• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.974-977
• /
• 1999

In this paper, we have proposed the hardware architecture which implements the algorithm for retaining the connectivity which prevents disconnecting in the gray-scale image thinning To perform the image thinning in a real time which find a skeleton in image, it is necessary to examine the connectivity of the skeleton in a real time. The proposed architecture finds the connectivity number in the 4-clock period. The architecture is consists of three blocks, PS(Parallel to Serial) Converter and State Generator and Ridge Checker. The PS Converter changes the 3$\times$3 gray level image to four sets of image pixels. The State Generator examine the connectivity of the central pixel by searching the data from the PS Converter. the 3$\times$3 gray level image determines. The Ridge Checker determines whether the central pixel is on the skeleton or not The proposed architecture finds the connectivity of the central pixel in a 3$\times$3 gray level image in the 4-clocks. The total circuits are verified by the design tools and operate correctly.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1349-1355
• /
• 1999

A power distribution facility map is drawn on cadastral map. Besides, grid lines are added on the map for sectionalization. For automatic recognition of the map, we first extract recognizing regions. In this paper, we propose an extraction method of recognizing regions by partially extending thinned image. The proposed method is consist of three phases, binarization phase, thinning phase and partial extending phase. The first phase generate a binary image using threshold value which is obtained by histogram analysis. The binary image contains many part of recognizing regions, but not all. The second phase generate thinned image which is generated by appling thinning operator to the binary image. And the third phase extends thinned image from terminal point until satisfying termination condition. The proposed method is tested on several power distribution facility maps, and the results are presented.

• 농업과학연구
• /
• 제27권1호
• /
• pp.5-12
• /
• 2000

The main purpose of this study is to obtain spatial image information toward forest thinning process in Larix forest stands. Thirteen different alternatives were simulated to visualize on the basis of actual thinning work photos. The options were illustrated as photos produced by photoshop program. Each alternatives were evaluated by forest visitor group with total 244 respondents after reliability test. Spatial images of 13 thinning photos were measured by 12 semantic differential scale as broad -narrow, ordered-tangled, friendly-unfriendly, monotonous-divers, dry-refreshing, relieved -stifling, healthy-sickly, uniform-scattered, dead-alive, opened-closed, bent-straight, and beautiful-ugly. In comparison with thinning stands and natural stands, thinning works were visual improvement effects of spatial images. Seemingly, this trend is due to definite form beauty, straight and clear length form of coniferous forest, As can be expected, slash and downwood were negatively related to improvement effects of spatial images. The 60% ratio of stem/ tree height and 450-950 trees/ha was positive in attraction of spatial images. Results indicate how to conduct forest thinning system for spatial images on Larix forest stands.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.365-365
• /
• 2000

In this paper, we describe the system to recognize the six digit postal number of mails using neural network. Our zip-code recognition system consists of a preprocessing procedure for the original captured image, a segmentation procedure for separating an address block area with a shape, and recognition procedure for the cognition of a postal number. we extract the feature vectors that are the input of a neural network for the recognition process based on an area optimizing and an image thinning processing. The neural network classifies the zip-code in the mail and the recognized zip-code is verified through the zip-code database.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.65-68
• /
• 2002

In an automatic fingerprint recognition system, a thinning process after binarization is commonly used. However it gives rise to spurs and holes often causing many spurious minutiae. Thus, more elaborate postprocessing is urgently needed to remove such spurious minutiae. To overcome this problem, we present a method of extracting minutiae based on horizontal and vertical run-length encoding from a binary fingerprint image without thinning process. Experimental results show that the proposed method for extracting minutiae is fairly reliable and fast, when il is compared to other method adopting a thinning process.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 학술대회지
• /
• pp.814-818
• /
• 2004

Off-line handwritten character recognition is in difficulty of incomplete preprocessing because it has not dynamic and timing information besides has various handwriting, extreme overlap of the consonant and vowel and many error image of stroke. Consequently off-line handwritten character recognition needs to study about preprocessing of various methods such as binarization and thinning. This paper considers running time of watershed algorithm and the quality of resulting image as preprocessing For off-line handwritten Korean character recognition. So it proposes application of effective watershed algorithm for segmentation of character region and background region in gray level character image and segmentation function for binarization image and segmentation function for binarization by extracted watershed image. Besides it proposes thinning methods which effectively extracts skeleton through conditional test mask considering running time and quality. of skeleton, estimates efficiency of existing methods and this paper's methods as running time and quality. Watershed image conversion uses prewitt operator for gradient image conversion, extracts local minima considering 8-neighborhood pixel. And methods by using difference of mean value is used in region merging step, Converted watershed image by means of this methods separates effectively character region and background region applying to segmentation function. Average execution time on the previous method was 2.16 second and on this paper method was 1.72 second. We prove that this paper's method removed noise effectively with overlap stroke as compared with the previous method.

• 인지과학
• /
• 제2권2호
• /
• pp.341-358
• /
• 1990

본 논문은 기존의 세선화 알고리즘이 갖는 문제점의 하나인 잡음을 해결하는 방법을 제안하였다. 이를 위하여 세선화 알고리즘은 Pavlidis에 의해 제안된 방식을 근간으로 하였으며,외곽추적을 수행할때 제안된 $3{\times}3$ 마스크로부터 잡음을 판별해 낼 수 있도록 하였다. 그리고, 추적이 완료되면 자동적으로 잡음이 제거되도록 하였다. 이 방법을 구현시켜 얻어진 세선화 결과는 잡음이 없는 경우와 유사한 형태를 보이고 있으며, 잡음이 있는 경우에 비해 간략화된 구조르 갖음을 알수가 있다. 이와같은 결과는 인식단계의 구성요소들이 간략화 될수 있는 근거를 제공하여 주게 된다.

• 한국측량학회지
• /
• 제26권4호
• /
• pp.407-414
• /
• 2008

본 논문은 항공사진과 위성영상의 서로 다른 해상도를 지닌 이종센서 영상들에 대한 효율적인 특이점 자동 매칭 기법에 대한 알고리즘에 관한 연구이다. 본 연구의 자동 매칭 알고리즘은 매칭 정확도 및 속도를 향상시키기 위해 다양한 영상 처리 방법을 적용하였다. 특이점을 추출하기 위하여 전처리 과정, 필터링, 세선화, 특이점 추출 방법을 사용하였으며, 특이점에 대한 키서술자(Key-descriptor)를 비교하여 매칭의 정확도를 향상시켰다. 특히 본 연구에서 제안된 이종센서간의 정확도 높은 자동 영상 매칭을 위해 센서마다 지닌 기하학적 및 방사학적인 영상의 특징을 활용하였다. 아울러 매칭 속도를 높이기 위해 센서 모델을 이용하여 탐색 영역을 최소화 하고 매칭이 잘못된 특이점을 제거할 수 있는 방법을 제시하고 있다.

• 대한원격탐사학회지
• /
• 제37권6_1호
• /
• pp.1731-1738
• /
• 2021

본 연구에서는 드론 정사영상과 객체추출 기법을 융합하여 개체목을 선별함과 더불어 수고를 추정할 수 있는 방법론을 제시하고자 하였다. 연구대상지는 충청남도 예산군 공주대학교 학술림에 위치한 리기다소나무림으로 간벌을 강도별로(40%, 20%, 10%, 대조구)로 조성한 시험지이다. 정사영상취득은 DJI사의 MAVIC2 PRO 드론을 이용하였으며, 촬영 범위 내 가장 높은 지형지물을 고려하여 고도를 180 m로 설정하였다. 영상왜곡을 방지하기 위하여 지상기준점 설치 및 내중첩(End lap)과 옆중첩(Side lap)을 각각 80%로 설정하였다. 영상분석 통하여 수치표면모델(DSM)과 수치지형 표고모델(DTM)을 추출하고 두 모델의 고도차를 이용해 수고모델(DCHM)을 생성하였다. 본 연구결과에 의하면, 간벌강도별 개체목 추출율은 간벌강도 40%는 109.1%, 간벌강도 20% 87.1%, 간벌강도 10% 63.5%, 대조구 56.0% 수준이었다. 개체목 별 수고특성을 추출한 결과, 간벌강도 40%는 현장조사 결과보다 약 1.43 m 낮았으며, 간벌강도 20%는 1.73 m, 간벌강도 10%는 1.88 m, 대조구는 2.22 m 낮게 측정되었다.

• 대한수학회지
• /
• 제44권6호
• /
• pp.1479-1503
• /
• 2007

In this paper, we study a strong k-deformation retract derived from a relative k-homotopy and investigate its properties in relation to both a k-homotopic thinning and the k-fundamental group. Moreover, we show that the k-fundamental group of a wedge product of closed k-curves not k-contractible is a free group by the use of some properties of both a strong k-deformation retract and a digital covering. Finally, we write an algorithm for calculating the k-fundamental group of a dosed k-curve by the use of a k-homotopic thinning.