• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.157-163
• /
• 2022

Recently, with the development of automation in the industrial field, research on anomaly detection is being actively conducted. An application for anomaly detection used in factory automation is camera-based defect inspection. Vision camera inspection shows high performance and efficiency in factory automation, but it is difficult to overcome the instability of lighting and environmental conditions. Although camera inspection using deep learning can solve the problem of vision camera inspection with much higher performance, it is difficult to apply to actual industrial fields because it requires a huge amount of normal and abnormal data for learning. Therefore, in this study, we propose a network that overcomes the problem of collecting abnormal data with 72 geometric transformation deep learning methods using only normal data and adds an outlier exposure method for performance improvement. By applying and verifying this to the MVTec data set, which is a database for auto-mobile parts data and outlier detection, it is shown that it can be applied in actual industrial sites.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.221-232
• /
• 2021

This study analyzed co-registration results according to the geometric processing level of reference image, which are Level 1R and Level 1G provided from KOMPSAT-3 and KOMPSAT-3A images. We performed co-registration using each Level 1R and Level 1G image as a reference image, and Level 1R image as a sensed image. For constructing the experimental dataset, seven Level 1R and 1G images of KOMPSAT-3 and KOMPSAT-3A acquired from Daejeon, South Korea, were used. To coarsely align the geometric position of the two images, SURF (Speeded-Up Robust Feature) and PC (Phase Correlation) methods were combined and then repeatedly applied to the overlapping region of the images. Then, we extracted tie-points using the SURF method from coarsely aligned images and performed fine co-registration through affine transformation and piecewise Linear transformation, respectively, constructed with the tie-points. As a result of the experiment, when Level 1G image was used as a reference image, a relatively large number of tie-points were extracted than Level 1R image. Also, in the case where the reference image is Level 1G image, the root mean square error of co-registration was 5 pixels less than the case of Level 1R image on average. We have shown from the experimental results that the co-registration performance can be affected by the geometric processing level related to the initial geometric relationship between the two images. Moreover, we confirmed that the better geometric quality of the reference image achieved the more stable co-registration performance.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.1
• /
• pp.17-26
• /
• 2012

This paper presents an image processing-based validation method for unrecognizable numbers in severely distorted license plate images which have been degraded by various factors including low-resolution, low light-level, geometric distortion, and periodic noise. Existing vehicle license plate recognition (LPR) methods assume that most of the image degradation factors have been removed before performing the recognition of printed numbers and letters. If this is not the case, conventional LPR becomes impossible. The proposed method adopts a novel approach where a set of reference number images are intentionally degraded using the same factors estimated from the input image. After a series of image processing steps, including geometric transformation, super-resolution, and filtering, a comparison using cross-correlation between the intentionally degraded reference and the input images can provide a successful identification of the visually unrecognizable numbers. The proposed method makes it possible to validate numbers in a license plate image taken under low light-level conditions. In the experiment, using an extended set of test images that are unrecognizable to human vision, the proposed method provides a successful recognition rate of over 95%, whereas most existing LPR methods fail due to the severe distortion.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.6
• /
• pp.621-626
• /
• 2010

For geometric correction of high-resolution images, the authors matched corresponding objects between a large-scale digital map and a QuickBird image to obtain the coefficients of the first order polynomial. Proximity corrections were performed, using the Boolean operation, to perform automated matching accurately. The modified iterative closest point (ICP) algorithm was used between the point data of the surface linear objects and the point data of the edge objects of the image to determine accurate transformation coefficients. As a result of the automated geometric correction for the study site, an accuracy of 1.207 root mean square error (RMSE) per pixel was obtained.

• Journal of Korea Multimedia Society
• /
• v.6 no.7
• /
• pp.1139-1148
• /
• 2003

Biometric system has been studied as an optimal solution for preventing or reducing the peculation or loss of ID. Nowadays, face recognition has been spot-lighted as a future biometric system because it is not forced to contact the part of human body with the specific input area of the system. However, there is some limitations to get the constant facial features because the size of face area is varied by the capturing distance or tilt of the face. In this paper, we can extract constant facial features within the predefined threshold using the simple geometric processing such as image scaling, transformation, and rotation for frontal face images. This face recognition system identifies faces with 92% of accuracy for the 400 images of 40 different people.

• Fashion & Textile Research Journal
• /
• v.16 no.1
• /
• pp.1-12
• /
• 2014

Leggings are recognized as unique fashion items that meet the needs of customers to express individuality due to their protective and thermal functions. They are highly practical fashion items that show a casual, street and sportive style with a noted influence on outdoor leisure fields. This study analyzes the sociocultural background for the spread of leggings as well as their design characteristics, coordination characteristics and authentic characteristics. The formative characteristics of modern legging designs are as follows. First, the shapes of modern leggings are ankle-length, calflength, above-knee, knee-length, stirrup and top of the foot-length. Leggings are transformed in many ways: length-expansion, side-slit, unbalanced length, variations of straps, cut-out, trimmings, pattern transformation and complex form. Second, modern leggings contain achromatic colors in modern and sensual image, vivid colors in sportive image and metallic colors futuristic and technical image. Third, leggings patterns value originality, uniqueness and rarity as shown by printed geometric patterns, hand crafted geometric and natural patterns, and abstract patterns expressed through various materials and themes. Fourth, modern leggings' textures are categorized into erotic, simply-functional, seasonless, glossy, and metallic. Functional and fashionable leggings reflect the psychological needs of modern society. This study suggests a direction for the development of legging designs and provides a theoretical database for higher value-added leggings business.

• School Mathematics
• /
• v.15 no.4
• /
• pp.957-973
• /
• 2013

This study analyzed Secondary Mathematically Gifted' mathematical thinking processes demonstrated from the activities. They configured regular triangle tessellations in the Non-Euclidean hyperbolic disk model. The students constructed the figure and transformation to construct the tessellation in the poincare disk. gsp file which is the dynamic geometric environmen, The students were to explore the characteristics of the hyperbolic segments, construct an equilateral triangle and inversion. In this process, a variety of strategic thinking process appeared and they recognized to the Non-Euclidean geometric system.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.283-290
• /
• 2005

The mismatched allocation of watermarking position due to parallel translation, rotation, and scaling distortion is a problem that requires an answer in watermarking. In this paper, we propose a watermarking method robust enough to hold against geometrical distorting using restoration pattern matching. The proposed method defines restoration pattern, then inserts the pattern to a watermark embedded image for distribution. Geometrical distortion is verified by comparing restoration pattern extracted from distributed image and the original restoration pattern inserted to the image. If geometrical distortion is found, inverse transformation is equally performed to synchronize the watermark insertion and extraction position. To evaluate the performance of the proposed method, experiments in translation, rotation, and scaling attack are performed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.348-351
• /
• 2002

Recently, the medical imaging field has been digitalized by the development of computer science and digitization of the medical devices. There are needs of the medical imaging database service and long term storage today because of the installation of PACS system following DICOM standards, telemedicine and etc. and ,also, the illegal distortion of the medical information, data authentication and copyright are being happened. In this paper, we propose watermarking technique as a method which can protect private informations and medical imaging from geometric distortion. Because many watermarks for images are sensitive to geometric distortion, we present a algorithm that is insensitive to RST distortion in medical image. we observed the robustness against several of the signal processing and attacks in medical imaging field by embedding watermark after making a region which is insensitive to RST distortion by using FFT and LPM transformation.

• Korean Institute of Interior Design Journal
• /
• v.14 no.3 s.50
• /
• pp.95-102
• /
• 2005

Guarini's architectural contribution has simply focused on the dome structure that has been known to us; however, his geometric and spatial construction has been overlooked so far Through this study, it has been demonstrated that the dome structure was simply part of geometrical forms that Guarini wanted to express ultimately and it functioned as a geometrical element such as the network combined with the entire spatial structure. The purpose of this study is to reevaluate Guarini's architectural thought by means of investigating the ultimate principles of spatial composition appeared in the late Baroque architecture through the analysis of the principles of spatial composition and organized formal Idioms by Guarini's geometrical concepts. Besides, it has been assumed that such geometrical concepts by Guarini's mathematical proportion and his reiteration and change of diagrams could be clearly distinguished from the Classical geometry in the Renaissance and Guarini. suggested a way to create a new space through more active and amusing application and transformation. In this aspect, Guarini's principles of geometric composition will be one of the role models that need to be seriously reconsidered in chaotic reality of modern architecture.