http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Whoi-Yul Kim 한국정보과학회 1997 Journal of Electrical Engineering and Information Vol.2 No.6
In order to achieve scale- and rotation-invariance in recognizing unoccluded objects in binary images using Zemike moment features, an image of an object has often been normalized first by its zeroth-order moment (ZOM) or area. With elongated objects such as characters, a stroke width varies with the threshold value used; it becomes one or two pixels wider or thinner. The variations of the total area of the character becomes significant when the character is relatively thin with respect to its overall size, and the resulting normalized moment features are no longer reliable. This dilation/erosion effect is more severe when the object is not focused precisely. In this paper, we analyze the ZOM method and propose as a normalization method, the maximum enclosing circle (MEC) centered at the centroid of the character. We compare both the ZOM and MEC methods in their performance through various experiments.
Kim, Whoi-Yul The Korean Institute of Electrical Engineers 1997 Journal of Electrical Engineering and Information Vol.2 No.6
In order to achieve scale- and rotation-invariance in recognizing unoccluded objects in binary images using Zernike moment features, an image of an object has often been normalized first by its zeroth-order moment (ZOM) or area. With elongated objects such as characters, a stroke width varies with the threshold value used, it becomes one or two pixels wider or thinner. The variations of the total area of the character becomes significant when the character is relatively thin with respect to its overall size, and the resulting normalized moment features are no longer reliable. This dilation/erosion effect is more severe when the object is not focused precisely. In this paper, we analyze the ZOM method and propose as a normalization method, the maximum enclosing circle (MEC) centered at the centroid of the character. We compare both the ZOM and MEC methods in their performance through various experiments.
NAM, Sang Yul,KIM, Duk Man,KIM, Hyung Suk,KOO, Tae Whoi 慶熙大學校 1974 論文集 Vol.8 No.-
照射前 Sprague-Dawley系 雄性인 흰쥐에 生理的食鹽水 或은 methylene blue(40㎎/㎏)를 腹腔內 注射한 後 單回 全身감마線 照射로 360㎭의 線量을 投與하였다. 血淸알칼리性 phosphatase (SALP)와 血淸酸性 phosphatase (SACP)의 活性을 照射後 여러 時間區에서 測定하였다. (1) 正常흰쥐의 SALP 및 SACP의 平均値는 各各 5.89±0.54 및 0.93±0.08 units/ℓ이었다. (2) SALP 및 SACP의 平均値는 一般的으로 감마線 全身照射後 460 時間期間에 걸쳐 有意性있게 增加하는 傾向이 나타났다. (3) SALP의 平均値는 對照群에 있어서 6,25 및 190 時間區에서 各各 7.56±0.54, 7.01±0.56 및 7.71±0.61 units/ℓ에 이르렀으나, 한便 放射線保護效果가 있는 methylene blue로 處理된 群에서는 단지 6.73±0.64, 6.00±0.77 및 6.56±0.88 units/ℓ에 이르렀다. (4) SACP의 平均値는 對照群에 있어서 6 및 130時間區에서 各各 1.19±0.07 및 1.15±0.10 units/ℓ에 이르렀으나, 한便 保護效果가 있는 methylene blue로 處理된 群에서는 단지 1.03±0.13 및 1.00±0.08에 이르렀다. (5) 以上의 結果로 미루어보아 放射線照射前에 methylene blue를 投與하였을 境遇, 흰쥐의 SALP 및 SACP活性에 對하여 顯著하게 放射線保護作用이 있는 것으로 思料된다.
영상 데이터베이스 검색 시스템의 검색효율 평가를 위한 새로운 평가척도
서창덕,김회율 한국방송공학회 2000 방송공학회논문지 Vol.5 No.1
This paper proposes a single metric to measure and evaluate the retrieval effectiveness of image database retrieval system that requires an ordered ranking. There are four conditions to be a gad ranking system. First, the number of relevant images among the retrieved should be as large as possible. Secondly, the number of irrelevant images should be smaller. Third, the average rank of relevant images should be higher. Last, the relevant images should be clustered close together. The conventional evaluation measures only reflect a part of the conditions listed above, and the evaluated results are coarse or inaccurate. The proposed NDS, however, resolves all those problems. In order to prove the efficiency of the NDS, we generate patterns of _nC_r(_(10)C_5=252, _(20)C_9=167.960) to evaluate and compare with other measures. The patterns were generated automatically by a recursive function call on the assumption that 'r' relevant images are retrieved within the range of 'n'.
Parallelized Tube Rearrangement Algorithm for Online Video Synopsis
Ra, Moonsoo,Kim, Whoi-Yul IEEE 2018 IEEE signal processing letters Vol.25 No.8
<P>Video synopsis allows us to analyze security videos efficiently by condensing or shortening a long video into a short one. To generate a condensed video, moving objects (a.k.a. object tubes) in the video are rearranged in the temporal domain using a predefined objective function. The objective function consists of several energy terms which play important roles in making a visually appealing condensed video. One of the energy terms, collision energy, creates a bottleneck in the computation because it requires two object tubes to calculate the degree of collision between them. Existing approaches try to reduce the computation time of the collision energy calculation by reducing the number of tubes processed at once. However, those approaches are not sufficient to generate condensed video when the number of object tubes becomes large.</P> <P>In this letter, we propose a fast Fourier transform (FFT)-based parallelized tube rearrangement algorithm. To take advantage of both parallel processing and FFT, we represent object tubes as three-dimensional binary matrices (occupation matrices). An objective function of the tube rearrangement problem is defined on the occupation matrix, and a starting position for each tube in the temporal domain is then determined by optimizing the objective function. Throughout the experiments, the proposed algorithm took a much shorter time to condense the video than existing algorithms, while other performance metrics were similar.</P>
적응적 UV-histogram과 템플릿 매칭을 이용한 거리 영상에서의 고속 인간 검출 방법
윤범식(Bumsik Yoon),김회율(Whoi-Yul Kim) 대한전자공학회 2014 전자공학회논문지 Vol.51 No.9
본 논문에서는 이전 연구 방법에서의 UV-histogram을 확장하여 적응적 UV-histogram을 제시함으로써, 복잡한 구성의 장면에서 사람의 검출율을 높이는 방법을 제시한다. 제안 방법은 먼저 U-histogram에서 사람 영역을 1차 추출하고, 각각의 레이블링된 U에서 V-histogram을 생성함으로써, 이전 방법에서 구분할 수 없었던 사람 후보 영역을 정확하게 추출한다. 또한 제안 방법은 사람 판정시, 초점거리와 거리에 따라 적응적인 크기를 가지는 오메가 모양의 템플릿을 이용하여 검출의 정확도를 높였으며, 누적 영상을 이용하여 오검출을 템플릿 재매칭 함으로써, occlusion에도 강인한 특성을 가진다. 실험 결과는 Bae의 연구방법에 비하여 복잡한 환경에서 약 15%의 정확도 향상, 80%의 재현율 향상을 보이며, Xia의 연구방법에 비하여 20배 빠른 수행속도를 보여, 제안 방법의 성능이 우수함을 입증한다. In this paper, a fast human detection method using adaptive UV-histogram and template matching is proposed. The proposed method improves the detection rate in the scene of complex environment. The method firstly generates U-histogram to extract human candidates and adaptively generates V-histogram for each labled U-histogram, thus it could extract humans correctly, which was impossible in the previous method. The method tries to match the human candidates with the adaptively sized omega shape template to the focal length and distance in order to improve the detection accuracy. It also detects false positives by rematching the template with accumulated foreground images and hence is robust to the occlusion. Experimental results showed that the proposed method has superior performance to the Bae’s method in the complex environment with about 15% improvement in precision and 80% in recall and has 20 times faster processing time than Xia’s method.