• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.19-21
• /
• 2019

본 논문에서는 인공지능의 인식률을 높이기 위해 명암비를 적용한 전처리 방법에 대해 제안한다. 이 방법은 인공지능이 기존의 방법보다 특징점을 쉽게 얻어내기 위해서 명암비를 적용한 전처리를 진행하여 인식률을 높이기 위함에 목적을 두고 있다. 제안한 방법으로 인하여 문자인식이 얼마나 향상되었고, 기존의 성능과 비교하여 정확도가 얼마나 향상되었는지를 알아보고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.805-808
• /
• 2005

엔트로피부호화(entropy coding)는 텍스트와 같은 일반적인 데이터들을 효율적으로 압축하는 반면에, 이미지 데이터들에 대해서는 그 성능이 다소 저하된다. 본 논문에서는 이러한 단점을 개선시키기 위한 효율적인 전처리기법(preprocessing technique)을 소개한다. 제안한 전처리기법은 입력된 명암도 등급 이미지를 무손실 압축하기 이전에, 이미지 내에서 인접한 명암도 값들의 발생빈도(occurrence frequency)를 조사한다. 다음으로 각 픽셀 쌍들의 명암도 값들을 발생빈도에 기반한 순서화된 값(ordered number)들로 대체시킨 후, 최종적으로 엔트로피부호화에 의한 압축을 수행한다. 이와 같은 단계들을 거치면서 이미지 데이터의 통계적인 특성(statistical feature)이 보다 강화되기 때문에, 엔트로피부호화에서의 무손실 압축 성능을 효율적으로 개선시킬 수 있다. 실험을 통하여 256 명암도 등급 이미지들을 산술부호화와 허프만부호화를 사용하여 압축한 결과, 제안한 전처리기법이 압축 후 비트율(bit rate)을 최대 37.49%까지 감소시켰음을 확인하였다.

• Journal of Conservation Science
• /
• v.23
• /
• pp.81-93
• /
• 2008

The analysis of ancient DNA (aDNA) in paleogenetics has become an increasingly important subject of archaeological, anthropological, biological as well as public interest. In this study, paleogenetic analyses were carried out on the human skeletal remains from a historical cemetery site in Myeongam-ri, Asan, Korea. Archaeological records show that this particular location had been used as a habitation or mortuary site as early as the Bronze Age and up until the Joseon Dynasty. Human remains of twenty individuals out of forty-nine tombs from the Goryeo to Joseon Dynasty were selected for the analysis of this study. In order to identify the genealogy of the population and traditional burial pattern of the cemetery, we conducted comparative analyses of the hyper variable regions (HVRs) in mitochondrial DNA (mtDNA) of each sample. A number of cautious steps were taken at all experimental stages in order to avoid erroneous recombination by the segmental and modern contaminations derived from the researchers. We sequenced segmental amplicons of HVRs andassigned relevant haplogroups according to the sequence polymorphism on the basis of the known mtDNA database. The result shows that diverse haplogroups were unexpectedly present in the small population group of the Myeongam-ri site. This diversity appears to be related to the geographical conditions and archaeological properties of the Myeongam-ri site.

• 보존과학연구
• /
• s.36
• /
• pp.33-48
• /
• 2015

In this study, ancient DNA analyses were carried out on the human skeletal remains from a historical cemetery site in Myeongam-ri, Asan, Korea. Human remains of 27 individuals out of tombs from the Goryeo to Joseon Dynasty were selected for the analysis of this study. In order to identify the genealogy of the population and traditional burial pattern of the cemetery, we conducted comparative analyses of the hyper variable regions (HVRs) in mitochondrial DNA (mtDNA) of each sample. We sequenced 9 segmental amplicons of HVRs and assigned relevant haplogroups according to the sequence polymorphism on the basis of the known mtDNA database. As a result, we were analyses 18 human remains of 27 individuals and result of amelogenin analysis were only 4 samples.

• Korean Journal of Heritage: History & Science
• /
• v.49 no.4
• /
• pp.38-51
• /
• 2016

This study reports on human dietary reconstruction of Joseon Dynasty using stable isotope analysis. The stable carbon and nitrogen isotope values were measured of bone collagen extracted from 25 human bones from archaeological site in Myeongam-ri, Asan. Average values of ${\delta}^{13}C$ and ${\delta}^{15}N$ are $-19.7{\pm}0.5$‰(n=23) and $9.6{\pm}1.1$‰(n=23), respectively. The isotopic data indicates that Myeongam-ri individuals consumed $C_3$ plants mainly and assumed of dietary resourced from a terrestrial animal protein. Previous isotopic studies of the Joseon era suggested that dietary composition of Joseon population was not influenced by region and burial type. Also comparison of the isotopic results of male and female from double burials showed sex-dependent dietary patterns among individuals living in the same circumstances.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.1077-1083
• /
• 2000

본 논문은 운송 컨테이너 식별자의 자동화 처리를 위한 문자 인식의 단계중 최종 문자 인식 전단계 까지의 처리 과정을 컨테이너의 특성에 맞게 제안하였으며, 이러한 전처리 과정은 문자 인식 시스템의 성능에 중요한 영향을 미친다. 제안한 방법은 먼저 입력된 컨테이너 컬러 영상을 명암 영상으로 바꾸고 전체 영상중 인식에 필요한 식별자 영역만을 경계선 검출과 형태학적 연산을 이용하여 추출한다. 이어서 다양한 배경색과 문자색을 판단하여 일반 문서와 같이 일관성있게 통일한 후, DCT를 이용한 명암도별 이진영역으로 분할한 후에 Otsu방법과 새로운 이진화방법을 자동으로 선택하여 효율적인 이진화가 이루어지도록 하였다. 이렇게 얻어진 이진 영상은 문자인식 단계로 넘어갈 수 있도록 개별 문자로 분할한다. 이 방법은 컨테이너 영상의 불균등한 배경색과 잡음으로 인하여 문자인식에 오류가 생기는 단점을 보완하였으며 컨테이너 특성을 최대한 반영함으로써 효과적인 전처리 결과를 얻을 수 있었다. 또한, 제안한 방법의 응용은 컨테이너 이외의 다른 상황에서도 매우 효과적으로 사용될 수 있으리라 본다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.2 no.1
• /
• pp.325-334
• /
• 1959

• 한국문화재보존과학회:학술대회논문집
• /
• 2003.03a
• /
• pp.49-50
• /
• 2003

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.21-28
• /
• 2006

In a face detection system based on template matching, histogram equalization or log transform is applied to an input image for the intensity normalization and the image improvement. It is known that they are noneffective in improving an image with intensity distortion by illumination variation. In this paper, we propose an efficient image improvement method using a simple regression analysis combined with a bilateral symmetry average for images with intensity distortion by illumination variation. Experimental results show that our method delivers the detection performance better than previous methods and also remarkably reduces the number of face candidates.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.437-440
• /
• 2022

In modern society, the use of the image processing field is increasing rapidly due to the 4th industrial revolution and the development of IoT technology. In particular, edge detection is widely used in various fields as an essential preprocessing process in image processing applications such as image classification and object detection. Conventional methods for detecting an edge include a Sobel edge detection filter, a Roberts edge detection filter, a Prewitt edge detection filter, Laplacian of Gaussian (LoG), and the like. However, existing methods have the disadvantage of showing somewhat insufficient performance of edge detection characteristics in a low-light level environment with low contrast. Therefore, this paper proposes an edge detection algorithm based on contrast analysis to increase edge detection characteristics even in low-light level environments.