• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.239-246
• /
• 2009

In this paper, we propose a Korean character recognition method from outboard signboard images. We have chosen 808 classes of Korean characters by an analysis of frequencies of appearance in a dictionary of signboard names. The proposed method mainly consists of three steps: feature extraction, rough classification, and coarse classification. The first step is to extract a nonlinear directional segments feature, which is immune to the distortion of character shapes. The second step computes an ordered set of 10 recognition candidates using a minimum distance classifier. The last step reorders the recognition candidates using a Fisher discriminant measure. As experimental results, the recognition accuracy is 80.45% for the first choice, and 93.51% for the top five choices.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.205-211
• /
• 2019

Steganalysis is a technique that aims to detect and recover data hidden by steganography. Steganalytic methods detect hidden data by analyzing visual and statistical distortions caused during data embedding. However, for recovering the hidden data, they need to know which steganographic methods the hidden data has been embedded by. Therefore, we propose a hierarchical convolutional neural network (CNN) structure that identifies a steganographic method applied to an input image through multi-level classification. We trained four base CNNs (each is a binary classifier that determines whether or not a steganographic method has been applied to an input image or which of two different steganographic methods has been applied to an input image) and connected them hierarchically. Experimental results demonstrate that the proposed hierarchical CNN structure can identify four different steganographic methods (LSB, PVD, WOW, and UNIWARD) with an accuracy of 79%.

• Korean Journal of Geomatics
• /
• v.2 no.1
• /
• pp.37-46
• /
• 2002

Accurate classification of water area is an preliminary step to accurately analyze the flooded area and damages caused by flood. This step is especially useful for monitoring the region where annually repeating flood is a problem. The accurate estimation of flooded area can ultimately be utilized as a primary source of information for the policy decision. Although SAR (Synthetic Aperture Radar) imagery with its own energy source is sensitive to the water area, its shadow effect similar to the reflectance signature of the water area should be carefully checked before accurate classification. Especially when we want to identify small flood area with mountainous environment, the step for removing shadow effect turns out to be essential in order to accurately classify the water area from the SAR imagery. In this paper, the flood area was classified and monitored using multi-temporal RADARSAT SAR images of Ok-Chun and Bo-Eun located in Chung-Book Province taken in 12th (during the flood) and 19th (after the flood) of August, 1998. We applied several steps of geometric and radiometric calculations to the SAR imagery. First we reduced the speckle noise of two SAR images and then calculated the radar backscattering coefficient $(\sigma^0)$. After that we performed the ortho-rectification via satellite orbit modeling developed in this study using the ephemeris information of the satellite images and ground control points. We also corrected radiometric distortion caused by the terrain relief. Finally, the water area was identified from two images and the flood area is calculated accordingly. The identified flood area is analyzed by overlapping with the existing land use map.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.151-156
• /
• 2020

In this paper, we propose a watermark extraction method of omnidirectional images using CNN (Convolutional Neural Network) to improve the extracted watermark accuracy of the previous deterministic method that based on algorithm. This CNN consists of a restoration process of extracting watermarks by correcting distortion during omnidirectional image generation and/or malicious attacks, and a classification process of classifying which watermarks are extracted watermarks. Experiments with various attacks confirm that the extracted watermarks are more accurate than the previous methods.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.889-894
• /
• 2009

Accompanied by the rapid development of Computer Vision, Visual surveillance has achieved great evolution with more and more complicated processing. However there are still many problems to be resolved for robust and reliable visual surveillance, and the cast shadow occurring in motion detection process is one of them. Shadow pixels are often misclassified as object pixels so that they cause errors in localization, segmentation, tracking and classification of objects. This paper proposes a novel cast shadow removal method. As opposed to previous conventional methods, which considers pixel properties like intensity properties, color distortion, HSV color system, and etc., the proposed method utilizes observations about edge patterns in the shadow region in the current frame and the corresponding region in the background scene, and applies Laplacian edge detector to the blob regions in the current frame and the background scene. Then, the product of the outcomes of application determines whether the blob pixels in the foreground mask comes from object blob regions or shadow regions. The proposed method is simple but turns out practically very effective for Gaussian Mixture Model, which is verified through experiments.

• Journal of Welding and Joining
• /
• v.34 no.5
• /
• pp.41-46
• /
• 2016

Welding is an absolutely essential component of industries such as the automotive industry, the construction industry and even the aviation industry. Although it is a widespread technology it is still characterized by lots of uncertainties. This still requires well experienced and highly skilled workforce to design and perform safe welding processes. The early knowledge of distortion and residual stresses is almost an issue which is influenced mainly by the welding parameters and the fixture design. But more and more engineers want to know as well final properties of the assembled components. With the beginning of the computer age in the 1970s and 1980s last century, the numerical prediction of manufacturing processes using FEM was gradually getting better and has established itself in the industry since the 1990s as a standard tool. Unlike in metal casting and forming industry, however, the everyday use of FEM- simulation tools for welding processes eked out a shadowy existence for a long time. This paper will give a short classification of welding simulation types and a structured overview on the technical questions. Selected case studies and the benefits achieved through simulations with the software Simufact welding are discussed. Finally an outlook on future developments will be given.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.4
• /
• pp.590-597
• /
• 2011

The IDRS provides detection, classification and bearing/range estimation by performing wavefront curvature analysis on an intercepted active transmission from target. Especially, a estimate of the target bearing/range that significantly affects the optimal operation of own submarine is required. Target bearing/range can be estimated by wavefront curvature ranging which use the difference of time arrival at sensors. But estimation ambiguity occur in bearing/range estimation due to a number of peaks caused by high center frequency and limited bandwidth of the intercepted active transmission and distortion caused by noise. As a result the bearing/range estimation performance is degraded. To estimate target bearing/range correctly, bearing/range estimation method that eliminate estimation ambiguity is required. In this paper, therefore, for wavefront curvature ranging, NLS cost function with curve fitting method is proposed, which provide robust bearing/range estimation performance by eliminating estimation ambiguity. Through simulation the performance of the proposed bearing/range estimation methods are verified.

• Journal of the Society of Naval Architects of Korea
• /
• v.43 no.2 s.146
• /
• pp.197-205
• /
• 2006

In general, brackets found at tank boundary are design according to the Classification Society Rule. Since much man power is needed in manufacturing the brackets stiffened by flange, it is necessary to suggest alternative designs, of which flanges are removed, through the rigorous structural analysis. In this paper non-linear structural analysis for brackets with and/or without flange have been carried out to examine their structural behavior and ultimate strengths. Alternative designs for brackets are suggested based on the results of ultimate strength analysis so that the alternative brackets have the similar level of strength and stiffness to the original brackets. It has been seen that the structural safety of alternative brackets proposed in this paper are beyond the appropriate level. The primary benefit of replacing the original brackets by the alternatives is the reduction of man power in manufacturing brackets and 10 to 15% weight saving can be expected in additional. This paper ends with some comments about the extension of the present study.

• Journal of Multimedia Information System
• /
• v.8 no.3
• /
• pp.147-158
• /
• 2021

Versatile Video Coding (VVC) is the latest video coding standard developed by Joint Video Exploration Team (JVET). In VVC, the quadtree plus multi-type tree (QT+MTT) structure of coding unit (CU) partition is adopted, and its computational complexity is considerably high due to the brute-force search for recursive rate-distortion (RD) optimization. In this paper, we aim to reduce the time complexity of inter-picture prediction mode since the inter prediction accounts for a large portion of the total encoding time. The problem can be defined as classifying the split mode of each CU. To classify the split mode effectively, a novel convolutional neural network (CNN) called multi-level tree (MLT-CNN) architecture is introduced. For boosting classification performance, we utilize additional information including inter-picture information while training the CNN. The overall algorithm including the MLT-CNN inference process is implemented on VVC Test Model (VTM) 11.0. The CUs of size 128×128 can be the inputs of the CNN. The sequences are encoded at the random access (RA) configuration with five QP values {22, 27, 32, 37, 42}. The experimental results show that the proposed algorithm can reduce the computational complexity by 11.53% on average, and 26.14% for the maximum with an average 1.01% of the increase in Bjøntegaard delta bit rate (BDBR). Especially, the proposed method shows higher performance on the sequences of the A and B classes, reducing 9.81%~26.14% of encoding time with 0.95%~3.28% of the BDBR increase.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2003.10a
• /
• pp.115.2-116
• /
• 2003

Complete genomic nucleotide sequence of Daphe virus S (DVS), a member of the genus Carlavirus, causing leaf distortion and chlorotic spot disease symptoms in daphne plants, has been determined in this study. The genome of DVS contained six open reading fames coding for long viral replicase, triple gene block, 36 kDa viral coat protein (CP) and 12 kDa from the 5' to 3' ends, which is a typical genome structure of carlaviruses. Two Korean isolates of DVS isolates were 98.1％ and 93.6％ amino acid identical in the CP and 12kDa, respectively. The CP gene of DVS shares 25.2-55.2％ and 42.9-56.1％ similarities with that of 19 other carlaviruses at the amino acid and nucleotide levels, respectively. The 3'-proximal 12 kDa gene of DVS shares 20.2-57.8％ amino acid identities with that of 18 other members of the genus. The 3' noncoding region of DVS consists of 73 nucleotides with long excluding poly A tract, and shares 69.1-77.1％ identities to the known carlaviruses. In the phylogenetic analyses of the two proteins, DVS was closely related to Helenium virus S and Chrysanthemum virus B. This is the first complete sequence information for the DVS, and further confirms the classification of DVS as a distinct species of the genus Carlavirus.