• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.63-70
• /
• 2014

Process of recognizing objects in binary images consists of image segmentation and pattern matching. If binary objects in the image are assumed to be separated, global features such as area, length of perimeter, or the ratio of the two can be used to recognize the objects in the image. However, if such an assumption is not valid, the global features can not be used but local features such as points or line segments should be used to recognize the objects. In this paper points with large curvature along the perimeter are chosen to be the feature points, and pairs of points selected from them are used as local features. Similarity of two local features are defined using elastic deformation energy for making the lengths and angles between gradient vectors at the end points same. Neighbour support value is defined and used for robust recognition of partially occluded binary objects. An experiment on Kimia-25 data showed that the proposed algorithm runs 4.5 times faster than the maximum clique algorithm with same recognition rate.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.3
• /
• pp.132-140
• /
• 1994

SCRIPT (Symbol/Character Recognition In Pen-based Technology) is an algorithm for on-line recognition of handwriting Hangeul. English upperacase letters, decimal digits, and some keyboard symbols. The shape of handwriting symbols has a large variation even when written by the same person. Though the feature analysis approach using a conventional decision tree is efficient, it is not robust under shape variations and prone to misclassification. Thus, a new method to overcome this shortcoming is necessary. In this paper, a feature analysis algorithm using two fuzzy decision trees which utilize the hierarchical property of the pattern is proposed. The first tree is used to represent the stroke shape, and the other tree is used to represent the relation between the strokes. since this method stores various possibilities. it is robust to shape variations and can readily modify false selections. In addition, there is a large increase in the recognition rate of high-level patterns due to low-level candidated. Experimental results show 91% recognition rate for Hangeul at the recognition speed of 0.33 second per character, and the recognition rate of alphanumerics and some keyboard symbols is 95% at 0.08 second per symbol. This is 8~18% increase in the recognition rate over th method not applying fuzzy decision trees.

• Journal of Bio-Environment Control
• /
• v.24 no.3
• /
• pp.210-216
• /
• 2015

Purpose of this study was a development of an image processing algorithm to recognize paprika and acquire it's 3D coordinates from stereo images to precisely control an end-effector of a paprika auto harvester. First, H and S threshold was set using HSI histogram analyze for extracting ROI(region of interest) from raw paprika cultivation images. Next, fundamental matrix of a stereo camera system was calculated to process matching between extracted ROI of corresponding images. Epipolar lines were acquired using F matrix, and $11{\times}11$ mask was used to compare pixels on the line. Distance between extracted corresponding points were calibrated using 3D coordinates of a calibration board. Non linear regression analyze was used to prove relation between each pixel disparity of corresponding points and depth(Z). Finally, the program could calculate horizontal(X), vertical(Y) directional coordinates using stereo camera's geometry. Horizontal directional coordinate's average error was 5.3mm, vertical was 18.8mm, depth was 5.4mm. Most of the error was occurred at 400~450mm of depth and distorted regions of image.

• Journal of the Economic Geographical Society of Korea
• /
• v.9 no.3
• /
• pp.379-395
• /
• 2006

The purpose of this study is to analyze the spatial characteristics of travel patterns and travel behaviors of transit users in the Metropolitan Seoul area. We apply the data mining techniques to explore the travel patterns of transit users from the T-money card database which has been produced over 10,000,000 transaction records per day. The database contains the information of locations and times of origin, transfer, and destination points for each transaction as well as the informations of transit modes taken via the transaction. We develop an data mining algorithm to explore traversal patterns from the enormous information. The algorithm determines the travel sequences of each passenger, and produce the volumes of support on each points (stops) of transportation networks in the Metropolitan Seoul area. In order to visualize the spatial patterns of travel demands for transit systems we apply GIS techniques, and attempt to investigate the spatial characteristics of travel patterns and travel demand. Subway stops located in the Gangnam area appear the highest peak for the travel origin and destination, while the CBD in the Gangbuk stands at the second position. Two or three sub-peaks appear at the densely populated residential areas developed as the high-rise apartment complex. Subway stations located along the Subway Line 2, especially from Guro to Samsung receive heavy travel demand (total support), while bus stops located at the CBD in the Gangbuk stands the highest travel demand by bus.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.2
• /
• pp.1-8
• /
• 2001

In this paper, we propose an algorithm which estimates the displacements and velocities of objects in the soccer field from the soccer image sequences. Assuming the time interval of an object movement is given, we transform the object positions into those in the soccer field model and compute the distance and the velocity. When four corresponding pairs of the feature points, such as the crossing points of the lines in the soccer field, exist and three of them are not on a line, we transform the object positions in the soccer image into those in the soccer field by using the perspective displacement field model. In addition, when the soccer image has less than four feature points, we first transform the object positions into those in the image which has more than four feature points, and then transform the positions into those in the soccer field again. To find the coordinate transformation between two images, we estimate the panning and zooming for consecutive images in the sequence. In the experimental results, we quantitatively evaluated the estimation accuracy by applying our algorithm to the synthetic. soccer image sequences generated by graphic tools, and applied it to the real soccer image sequences for broadcasting to show its usefulness.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.35 no.3
• /
• pp.167-173
• /
• 2013

Purpose: The aim of this study is to analyze the series of panoramic radiograph of implant patients using the system to measure peri-implant crestal bone loss according to the elapsed time from fixture installation time to more than three years. Methods: Choose 10 patients having 45 implant fixtures installed, which have series of panoramic radiograph in the period to be analyzed by the system. Then, calculated the crestal bone depth and statistics and selected the implant in concerned by clicking the implant of image shown on the monitor by the implemented pattern recognition system. Then, the system recognized the x, y coordination of the implant and peri-implant alveolar crest, and calculated the distance between the approximated line of implant fixture and alveolar crest. By applying pattern recognition to periodic panoramic radiographs, we attained the results and made a comparison with the results of preceded articles concerning peri-implant marginal bone loss. Analyzing peri-implant crestal bone loss in a regression analysis periodic filmed panoramic radiograph, logarithmic approximation had highest $R^2$ value, and the equation is as shown below. $y=0.245Logx{\pm}0.42$, $R^2=0.53$, unit: month (x), mm (y) Results: Panoramic radiograph is a more wide-scoped view compared with the periapical radiograph in the same resolution. Therefore, there was not enough information in the radiograph in local area. Anterior portion of many radiographs was out of the focal trough and blurred precluding the accurate recognition by the system, and many implants were overlapped with the adjacent structures, in which the alveolar crest was impossible to find. Conclusion: Considering the earlier objective and error, we expect better results from an analysis of periapical radiograph than panoramic radiograph. Implementing additional function, we expect high extensibility of pattern recognition system as a diagnostic tool to evaluate implant-bone integration, calculate length from fixture to inferior alveolar nerve, and from fixture to base of the maxillary sinus.

• Journal of Navigation and Port Research
• /
• v.26 no.4
• /
• pp.473-479
• /
• 2002

The estimation of the volume of a pit excavation is often required in many surveying, soil mechanics, highway applications and transportation engineering situations. The calculation of earthwork plays a major role in plan or design of many civil engineering projects such as seashore reclamation, and thus it has become very important to improve the accuracy of earthwork calculation. In this paper the spot height method, proposed formulas(A, B, C), and chen and Line method are compared with the volumes of the pits in these examples. And we proposed an algorithm of finding a terrain surface with the free boundary conditions and both direction spline method drawback, i.e., the modeling curves form peak points at the joints. To avoid this drawback, the cubic spline polynomial was chosen as the methematical model of the new method. From the characteristics of the cubic spline polynomial, the modeling curve of the new method was smooth and matched the ground profile well. As a result of this study, algorithm of proposed three methods to estimate pit excavation volume provided a better accuracy than spot height, chamber, chen and Lin method. And the mathematical model mentioned makes is thought to give a maximum acccuracy in estimating the volume of a pit excavation.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.1
• /
• pp.32-38
• /
• 2012

Each sensor node can know its location in several ways, if the node process the information based on its geographical position in sensor networks. In the localization scheme using GPS, there could be nodes that don't know their locations because the scheme requires line of sight to radio wave. Moreover, this scheme is high costly and consumes a lot of power. The localization scheme without GPS uses a sophisticated mathematical algorithm estimating location of sensor nodes that may be inaccurate. AHLoS(Ad Hoc Localization System) is a hybrid scheme using both GPS and location estimation algorithm. In AHLoS, the GPS node, which can receive its location from GPS, broadcasts its location to adjacent normal nodes which are not GPS devices. Normal nodes can estimate their location by using iterative triangulation algorithms if they receive at least three beacons which contain the position informations of neighbor nodes. But, there are some cases that a normal node receives less than two beacons by geographical conditions, network density, movements of nodes in sensor networks. We propose an indirect localization scheme for low-density sensor nodes which are difficult to receive directly at least three beacons from GPS nodes in wireless network.

• Journal of the Korean Wood Science and Technology
• /
• v.37 no.1
• /
• pp.37-47
• /
• 2009

For the inspection of wood, machine vision is the most common automated inspection method used at present. It is required to sort wood products by grade and to locate surface defects prior to cut-up. Many different sensing methods have been applied to inspection of wood including optical, ultrasonic, X-ray sensing in the wood industry. Nowadays the scanning system mainly employs CCD line-scan camera to meet the needs of accurate detection of lumber defects and real-time image processing. But this system needs exact feeding system and low deviation of lumber thickness. In this study low cost CCD area sensor was used for the development of image processing system for lumber being fed. When domestic red pine being fed on the conveyer belt, lumber images of irregular term of captured area were acquired because belt conveyor slipped between belt and roller. To overcome incorrect image merging by the unstable feeding speed of belt conveyor, it was applied template matching algorithm which was a measure of the similarity between the pattern of current image and the next one. Feeding the lumber over 13.8 m/min, general area sensor generates unreadable image pattern by the motion blur. The red channel of RGB filter showed a good performance for removing background of the green conveyor belt from merged image. Threshold value reduction method that was a image-based thresholding algorithm performed well for knot detection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.6
• /
• pp.786-792
• /
• 2010

This paper presents a real-time lane detection method which can accurately find the lane-mark boundaries in complex road environment. Unlike many existing methods that pay much attention on the post-processing stage to fit lane-mark position among a great deal of outliers, the proposed method aims at removing those outliers as much as possible at feature extraction stage, so that the searching space at post-processing stage can be greatly reduced. To achieve this goal, a grid-based morphology operation is firstly used to generate the regions of interest (ROI) dynamically, in which a directional edge-linking algorithm with directional edge-gap closing is proposed to link edge-pixels into edge-links which lie in the valid directions, these directional edge-links are then grouped into pairs by checking the valid lane-mark width at certain height of the image. Finally, lane-mark colors are checked inside edge-link pairs in the YUV color space, and lane-mark types are estimated employing a Bayesian probability model. Experimental results show that the proposed method is effective in identifying lane-mark edges among heavy clutter edges in complex road environment, and the whole algorithm can achieve an accuracy rate around 92% at an average speed of 10ms/frame at the image size of $320{\times}240$.