• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.55 no.4
• /
• pp.167-175
• /
• 2006

This paper presents a method to segment semiconductor wafer ID on poor quality images. The method is based on multiple templates and normalized gray-level correlation (NGC) method. If the lighting condition is not so good and hence, we can not control the image quality, target image to be inspected presents poor quality ID and it is not easy to identify and then recognize the ID characters. Conventional several method to segment the interesting ID regions fails on the bad quality images. In this paper, we propose a multiple template method, which uses combinational relation of multiple templates from model templates to match several characters of the inspection images. To find out the optimal solution of multiple template model in ID regions, we introduce newly-developed snake algorithm. Experimental results using images from real FA environment are presented.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1351-1367
• /
• 2018

Image registration is an essential process for image fusion, change detection and time series analysis using multi-sensor images. For this purpose, we need to detect accurately the difference of scale and rotation between the multi-sensor images with difference spatial resolution. In this paper, we propose a new feature matching method using variable circular template for image registration between multi-resolution images. The proposed method creates a circular template at the center of a feature point in a coarse scale image and also a variable circular template in a fine scale image, respectively. After changing the scale of the variable circular template, we rotate the variable circular template by each predefined angle and compute the mutual information between the two circular templates and then find the scale, the angle of rotation and the center location of the variable circular template, respectively, in fine scale image when the mutual information between the two circular templates is maximum. The proposed method was tested using Kompsat-2, Kompsat-3 and Kompsat-3A images with different spatial resolution. The experimental results showed that the error of scale factor, the error of rotation angle and the localization error of the control point were less than 0.004, $0.3^{\circ}$ and one pixel, respectively.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1224-1227
• /
• 2002

In this paper, we propose a composition method of the template image whose detection performance does not have incorrect detection and improves also on the tough photography conditions of the outdoors, rainy weather and night. This research was done to measure a relative position between a spreader and a target container with image processing to realize full-automatic quayside gantry cranes. By the proposal method, we confirmed that the template image for object detection has a contour image more effective than a gray image.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.4
• /
• pp.700-705
• /
• 2008

In this paper, we propose object classification algorithm for real-time surveillance system. We have approached this problem using silhouette-based template matching. The silhouette of the object is extracted, and then it is compared with representative template models. Template models are previously stored in the database. Our algorithm is similar to previous pixel-based template matching scheme like Hausdorff Distance, but we use 1D image array rather than 2D regions inspired by Hilbert Path. Transformation of images could reduce computational burden to compute similarity between the detected image and the template images. Experimental results show robustness and real-time performance in object classification, even in low resolution images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.7
• /
• pp.1429-1436
• /
• 2009

In this paper, we propose a robust eye detection method using template matching based on genetic algorithm in the single facial image. The previous works for detecting pupil using genetic algorithm had a problem that the detection accuracy is influnced much by the initial population for it's random value. Therefore, their detection result is not consistent. In order to overcome this point we extract local minima in the facial image and generate initial populations using ones that have high fitness with a template. Each chromosome consists of geometrical informations for the template image. Eye position is detected by template matching. Experiment results verify that the proposed eye detection method improve the precision rate and high accuracy in the single facial image.

• Progress in Medical Physics
• /
• v.15 no.1
• /
• pp.45-53
• /
• 2004

SPM has been widely applied for comparison studios of the functional image data among groups of patients or individuals under different conditions and these images are from people ranging from children to adults. However, the analysis of children's brain images by using SPM can make children's brain images normalized to an adult's template image and this can result in some errors. So this study created the children's mean MR images based on the Magnetic Resonance Images of 36 normal children (age: 2～6, average age: 4.36, SD age: 1.41, M/F: 17/19), and the children's mean SPECT images by using SPECT images of 13 normal children (age: 2～6, average age: 4.80, SD age: 1.17, M/F: 10/3). We created the Korean children's brain template image, based on those mean images, and then we compared between the positions of the clusters, based on the blood flow, by normalizing ADHD children's SPECT image to Korean children's template image and SPM adult's template image. As a result of the analysis, the variation of the cluster positions was found to be a maximum of 25 ㎜. Therefore, we should be aware that we need to consider the template image and the p-value when we analyze the chlidren's brain image by using SPM.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.3
• /
• pp.264-268
• /
• 2010

The purpose of this paper is to propose new techniques to match measured optical images by using the edge abstraction method and differentiation method based on image processing technology. To do this, we detect the matching template and non-matching template from each optical image. And then, we detect the edge parts of the overlaped image from comer edge abstraction method and remove noise image. At last, these data are related to applied first-order derivative operator. Finally, we show the effectiveness and feasibility of the proposed method through some experiments.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.35 no.11
• /
• pp.1043-1051
• /
• 2007

The digital sun sensor calculates the incident sunlight angle using the sunlight image registered on a CMOS image sensor. In order to accomplish this, an exact center of the sunlight image has to be determined. Therefore, an accurate estimate of the centroid is the most important factor in digital sun sensor development. The most general method for determining the centroid is the thresholding method, and this method is also the simplest and easy to implement. Another centering algorithm often used is the image filtering method that utilizes image processing. The sun sensor accuracy using these methods, however, is quite susceptible to noise in the detected sunlight intensity. This is especially true in the thresholding method where the accuracy changes according to the threshold level. In this paper, a template method that uses the sunlight image model to determine the centroid of the sunlight image is suggested, and the performance has been compared and analyzed. The template method suggested, unlike the thresholding and image filtering method, has comparatively higher accuracy. In addition, it has the advantage of having consistent level of accuracy regardless of the noise level, which results in a higher reliability.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.12
• /
• pp.107-114
• /
• 2018

We propose EPD(Electrophoretic Display) file generation system based on template that enable users to choose contents layout for E-paper display. And also we show implementation results that apply the proposed system in digital doorsign management field adopting E-paper display. Template includes information for contents layout which is composed of standard form image to be used as background image, coordinates of area for dynamic data to be inserted, data source about dynamic data, and characteristic data of EPD panel for displaying contents. System administrator registers templates in Forms Server. When user chooses a contents layout, Forms Server automatically generates EPD file for displaying contents in E-paper by using information of the template and sends EPD file into doorsign. Strength of the proposed system lies in reflecting user preference about contents design and adding personal data into E-paper contents by smartphone application.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.6
• /
• pp.413-422
• /
• 2013

In this paper, we propose a novel method for real-time lane detection that is robust for inclined roads and not require a camera parameter, the Inverse Perspective Transform of the image, and the proposed lane filter. After finding the vanishing point from the start frame of the image and storing the region surrounding the vanishing point as the Template Area(TA), our method predict the lanes by scanning toward the lower part from the vanishing point of the image and obtain the image removed the perspective effect using the Inverse Perspective Transform coefficients extracted based on the predicted lanes. To robustly determine lanes on inclined roads, the region surrounding the vanishing point is set up as the template area (TA), and, by recalculating the vanishing point by tracing the area similar to the TA (SA) in the input image through template matching, it responds to the changes on the road conditions. The proposed method for a more robust lane detection method for inclined roads is a lane detection method by applying a lane detection filter on an image removed of the perspective effect. Through this method, the processing region is reduced and the processing procedure is simplified to produce a satisfactory lane detection result of about 40 frames per second.