• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.456-458
• /
• 2023

원본 이미지를 변형하여 학습용 데이터를 확장하는 기법에 대해서는 이전부터 꾸준히 논의된 바가 있다. 턴 테이블과 크로마 키를 이용하여 객체의 영상을 촬영하고 프레임을 추출하여 이미지 분류, 영상 내 객체 탐지 등에 사용이 가능한 데이터 셋의 확장 구축 방안에 대해 다루며, 성능 분석 결과 평균 90% 이상의 객체 검출률을 보였으며 객체 탐지 모델의 경우에서 보다 높은 정확도를 보임을 확인할 수 있었다. 영상내 단일 객체를 인지하기 위한 상황을 위해 본 논문이 제시하는 데이터셋 구축 방안은 충분한 효과를 보일 수 있을 것으로 기대된다.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.375-380
• /
• 2010

Most of previous algorithms of object boundary extraction have been studied for extracting the boundary of single object. However, multiple objects are much common in the real image. The proposed algorithm of extracting the boundary of each of multiple objects has two steps. In the first step, we propose the fast method using the outer and inner products; the initial contour including multiple objects is split and connected and each of new contours includes only one object. In the second step, an improved active contour model is studied to extract the boundary of each object included each of contours. Experimental results with various test images have shown that our algorithm produces much better results than the previous algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1790-1796
• /
• 2021

A large amount of image data sets are required for image deep learning, and there are many differences in the method of obtaining images and constructing image data sets depending on the type of object. In this paper, we presented a method of constructing an image data set for deep learning and analyzed the performance that varies depending on the object to be tracked. We took a video by rotating the object, and then created a data set by segmenting the video using the proposed data set construction method. As a result of performance analysis, detection rate was more than 95%, and detection rate of objects with little change in shape was higher performance. It is considered that it is effective to use the data set construction method presented in this paper for a situation in which it is difficult to obtain image data and to track an object with little change in shape within a video.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.3
• /
• pp.82-98
• /
• 2019

The importance of spatial information is rapidly rising. In particular, 3D spatial information construction and modeling for Real World Objects, such as smart cities and digital twins, has become an important core technology. The constructed 3D spatial information is used in various fields such as land management, landscape analysis, environment and welfare service. Three-dimensional modeling with image has the hig visibility and reality of objects by generating texturing. However, some texturing might have occlusion area inevitably generated due to physical deposits such as roadside trees, adjacent objects, vehicles, banners, etc. at the time of acquiring image Such occlusion area is a major cause of the deterioration of reality and accuracy of the constructed 3D modeling. Various studies have been conducted to solve the occlusion area. Recently the researches of deep learning algorithm have been conducted for detecting and resolving the occlusion area. For deep learning algorithm, sufficient training data is required, and the collected training data quality directly affects the performance and the result of the deep learning. Therefore, this study analyzed the ability of detecting the occlusion area of the image using various image quality to verify the performance and the result of deep learning according to the quality of the learning data. An image containing an object that causes occlusion is generated for each artificial and quantified image quality and applied to the implemented deep learning algorithm. The study found that the image quality for adjusting brightness was lower at 0.56 detection ratio for brighter images and that the image quality for pixel size and artificial noise control decreased rapidly from images adjusted from the main image to the middle level. In the F-measure performance evaluation method, the change in noise-controlled image resolution was the highest at 0.53 points. The ability to detect occlusion zones by image quality will be used as a valuable criterion for actual application of deep learning in the future. In the acquiring image, it is expected to contribute a lot to the practical application of deep learning by providing a certain level of image acquisition.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.87-94
• /
• 2008

In this paper, an extraction method of objects of interest in the color images is proposed. It is possible to extract objects of interest from a complex background without any prior-knowledge based on the proposed method. For object extraction, Gator images that contain information of object location, are created by using Gator filter. Based on the images the initial location of attention windows is determined, from which image features are selected to extract objects. To extract object, I modify the previous method partially and apply the modified method. To evaluate the performance of propsed method, precision, recall and F-measure are calculated between the extraction results from propsed method and manually extracted results. I verify the performance of the proposed methods based on these accuracies. Also through comparison of the results with the existing method, I verily the superiority of the proposed method over the existing method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.296-299
• /
• 2011

임상 진단에서 환자의 의료 영상을 시각적으로 보고 해석하거나 또는 수작업으로 영상을 해석하여 진단에 이용한다. 이러한 수작업의 불편함을 해소하기 위하여 의료 영상처리 알고리즘들이 많이 연구되어오고 있다. 그 중 영상처리의 정확도 부분이 많은 문제가 되고 있는데, 특히 세포영상에서는 인접한 영역의 분할이 가장 중요시되고 있다. 본 논문은 이러한 인접영역의 분할을 위해 객체의 기하 정보인 곡률(Curvature) 정보와 컨벡스 헐(Convex Hull)을 통한 분할 방법을 제안하고자 한다. 실험 결과 87.5%의 정확도가 검출되었으며 향후 인접 객체의 내부정보까지 고려한 효과적인 분할 방법을 연구하고자 한다.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.61-68
• /
• 2018

In this paper, we propose a method of character detection by analyzing image enhancement and character type to detect characters in natural images that can be acquired in everyday life. The proposed method emphasizes the boundaries of the object part using the unsharp mask in order to improve the detection rate of the area to be recognized as a character in a natural image. By using the boundary of the enhanced object, the character candidate region of the image is detected using Maximal Stable Extermal Regions (MSER). In order to detect the region to be judged as a real character in the detected character candidate region, the shape of each region is analyzed and the non-character region other than the region having the character characteristic is removed to increase the detection rate of the actual character region. In order to compare the objective test of this paper, we compare the detection rate and the accuracy of the character region with the existing methods. Experimental results show that the proposed method improves the detection rate and accuracy of the character region over the existing character detection method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.655-657
• /
• 2022

본 논문은 유튜브에 업로드 된 운동 영상을 시청하는 사람의 얼굴 영역을 YoloV3을 이용하여 얼굴 영상에서 눈 및 입술영역을 검출하는 방법을 연구하여, YoloV3은 딥 러닝을 이용한 물체 검출 방법으로 기존의 특징 기반 방법에 비해 성능이 우수한 것으로 알려져 있다. 본 논문에서는 영상을 다차원적으로 분리하고 클래스 확률(Class Probability)을 적용하여 하나의 회귀 문제로 접근한다. 영상의 1 frame을 입력 이미지로 CNN을 통해 텐서(Tensor)의 그리드로 나누고, 각 구간에 따라 객체인 경계 박스와 클래스 확률을 생성해 해당 구역의 눈과 입을 검출한다. 검출된 이미지 감성 분석을 통해, 운동 영상 중 하이라이트 부분을 자동으로 선별하는 시스템을 설계하였다.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.263-272
• /
• 2007

This paper proposes a skeleton-based hierarchical shape description scheme, called a skeleton tree, for accurate shape-based image retrieval. A skeleton tree represents an object shape as a hierarchical tree where high-level nodes describe parts of coarse trunk regions and low-level nodes describe fine details of boundary regions. Each node refines the shape of its parent node. Most of the noise disturbances are limited to bottom level nodes and the boundary noise is reduced by decreasing weights on the bottom levels. The similarity of two skeleton trees is computed by considering the best match of a skeleton tree to a sub-tree of another skeleton tree. The proposed method uses a hybrid similarity measure by employing both Fourier descriptors and moment invariants in computing the similarity of two skeleton trees. Several experimental results are presented demonstrating the validity of the skeleton tree scheme for the shape description and indexing.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1367-1368
• /
• 2015

본 논문에서는 지능형 인식 기술인 RBFNNs 패턴분류기와 추적 기법인 Particle Filter를 융합한 다중 객체 추적 시스템을 설계한다. 여러 객체가 동시에 존재하는 상황에서 각각의 객체를 개별적으로 추적하기 위해 추적 기법에 인식 알고리즘을 추가하였다. 학습 데이터는 다양한 상황에서 정확한 인식 결과를 확인하기 위해 정면, 좌, 우측 데이터를 사용하였으며, 테스트 영상에서 검출된 얼굴 이미지를 테스트 데이터로 사용하였다. 추적 알고리즘인 Particle Filter를 사용하여 검출된 객체의 추적을 수행하며, 인식 결과를 바탕으로 다양한 객체에 대하여 개별적인 추적을 수행한다.