• 지능정보연구
• /
• 제8권1호
• /
• pp.27-39
• /
• 2002

본 논문은 다양한 웹 이미지로부터 문자영역(text block)의 위치를 알아내고 문자영역을 추출하는 방법을 제안한다. 인터넷 사용자관점에서 볼 때, 웹 이미지에 포함되어 있는 문자정보는 중요한 정보이지만 최근까지 이 분야의 연구는 그리 활발하지 못했다. 본 연구에서 제안된 알고리즘은 문자의 경사방향(skew)과 문자의 크기나 폰트에 관한 사전 정보 없이 수행되어 질 수 있도록 제안되었다 폰트 스타일과 크기에 제약되지 않고 문자영역을 적합하게 추출하기 위해 유용한 에지 검출, 문자 클러스터링 영역으로 정의되는 문자의 고유한 특성을 위한 히스토그램을 사용하였다. 다수의 실험을 통하여 제안된 방법을 테스트하고 수용할 만한 결과를 도출했다.

• 전자공학회논문지CI
• /
• 제38권1호
• /
• pp.46-57
• /
• 2001

시간적 특성을 가진 비디오 자료와 같은 멀티미디어의 자료에 접근하기 위해서는 내용 기반 이미지 검색 기술이 필요하다. 더욱이, 내용 기반 이미지 검색의 기본적인 기술 중의 하나가 대표키 프레임들의 추출이다. 제안된 방법을 구현했을 뿐만 아니라, 대표키 프레임들이 비디오 데이터의 특성에 대한 데이터 분석을 사용하여 추출될 수 있음을 보였다. 또한, 제안된 방법이 정확함 뿐만 아니라 효과적이라는 것을 증명하였다. 제안한 방법은 비디오 데이터 베이스를 위해 색인을 구축하는데 매우 유용하다. 그러므로 제안한 방법이 실세계에서 비디오 데이터 베이스를 구축하는데 사용되기를 기대한다.

• Journal of Mechanical Science and Technology
• /
• 제18권7호
• /
• pp.1236-1245
• /
• 2004

In this study, an optical imaging method was developed for the measurements of the sizes and velocities of droplets in sprays. Double-exposure single-frame spray images were captured by the imaging system. An image processing program was developed for the measurements of the sizes and positions of individual particles including separation of the overlapped particles and particle tracking and pairing at two time instants. To recognize and separate overlapping particles, the morphological method based on watershed segmentation as well as separation using the perimeter and convex hull of image was used consecutively. Better results in separation were obtained by utilization of both methods especially for the multiple or heavily-overlapped particles. The match probability method was adopted for particle tracking and pairing after identifying the positions of individual particles and it produced good matching results even for large particles like droplets in sprays. Therefore, the developed optical imaging method could provide a reliable way of analyzing the motion and size distribution of droplets produced by various sprays and atomization devices.

• Journal of Information Processing Systems
• /
• 제7권3호
• /
• pp.425-434
• /
• 2011

The success of iris recognition depends mainly on two factors: image acquisition and an iris recognition algorithm. In this study, we present a system that considers both factors and focuses on the latter. The proposed algorithm aims to find out the most efficient wavelet family and its coefficients for encoding the iris template of the experiment samples. The algorithm implemented in software performs segmentation, normalization, feature encoding, data storage, and matching. By using the Haar and Biorthogonal wavelet families at various levels feature encoding is performed by decomposing the normalized iris image. The vertical coefficient is encoded into the iris template and is stored in the database. The performance of the system is evaluated by using the number of degrees of freedom, False Reject Rate (FRR), False Accept Rate (FAR), and Equal Error Rate (EER) and the metrics show that the proposed algorithm can be employed for an iris recognition system.

• 한국전자통신학회논문지
• /
• 제14권6호
• /
• pp.1197-1206
• /
• 2019

순천만은 매우 중요한 자연자원으로 환경오염으로부터 이를 보호하기 위한 노력들이 이루어지고 있다. 순천만 갯벌에 서식하는 생물들을 주기적으로 관찰하여 환경의 변화를 모니터링하는 사업이 진행되고 있으나 사람이 직접 관찰하는 비효율적인 방법으로 이루어지고 있다. 본 논문에서는 갯벌에 서식하는 생물들을 자동으로 모니터링하기 위한 방법에 적용될 수 있는 객체 분할 방법을 제안한다. 제안하는 방법에서는 차 영상을 이용하여 객체의 위치 정보를 나타내는 전경 맵을 구하고, 영상의 세밀한 경계 검출을 위해 슈퍼픽셀 방법을 적용한다. 전경 맵과 슈퍼픽셀 정보를 이용하여 최종적으로 갯벌 영상에서 게의 영역을 추출한다. 실험 결과는 제안하는 방법이 간단하면서도 정확하게 갯벌 영상에서 게 영역을 분리하는 것을 보여준다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 Korea-Russia Joint Conference on Geometics
• /
• pp.64-72
• /
• 2004

Correction of shadow effects is critical step for image interpretation and feature extraction from aerial imagery. In this paper, an efficient algorithm to correct shadow effects from aerial color imagery is presented. The following steps have been performed to remove the shadow effect. First, the shadow regions are precisely located using the solar position and the height of ground objects derived from LIDAR (Light Detection and Ranging) data. Subsequently, segmentation of context regions is implemented for accurate correction with existing digital map. Next step, to calculate correction factor the comparison between the context region and the same non-shadowed context region is made. Finally, corrected image is generated by correcting the shadow effect. The result presented here helps to accurately extract and interpret geo-spatial information from aerial color imagery

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 추계학술발표대회
• /
• pp.347-350
• /
• 2011

This paper propose a statistical color model of background extraction base on Hue-Saturation-Value(HSV) color space, instead of the traditional RGB space, and shows that it provides a better use of the color information. HSV color space corresponds closely to the human perception of color and it has revealed more accuracy to distinguish shadows [3] [4]. The key feature of this segmentation method is based on processing hue component of color in HSV color space on image area. The HSV color model is used, its color components are efficiently analyzed and treated separately so that the proposed algorithm can adapt to different environmental illumination condition and shadows. Polar and linear statistical operations are used to calculate the background from the video frames. The experimental results show that the proposed background subtraction method can automatically segment video objects robustly and accurately in various illuminating and shadow environments.

• Journal of information and communication convergence engineering
• /
• 제6권1호
• /
• pp.94-99
• /
• 2008

Segmentation for the region of nucleus in the image of uterine cervical cytodiagnosis is known as the most difficult and important part in the automatic cervical cancer recognition system. In this paper, the region of nucleus is extracted from an image of uterine cervical cytodiagnosis using the HSI model. The characteristics of the nucleus are extracted from the analysis of morphemetric features, densitometric features, colormetric features, and textural features based on the detected region of nucleus area. The classification criterion of a nucleus is defined according to the standard categories of the Bethesda system. The fuzzy C-means clustering algorithm is employed to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

• Journal of information and communication convergence engineering
• /
• 제22권1호
• /
• pp.80-87
• /
• 2024

The Manchu language holds historical significance, but a complete dataset of Manchu script letters for training optical character recognition machine-learning models is currently unavailable. Therefore, this paper describes the process of creating a robust dataset of extracted Manchu script letters. Rather than performing automatic letter segmentation based on whitespace or the thickness of the central word stem, an image of the Manchu script was manually inspected, and one copy of the desired letter was selected as a region of interest. This selected region of interest was used as a template to match all other occurrences of the same letter within the Manchu script image. Although the dataset in this study contained only 4,000 images of five Manchu script letters, these letters were collected from twenty-eight writing styles. A full dataset of Manchu letters is expected to be obtained through this process. The collected dataset was normalized and trained using a simple convolutional neural network to verify its effectiveness.

• 한국컴퓨터정보학회논문지
• /
• 제23권10호
• /
• pp.87-94
• /
• 2018

This paper proposes a method of detecting the license plates of vehicles. The proposed technology applicable to different formats of license plates detects the numbers by standardizing the images at edge points. Specifically, in accordance with the format of each license plate, the technology captures the image in the character segment, and compares it against the sample model to derive their similarity and identify the numbers. Characters with high similarities are used to form a group of candidates and to extract the final characters. Analyzing the experimental results found the similarity of the extracted characters exceeded 90%, whereas that of less identifiable numbers was markedly lower. Still, the accuracy of the extracted characters with the highest similarity was over 80%. The proposed technology is applicable to extracting the character patterns of certain formats in diverse and useful ways.