• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.433-438
• /
• 2019

This paper proposes a method of improving deep learning based numbers and characters recognition performance on parts of drawing through image preprocessing. The proposed character recognition system consists of image preprocessing and 7 layer deep learning model. Mathematical morphological filtering is used as preprocessing to remove the lines and shapes which causes false recognition of numbers and characters on parts drawing. Further.. Further, the used deep learning model is a 7 layer deep learning model instead of VGG-16 model. As a result of the proposed OCR method, the recognition rate of characters is 92.57% and the precision is 92.82%.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.664-666
• /
• 2020

데이터의 다양성은 학습에 따른 모델의 성능을 좌지우지하는 중요한 요소이다. 그렇기 때문에 많은 양의 데이터를 확보하는 것은 학습에 있어서 아주 중요하다. 하지만, 데이터를 수집하는 것은 시간과 비용이 많이 드는 단계 중 하나이다. 본 논문에서는 제한된 데이터를 가지고 이미지 처리를 거쳐 대량의 데이터로 증폭시켜 많은 양의 데이터를 확보하는 과정에 대해 제안한다. 가지고 있는 YOLOv4용 학습 데이터 셋을 활용하여 사용자로부터 입력받은 확대/축소 비율, 각도로 데이터를 변형하고, 이렇게 추가로 생성된 데이터 셋을 기존 학습 데이터 셋에 재포함시키는 소프트웨어를 개발하는 것을 목표로 한다. 구현된 소프트웨어로 증폭된 대량의 데이터 셋을 다시 원본 학습 데이터 셋에 추가하고, 같은 영상에 대해서 원본 데이터 셋만 학습시킨 경우의 객체 검출 결과와 증폭된 학습 데이터 셋이 포함된 데이터 셋의 경우의 객체 검출 결과를 비교하여 그 성능을 검증하고 분석하도록 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1265-1267
• /
• 2022

방대한 분량의 콘텐츠 홍수 속에서 원하는 소재를 찾기 위해 콘텐츠 내용을 검색할 수 있는 효과적인 방법이 지원되는 것은 창작을 자유롭게 하고, 콘텐츠 활용도를 높이기 위해 매우 중요하다. KBS 바다 서비스의 경우 분류체계 방법을 사용하고 있으나. 최근 딥러닝을 이용한 인공지능 기술의 발전으로 콘텐츠의 내용을 인공지능 기술로 태깅하고, 태깅된 텍스트 정보를 이용하여 검색할 수 있는 기술 개발이 활발히 수행되고, 국가적으로도 해당 기술을 지원하고 있다. 본 논문에서는 이러한 기술 개발의 선행 요소인 방송사의 제작과정에서 요구되는 동영상 소재 콘텐츠 검색의 요구사항을 KBS 비디오 아카이브 검색 키워드 실제 사용 데이터를 이용하여 분석하였다. 약 1,000여건의 검색 키워드 분석과 이용자와 운영자의 응답 내용을 고찰한 결과, 특정 키워드에 집중하여 검색할 수 있도록 보완하여 주는 것이 필요함을 알아내었다. 또한, 검색 범위를 효과적으로 축소하여 검색을 손쉽고 빠르게 할 수 있는 방법을 고찰하였다. 본 논문에서는 미디어 창작에서 필요한 소재 콘텐츠를 찾기 위해 연구 개발해야 할 미디어 속성 추출 기술의 방향성을 제시하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.4
• /
• pp.11-21
• /
• 2013

The conventional real-time signal control strategy for oversaturated situation generally requires a number of detectors at the intersection in order to identify the queue length at each approach. Also, existing strategy for the spillback has limited effect due to the temporal spillback control which only reduce the green split at the approach. In this study, a signal control system utilizing the imagery information from ITS roadside equipment is developed for operation of oversaturated intersections. The strategy calculates the saturation ratio based on the queue length extracted from ITS RSE, and designs the signal control variables according to the saturation ratio. The signal control strategy is divided into two phases: oversaturated and supersaturated. In oversaturated conditions, timing plan for main approach is optimized by the queue length. In oversaturated conditions where spillback might occur, the signal timing is designed in order to avoid the spillback. To increase field adaptability, the strategy is designed to adjust the split length, all-red-time, and clearance time, and keep the major signal control variables intact. The result of the simulation shows that in oversaturated conditions, the improvement is similar to the real-time signal control system. In case of, oversaturated conditions, however, the effect of the strategy is superior to that of a real-time system.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1121-1135
• /
• 2005

This paper proposes a moving object extraction method using the contrast map and salient points. In order to make the contrast map, we generate three-feature maps such as luminance map, color map and directional map and extract salient points from an image. By using these features, we can decide the Attention Window(AW) location easily The purpose of the AW is to remove the useless regions in the image such as background as well as to reduce the amount of image processing. To create the exact location and flexible size of the AW, we use motion feature instead of pre-assumptions or heuristic parameters. After determining of the AW, we find the difference of edge to inner area from the AW. Then, we can extract horizontal candidate region and vortical candidate region. After finding both horizontal and vertical candidates, intersection regions through logical AND operation are further processed by morphological operations. The proposed algorithm has been applied to many video sequences which have static background like surveillance type of video sequences. The moving object was quite well segmented with accurate boundaries.

• Archives of design research
• /
• v.18 no.3 s.61
• /
• pp.209-218
• /
• 2005

Consciously or not, producers have to make many aesthetic choices in creative process of video production. If there are general acceptable aesthetic principles to make right choice it would be guideline of aesthetic decision to somewhat reduce mistakes and errors in the process. This paper proposes a theoretical approach on establishing the media aesthetic principle of 3D animation camera working, which is the most suitable for animation production context. We describe the Herbert Zettl's applied media aesthetics related directly to the camera, which is about the two-Dimensional field focusing on aspect radio and forces within the screen, three-dimensional field focusing on depth, volume, and four-dimensional field focusing on time and motion. In order to have theoretical approach we made an analysis on comparing a camera working of movie with 3D computer animation's one, and reconstructed these basic principles to be suited for the 3D animation production. When applied media aesthetics of the traditional camera working are applied to the 3D animation production, it could be an efficient guideline for it. Futhermore, if we develop the research for the relationship with various visual languages with the basis of these principles, the theory of creative picture composition method for the 3D animation production will be logically and systematically established.

• Journal of Internet Computing and Services
• /
• v.7 no.2
• /
• pp.23-35
• /
• 2006

This work presents o novel method which extract facial region und features from motion picture automatically and controls the 3D facial expression in real time. To txtract facial region and facial feature points from each color frame of motion pictures a new nonparametric skin color model is proposed rather than using parametric skin color model. Conventionally used parametric skin color models, which presents facial distribution as gaussian-type, have lack of robustness for varying lighting conditions. Thus it needs additional work to extract exact facial region from face images. To resolve the limitation of current skin color model, we exploit the Hue-Tint chrominance components and represent the skin chrominance distribution as a linear function, which can reduce error for detecting facial region. Moreover, the minimal facial feature positions detected by the proposed skin model are adjusted by using edge information of the detected facial region along with the proportions of the face. To produce the realistic facial expression, we adopt Water's linear muscle model and apply the extended version of Water's muscles to variation of the facial features of the 3D face. The experiments show that the proposed approach efficiently detects facial feature points and naturally controls the facial expression of the 3D face model.

• The Journal of Korean Society for Radiation Therapy
• /
• v.34
• /
• pp.73-82
• /
• 2022

Purpose: The purpose of this study is to evaluate the effectiveness of reducing the absorbed dose to the ovaries and the quality of the CBCT image when using the Halcyon^TM Fast kV CBCT of cervical cancer patients of child-bearing age who performed ovarian transposition Materials and Methods : Contouring of the cervix and ovaries required for measurement was performed on the computed tomography images of the human phantom (Alderson Rando Phantom, USA), and three Optically Stimulated Luminescence Dosimeter(OSLD) were attached to the selected organ cross-section, respectively. In order to measure the absorbed dose to the cervix and ovaries in the Truebeam^TM pelvis mode (Hereinafter referred to as TP), The Halcyon^TM Pelvis mode (Hereinafter referred to as HP) and The Halcyon^TM Pelvis Fast mode (Hereinafter referred to as HPF), An image was taken with a scan range of 17.5 cm and also taken an image that reduced the Scan range to 12.5cm. A total of 10 cumulative doses were summed, It was replaced with a value of 23 Fx, the number of cervical cancer treatments, and compared In additon, uniformity, low contrast visibility, spatial resolution, and geometric distortion were compared and analyzed using Catphan 504 phantom to compare CBCT image quality between equipment. Each factor was repeatedly measured three times, and the average value was obtained by analysing with the Doselab (Mobius Medical Systems, LP. Versions: 6.8) program. Results: As a result of measuring absorbed dose by CBCT with OSLD, TP and HP did not obtain significant results under the same conditions. The mode showing the greatest reduction value was HPF versus TP. In HPF, the absorbed dose was reduced by 39.8% in the cervix and 19.8% in the ovary compared to the TP in the scan range of 17.5 cm. the scan range was reduced to 12.5 cm, absorbed dose was reduced by 34.2% in the cervix and 50.5% in the ovary. In addition, result of evaluating the quality of the image used in the above experiment, it complied with the equipment manufacturer's standards with Geometric Distortion within 1mm (SBRT standard), Uniformity HU, LCV within 2.0%, Spatial Resolution more than 3 lp/mm. Conclusion: According to the results of this experiment, Halcyon^TM can select more various conditions than Truebeam^TM in treatment of fertility woman who have undergone ovarian Transposition , because it is important to reduce the radiation dose by CBCT during radiation therapy. So finally we recommend Halcyon^TM Fast kV CBCT which maintains image quality even at low mAs. However, it is consider that the additional exposure to low doses can be reduced by controlling the imaging range for patients who have undergone ovarian transposition in other treatment machines.

• The Journal of Korean Society for Radiation Therapy
• /
• v.27 no.1
• /
• pp.1-11
• /
• 2015

Purpose : Evaluating absorbed dose related to 2D and 3D imaging confirmation devices Materials and Methods : According to the radiographic projection conditions, absorbed doses are measured that 3 glass dosimeters attached to the centers of 0', 90', 180' and 270' in the head, thorax and abdomen each with Rando phantom are used in field size $26.6{\times}20$, $15{\times}15$. In the same way, absorbed doses are measured for width 16cm and 10cm of CBCT each. OBI(version 1.5) system and calibrated glass dosimeters are used for the measurement. Results : AP projection for 2D imaging check, In $0^{\circ}$ degree absorbed doses measured in the head were $1.44{\pm}0.26mGy$ with the field size $26.6{\times}20$, $1.17{\pm}0.02mGy$ with the field size $15{\times}15$. With the same method, absorbed doses in the thorax were $3.08{\pm}0.86mGy$ to $0.57{\pm}0.02mGy$ by reducing field size. In the abdomen, absorbed dose were reduced $8.19{\pm}0.54mGy$ to $4.19{\pm}0.09mGy$. Finally according to the field size, absorbed doses has decreased by average 5~12%. With Lateral projection, absorbed doses showed average 5~8% decrease. CBCT for 3D imaging check, CBDI in the head were $4.39{\pm}0.11mGy$ to $3.99{\pm}0.13mGy$ by reducing the width 16cm to 10cm. In the same way in thorax the absorbed dose were reduced $34.88{\pm}0.93(10.48{\pm}0.09)mGy$ to $31.01{\pm}0.3(9.30{\pm}0.09)mGy$ and $35.99{\pm}1.86mGy$ to $32.27{\pm}1.35mGy$ in the abdomen. With variation of width 16cm and 10cm, they showed 8~11% decrease. Conclusion : By means of reducing 2D field size, absorbed dose were decreased average 5~12% in 3D width size 8~11%. So that it is necessary for radiation therapists to recognize systematical management for absorbed dose for Imaging confirmation. and also for frequent CBCT, it is considered whether or not prescribed dose for RT refer to imaging dose.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.9 no.3
• /
• pp.39-52
• /
• 1999

In this paper we propose a new watermarking technique for copyright protection of images. The proposed technique is based on a spatial masking method with a spatial scale parameter. In general it becomes more robust against various attacks but with some degradations on the image quality as the amplitude of the watermark increases. On the other hand it becomes perceptually more invisible but more vulnerable to various attacks as the amplitude of the watermark decreases. Thus it is quite complex to decide the compromise between the robustness of watermark and its visibility. We note that watermarking using the spread spectrum is not robust enought. That is there may be some areas in the image that are tolerable to strong watermark signals. However large smooth areas may not be strong enough. Thus in order to enhance the invisibility of watermarked image for those areas the spatial masking characteristics of the HVS(Human Visual System) should be exploited. That is for texture regions the magnitude of the watermark can be large whereas for those smooth regions the magnitude of the watermark can be small. As a result the proposed watermarking algorithm is intend to satisfy both the robustness of watermark and the quality of the image. The experimental results show that the proposed algorithm is robust to image deformations(such as compression adding noise image scaling clipping and collusion attack).