examination operation. The automatic inspection system of this research is a tool for final examination of shaft worm. This tool can be practically used in production lines with simple adjustments.

• Journal of Computing Science and Engineering
• /
• v.10 no.4
• /
• pp.128-136
• /
• 2016

It is impossible for any human being to analyze the more than 500 million tweets that are generated per day. Lexical ambiguities on Twitter make it difficult to retrieve the desired data and relevant topics. Most of the solutions for the word sense disambiguation problem rely on knowledge base systems. Unfortunately, it is expensive and time-consuming to manually create a knowledge base system, resulting in a knowledge acquisition bottleneck. To solve the knowledge-acquisition bottleneck, a topic signature is used to disambiguate words. In this paper, we evaluate the effectiveness of various features of newspapers on the topic signature extraction for word sense discrimination in tweets. Based on our results, topic signatures obtained from a snippet feature exhibit higher accuracy in discriminating company names than those from the article body. We conclude that topic signatures extracted from news articles improve the accuracy of word sense discrimination in the automated analysis of tweets.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10b
• /
• pp.923-928
• /
• 1990

This paper describes the design and implementation of a real-time, high-precision vision system and its application to SMT(surface mounting technology) automation. The vision system employs a 32 bit MC68030 as a main processor, and consists of image acquisition unit. DSP56001 DSP based vision processor, and several algorithmically dedicated hardware modules. The image acquisition unit provides 512*480*8 bit image for high-precision vision tasks. The DSP vision processor and hardware modules, such as histogram extractor and feature extractor, are designed for a real-time excution of vision algorithms. Especially, the implementation of multi-processing architecture based on DSP vision processors allows us to employ more sophisticated and flexible vision algorithms for real-time operation. The developed vision system is combined with an Adept Robot system to form a complete SMD system. It has been found that the vision guided SMD assembly system is able to provide a satisfactory performance for SND automation.

• Language and Information
• /
• v.11 no.2
• /
• pp.67-86
• /
• 2007

The semantic literature on definiteness and specificity shows that the former is relatively an established notion, whereas the latter is still a vague notion that needs to be more clarified and confirmed. Given this, Ionin (2006) argues for the reality of specificity based on the informal use of this. She proposes this in spoken English as a specificity marker which has a semantic feature indicating "peaker intent to refer" and "noteworthiness." She also provides as evidence the results of some crosslinguistics studies including an L2 acquisition study with both L1-Russian and L1-Korean L2-English learners. However, this paper will argue that the informal use of this does not seem to mark specificity according to Ionin's definition of specificity. It will also be argued that the L2 acquisition study cannot be used as evidence for the reality of specificity. Based on these arguments, this paper will try to redefine specificity, based on the notions of existence and uniqueness.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.903-904
• /
• 2006

This paper is about a vision system that exhibits automatic examination of the conditions of shaft's worm. The system is composed of three part : image acquisition, vision algorithm, and user interface. The image acquisition part is composed of motor control, illumination and optics. The vision algorithm examines the parts using shaft image. User interface is divided into two parts, user interface for feature registering with control value settings and user interface for examination operation. The automatic inspection system introduced in this paper can be used as a tool for final examination of shaft worm.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.4
• /
• pp.51-56
• /
• 2010

As the price of image acquisition component becomes low enough, the compact and easily accessible handheld devices are generally equipped with image acquisition functionality. This trend speeds up various applications in diverse areas such as image related services and software. Therefore users strongly need to identify their images effectively and efficiently so that the duplicated images are perceived as one physical entity. In order to handle this environment, we propose a number of methods that generate image identifiers utilizing fundamental image features. In this paper, we analyze the identifier generation methods in terms of various size patterns, especially for tiny size cases, since the small images does not contain abundant pixels for feature extraction. In this paper, experimental evaluation over identifier generation methods' behavior according to different sizes is demonstrated.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.285-289
• /
• 2006

In this paper, a design and implementation of GPS/Galileo software receiver is given. As a GPS receiver, it is able to perform every function of receiver such as acquisition, code and carrier tracking, navigation bit extraction, navigation data decoding, pseudorange calculations, and position calculations. A method to acquire and track the Galileo BOC(1,1) signal is also required because the correlation of BOC(1,1) signal has multiple peaks different from that of GPS signal. Therefore, a method to detect the main-peak in correlation function of BOC signal is required to avoid false acquisition. In this paper, very-early, very late correlation is implemented to track the correct main peak. The performance of implemented GPS/Galileo software receiver with BOC(1,1) signal tracking feature is evaluated with GPS/Galileo IF signal generator.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.10a
• /
• pp.75-80
• /
• 2003

Most of the control point surveying use a triangulation point and a bench mark with Total Station and Level. nowadays, the research is being accomplished for practical use of GPS. but In this study the optimum time and the optimum occupation time are analyzed, so as to examine possibility of the control point surveying that use GPS continuous station data of National Geography Institute. Also, The efficient surveying methods that compare the result of data that processed using broadcast ephemeris with the result of data that processed using precise ephemeris. As a result of that, Error feature analysis of the control point surveying in connection with GPS continuous observation will provide us estimation of errors and efficient topography information acquisition

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.385-387
• /
• 2004

In this paper, we have designed a fingerprint cognition system based on the embedded Linux. The proposed algorithm in this paper use the wavelet transform to derive the special feature vector from the captured fingerprint and a probabilistic neural network is used to compare the feature vectors for the fingerprints. The system consists of server PC based on the Linux and the client based on the embedded Linux. The client is a Tynux box-x board using the PXA-255 CPU. For the acquisition of the fingerprint image, we use d the AS-S2 semiconductor sensor. The system is likely to be used to develop a police inspection system.