• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.902-906
• /
• 2000

망막 혈관 구조의 분석은 망막에 관련된 환자의 진단 및 치료에 중요한 정보를 제공하기 때문에 다양한 연구가 진행되어 왔다. 본 연구에서는 ICG(IndoCyanine Green) 기술을 이용한 망막 영상의 혈관 구조를 분석하기 위해 원의 방정식으로 묘사된 혈관 영역 에너지 함수와 분기점 추정 템플릿을 사용하여 혈관의 특징점들을 추정한 후 혈관의 형체(body)를 자동으로 추적하는 동시에 분기점을 추출하는 방법을 제안한다. 전체 혈관의 자동추적과 분기점 추출을 가능하게 하는 특징점 추정 방법과 혈관 형체의 자동추적 알고리즘 및 분기점 추출 방법을 ICG 망막 영상에 적용하여 실험한 결과 만족할 만한 성능을 보였다.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.209-215
• /
• 2015

In the past, there have been many theory and algorithms for vehicle tracking. But the time complexity of many feature point matching methods for vehicle tracking are exponential. Also, object segmentation and detection algorithms presented for vehicle tracking are exhaustive and time consuming. Therefore, we present the fast and efficient two stages method that can efficiently track the many moving vehicles on the road. The first detects the vehicle plate regions and extracts the feature points of vehicle plates. The second associates the feature points between frames using dynamic programming.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.6
• /
• pp.650-662
• /
• 1989

In this paper, a new algorithm for feature extraction and classification of recognizing Hanguel patterns is proposed. Inputed patterns classify into six basic formal patterns and divided into subregion of Hanguel phoneme and extract the crook feature from position information of the each subregion. Hanguel patterns are defined and are made of the indexed-sequence file using these crook features points. Hanguel patterns are recognized by retrievignt ehses two files such as feature indexed-sequence file and standard dictionary file. Thi paper show that the algorithm is very simple and easily construct the software system. Experimental result presents the output of feature extraction and grouping of input patterns. Proposed algorithm extract the crooked feature using distance transformation method within the rectangle of enclosure the characters. That uses the informationof relative position feature. It represents the 97% of recognition ratio.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.7
• /
• pp.535-544
• /
• 1990

In this paper, we represent the restoration and feature extraction of fingerprint image. The purpose of restoration of fingerprint image are to com pensate distortion which is affected by noise and to preserve various features of fingerprint image. To extracte the central point of fingerprint, we used sample matrix, and restore fingerprint, we used direction in formation of thinned image and the gray scale of the original images.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.164-167
• /
• 2019

모바일 운영체제 중 안드로이드의 점유율이 높아지면서 모바일 악성코드 위협은 대부분 안드로이드에서 발생하고 있다. 그러나 정상앱이나 악성앱이 진화하면서 권한 등의 단일 특징점으로 악성여부를 연구하는 방법은 유효성 문제가 발생하여 본 논문에서는 다양한 특징점 추출 및 기계학습을 활용하여 극복하고자 한다. 본 논문에서는 APK 파일에서 구동에 필요한 다섯 종류의 특징점들을 안드로가드라는 정적분석 툴을 통해 학습데이터의 특성을 추출한다. 또한 추출된 중요 특징점을 기반으로 모델링을 하는 세 가지 방법을 제시한다. 첫 번째 방법은 보안 전문가에 의해 엄선된 132가지의 특징점 조합을 바탕으로 모델링하는 것이다. 두 번째는 학습 데이터 7,000개의 앱에서 발생 빈도수가 높은 상위 99%인 8,004가지의 특징점들 중 랜덤포레스트 분류기를 이용하여 특성중요도가 가장 높은 300가지를 선정 후 모델링 하는 방법이다. 마지막 방법은 300가지의 특징점을 학습한 다수의 모델을 통합하여 하나의 가중치 투표 모델을 구성하는 방법이다. 최종적으로 가중치 투표 모델인 앙상블 알고리즘 모델을 사용하여 97퍼센트로 정확도가 개선되었고 오탐률도 1.6%로 성능이 개선되었다.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.3
• /
• pp.74-82
• /
• 2024

In this study, feature point detection and displacement measurement performance depending on feature extraction algorithms were compared and analyzed according to environmental changes and target types in the feature point-based displacement measurement algorithm. A three-story frame structure was designed for performance evaluation, and the displacement response of the structure was digitized into FHD (1920×1080) resolution. For performance analysis, the initial measurement distance was set to 10m, and increased up to 40m with an increment of 10m. During the experiments, illuminance was fixed to 450lux or 120lux. The artificial and natural targets mounted on the structure were set as regions of interest and used for feature point detection. Various feature detection algorithms were implemented for performance comparisons. As a result of the feature point detection performance analysis, the Shi-Tomasi corner and KAZE algorithm were found that they were robust to the target type, illuminance change, and increase in measurement distance. The displacement measurement accuracy using those two algorithms was also the highest. However, when using natural targets, the displacement measurement accuracy is lower than that of artificial targets. This indicated the limitation in extracting feature points as the resolution of the natural target decreased as the measurement distance increased.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.45 no.6
• /
• pp.49-59
• /
• 2008

SIFT(Scale Invariant Feature Transform) is an algorithm to extract vectors at pixels around keypoints, in which the pixel colors are very different from neighbors, such as vortices and edges of an object. The SIFT algorithm is being actively researched for various image processing applications including 3-D image constructions, and its most computation-intensive stage is a keypoint localization. In this paper, we develope a fixed-point model of the keypoint localization and propose its efficient hardware architecture for embedded applications. The bit-length of key variables are determined based on two performance measures: localization accuracy and error rate. Comparing with the original algorithm (implemented in Matlab), the accuracy and error rate of the proposed fixed point model are 93.57% and 2.72% respectively. In addition, we found that most of missing keypoints appeared at the edges of an object which are not very important in the case of keypoints matching. We estimate that the hardware implementation will give processing speed of $10{\sim}15\;frame/sec$, while its fixed point implementation on Pentium Core2Duo (2.13 GHz) and ARM9 (400 MHz) takes 10 seconds and one hour each to process a frame.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.623-626
• /
• 2000

본 논문에서는 얼굴의 특징 추출을 이용해서 캐리커쳐를 자동으로 생성하는 알고리즘을 제안한다. 제안된 방법은 사진이나 카메라를 이용해서 입력된 영상으로부터 색상정보를 이용하여 얼굴영역을 검출하고 얼굴의 기하학적인 구조를 이용해서 유전자 알고리즘의 추정 파라미터를 설정하여 최적의 특징 점의 위치를 검출한다. 검출된 특징 점 위치를 이용하여 눈, 코, 입, 눈썹, 머리카락 등 얼굴의 특징이 되는 구성요소를 추출한다. 마지막으로 얼굴의 윤곽선을 구한 다음 추출된 얼굴의 구성요소들을 합성하여 간단하면서도 개인의 특징을 잘 반영할 수 있는 캐리커쳐를 생성한다.

• Journal of Korea Multimedia Society
• /
• v.13 no.4
• /
• pp.547-559
• /
• 2010

Delaunay triangulation is suitable for fingerprint matching because of its robustness to rotation and translation. However, missing and spurious minutiae degrade the performance and computational efficiency. In this paper, we propose a method of combining local quality assessment and 4-category minutiae classification to improve accuracy and decrease computational complexity in matching process. Experimental results suggest that removing low quality areas from matching candidate areas and classifying minutiae improve computational efficiency without degrading performance. The results proved that the proposed algorithm outperforms the matching algorithm (BOZORTH3) provided by NIST.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.2
• /
• pp.263-270
• /
• 2024

As unmanned aerial vehicles(UAVs) and sensors have been developed in a variety of ways, it has become possible to update information on the ground faster than existing aerial photography or remote sensing. However, acquisition and input of ground control points(GCPs) UAV photogrammetry takes a lot of time, and geometric distortion occurs if measurement and input of GCPs are incorrect. In this study, RGB-based orthophotos were generated to reduce GCPs measurment and input time, and comparison and evaluation were performed by applying feature point algorithms to target orthophotos from various sensors. Four feature point extraction algorithms were applied to the two study sites, and as a result, speeded up robust features(SURF) was the best in terms of the ratio of matching pairs to feature points. When compared overall, the accelerated-KAZE(AKAZE) method extracted the most feature points and matching pairs, and the binary robust invariant scalable keypoints(BRISK) method extracted the fewest feature points and matching pairs. Through these results, it was confirmed that the AKAZE method is superior when performing geometric correction of the objective orthophoto for each sensor.