• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1222-1225
• /
• 2022

본 논문에서는 저조도 환경에서 촬영된 영상의 조도를 개선하여 얼굴 검증 정확도를 높이는 방법을 제안하였다. 입력 이미지의 조도 개선을 통해 얼굴 검출 정확도를 개선하며, 검출된 얼굴의 반복적인 조도 향상을 통해 생성된 다수의 특징 벡터를 이용하여 얼굴 검증에 이용하였다. 얼굴 검출 및 검증 정확도 측정을 위해 K-FACE 데이터셋을 이용하였다. 저조도 환경에서 촬영된 검증 이미지에 대하여, 제안하는 특징 벡터 합성 방법으로 인해, 동일인 쌍 및 타인 쌍의 유사도 점수 분포의 표준 편차가 줄어드는 경향을 확인했으며, 이로 인해 검증 성능이 높아지는 결과를 얻었다.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.9-15
• /
• 2020

In this paper, we propose a network model composed of Multi path Encoder-Decoder branches that can recognize each instance from the image. The network has two branches, Dot branch and Segmentation branch for finding the center point of each instance and for recognizing area of the instance, respectively. In the experiment, the CVPPP dataset was studied to distinguish leaves from each other, and the center point detection branch(Dot branch) found the center points of each leaf, and the object segmentation branch(Segmentation branch) finally predicted the pixel area of each leaf corresponding to each center point. In the existing segmentation methods, there were problems of finding various sizes and positions of anchor boxes (N > 1k) for checking objects. Also, there were difficulties of estimating the number of undefined instances per image. In the proposed network, an effective method finding instances based on their center points is proposed.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.15-22
• /
• 2019

In this paper, we proposed a Hangeul detection method using structural features of histogram, consonant, and vowel to solve the problem of Hangul which is separated and detected consonant and vowel The proposed method removes background by using DoG (Difference of Gaussian) to remove unnecessary noise in Hangul detection process. In the image with the background removed, we converted it to a binarized image using a cumulative histogram. Then, the horizontal position histogram was used to find the position of the character string, and character combination was performed using the vertical histogram in the found character image. However, words with a consonant vowel such as '가', '라' and '귀' are combined using a structural characteristic of characters because they are difficult to combine into one character. In this experiment, an image composed of alphabets with various backgrounds, an image composed of Korean characters, and an image mixed with alphabets and Hangul were tested. The detection rate of the proposed method is about 2% lower than that of the K-means and MSER character detection method, but it is about 5% higher than that of the character detection method including Hangul.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.11
• /
• pp.2478-2484
• /
• 2010

In this paper, real-time detection methods for Panorama system Key-Points offers. A recent study in PANORAMA system real-time area navigation or DVR to apply such research has recently been actively. The detection of the Key-Point is the most important elements that make up a Panorama system. Not affected by contrast, scale, Orientation must be detected Key-Point. Existing research methods are difficult to use in real-time Because it takes a lot of computation time. Therefore, this paper propose BLOG(BitRate Laplacian Of Gaussian)method for faster time Key-Point Detecting and Through various experiments to detect the Speed, Computation, detection performance is compared against.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.796-799
• /
• 2006

This paper presents a new method for automatic detection of skew in a document image using mathematical morphology. To speed up processing, we use reduced image but it still requires long time to estimate the skew angle so the proposed method works with region of interest, not with whole image. Character strings are connected by using morphological closing operation and a component labeling is used to select region of interest. The method considers the lowermost pixels of characters in candidate regions in the binary image of original document image. Experimental results shows that the proposed method is extremely fast and robust as well as independent of script forms.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.381-382
• /
• 2022

흘수는 선체가 물속에 얼마나 잠겨있는지를 나타내는 용어로, 선박에서는 화물의 양을 계산하거나 안정성을 평가하기 위해 흘수를 측정한다. 흘수를 측정하는 방법으로는 항해사가 부두에서 육안으로 확인하거나, 사다리를 타고 내려가 직접 확인하는 방법이 있다. 이러한 방법들은 경우에 따라 흘수 측정이 불가능하거나, 추락의 위험이 항상 존재한다는 문제가 있다. 이러한 문제를 해결하기 위해 드론 등을 통해 카메라로 선박의 흘수선 부근을 촬영하고, 필터링 및 이미지 검출 기법을 사용하여 선박의 흘수선을 탐지하는 방안을 제시하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.285-286
• /
• 2009

본 논문은 실시간 이미지 매칭을 위한 빠른 BLoG 특징점 검출방법을 제안하고 이미지 크기, 회전변화등 다양한 실험을 통하여 기존 방법과 속도와 연산량 그리고 검출 성능에 대하여 비교하고 앞으로 나아갈 방향에 대하여 제시한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.361-364
• /
• 2002

번호판 인식 시스템은 일반적으로 한 차선에 한 카메라를 사용한다. 만약 2개의 차로를 동시에 촬영하도록 카메라를 설치한다면 시스템 구축 비용이 많이 감소할 것이다. 본 논문은 이러한 시스템의 구축에 필요한 기본적인 방법으로써 이미지에서 번호판이 2개 이상 존재할 경우에도 그 위치를 모두 검출할 수 있는 방법에 대하여 제안한다. 번호판 후보 영역 추출은 모폴로지 연산을 통해 검출하고 각 후보 영역은 이진화후 제안한 검증 방법을 통해 후보 영역을 제거하고 번호판인 후보 영역에 대하여 정확한 번호판 영역을 검출한다. 제안한 검출 방법은 일반 번호판과 영업용 번호판 모두 검출할수 있다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.211-220
• /
• 2022

Recently, research on smart factories triggered by the 4th industrial revolution is being actively conducted. Accordingly, the manufacturing industry is conducting various studies to improve productivity and quality based on deep learning technology with robust performance. This paper is a study on the method of detecting tire surface defects in the visual inspection stage of the tire manufacturing process, and introduces a tire surface defect detection method using a depth image acquired through a 3D camera. The tire surface depth image dealt with in this study has the problem of low contrast caused by the shallow depth of the tire surface and the difference in the reference depth value due to the data acquisition environment. And due to the nature of the manufacturing industry, algorithms with performance that can be processed in real time along with detection performance is required. Therefore, in this paper, we studied a method to normalize the depth image through relatively simple methods so that the tire surface defect detection algorithm does not consist of a complex algorithm pipeline. and conducted a comparative experiment between the general normalization method and the normalization method suggested in this paper using YOLO V3, which could satisfy both detection performance and speed. As a result of the experiment, it is confirmed that the normalization method proposed in this paper improved performance by about 7% based on mAP 0.5, and the method proposed in this paper is effective.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1995-1996
• /
• 2011

영상 혹은 이미지 내에서 특정 물체를 검출하기 위한 일반적인 방법으로 비올라 존스(Viola-Jones) 알고리즘을 많이 사용하고 있으나 이 방법은 배경의 픽셀이 거의 동일한 값일 때에는 매우 높은 검출률을 보이는 반면 다양한 배경과 물체가 복합적으로 이루어져 있는 이미지의 경우에는 물체 검출 시 오인식 할 가능성이 매우 높다. 이러한 단점들은 얼굴 인식 시스템을 개발함에 있어 매우 불리하게 적용될 수 있는데, 본 연구는 얼굴인식 출입통제 시스템을 개발하는 과정에서 발생하는 이러한 문제점을 보완하기 위하여 비올라 존스 알고리즘에서 이용되는 하 라이크 피춰(Harr-like feature)에 새로운 형태의 사각 특징(Rectangular feature) 및 분산 특징(Varience feature) 추가하여 복잡한 배경에서도 물체 검출 성능을 향상시킬 수 있는 방법을 제안한다.