• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2826-2840
• /
• 2018

Traditional methods based active contours or region merging are powerless in processing images with blurring border or hair occlusion. In this paper, a structure based convolutional neural networks is proposed to solve segmentation of skin lesion image. The structure mainly consists of two networks which are segmentation net and discrimination net. The segmentation net is designed based U-net that used to generate the mask of lesion, while the discrimination net is designed with only convolutional layers that used to determine whether input image is from ground truth labels or generated images. Images were obtained from "Skin Lesion Analysis Toward Melanoma Detection" challenge which was hosted by ISBI 2016 conference. We achieved segmentation average accuracy of 0.97, dice coefficient of 0.94 and Jaccard index of 0.89 which outperform the other existed state-of-the-art segmentation networks, including winner of ISBI 2016 challenge for skin melanoma segmentation.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.16 no.7 s.98
• /
• pp.697-708
• /
• 2005

The forward link of the 3G CDMA system may become limited under the increasing of the number of users. The conventional channelization code, Walsh code, has not enough sizes f3r much possible users, therefore, the quasi orthogonal function(QOF), which process optimal crosscorrelation with Walsh code, is considered. In this paper, we investigate quasi orthogonal function on Jacket matrices, which can lead lower correlations values and better performance in 3G CDMA system. Moreover, to simplify the detector and improve the BER performance, a novel detection for QOF CDMA system is proposed. Finally, the simple recursive generation of the bent sequences for QOF mask function is discussed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2415-2421
• /
• 2013

Widespread personal data utilization has led personal data protection to its importance at core, and serious data spill has increased constantly as a result. Though various types of protection systems for data spill have been suggested, all these met failures in detection of personal data when printed out or preventing fatal data exposure without any protections when data spill happens. I propose API-Hook method which detects and controls personal data within printouts, and prevents data leakage through masking on the printed-out data. Also, it is verified if security is guaranteed on the documents containing personal data when implementing. In order to obtain security, it is essential to put more weights on the balance with availability than confidentiality.

• Journal of Biomedical Engineering Research
• /
• v.20 no.2
• /
• pp.155-164
• /
• 1999

In this paper, the prototype of SIS(Simulated Implantation System) for human femoral head is introduced. SIS is a software which carries on a virtual femoral head replacement surgery including 3d visualization as well as various numeric analyses between a patient's femur and artificial femur through certain stages of the image processing and of the computer graphics. Also, processes required after acquiring consecutive CT-images and projected image of an artificial femur are discussed, and the corresponding results including prototype of SIS are given.

• Convergence Security Journal
• /
• v.7 no.1
• /
• pp.1-10
• /
• 2007

Surveillance system with the fixed field of view generally has an identical background and is easy to extract and segment a moving object. However, it is difficult to extract the object when the gray level of the background is varied due to illumination condition in the real circumstance. In this paper we propose the segmentation algorithm to extract effectively the object in spite of the illumination change. In order to minimize the effect of illumination, the proposed algorithm is composed of three modes according to the background generation and the illuminational change. Then the object is finally obtained by using projection and the morphological operator in post-processing. A good segmentation performance is demonstrated by the simulation result.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.37 no.3
• /
• pp.45-52
• /
• 2000

In this study, we propose the image segmentation algorithm for facial region segmentation. The proposed algorithm separates the mean image of low frequency band from the differential image of high frequency band in order to make a boundary using HWT, and then we reduce the isolation pixels, projection pixels, and overlapped boundary pixels from the low frequency band. Also the boundaries are detected and simplified by the proposed boundary detection algorithm, which are cleared on the thinning process of 1 pixel unit. After extracting facial image boundary by using the proposed algorithm, we make the mask and segment facial image through matching original image. In the result of facial region segmentation experiment by using the proposed algorithm, the successive facial segmentation have 95.88% segmentation value.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.186-191
• /
• 1998

The first step in change detection in any SAR monitoring, including SAR interferometry, is the co-registration of the images. CCPs (Ground Control Points) for co-registration are usually detected manually, but for qualitative analyses of enormous volumes of data, some automation of the process will become necessary. An automated determination of common CCPs for the same path/row data is especially desirable. We selected the intersections of linear features as the candidates of common GCPs Very bright point targets, which are commonly used as GCPs, have the drawback of appearing and disappearing depending on the conditions of the observation. But in the case of linear features, some detailed elements may appear differently in some case, but the overall line-likeness will remain. In this study, we selected 18 common GCPs for a single-look JERS-1 SAR image of Omaezaki area in central Japan. Although the GCPs in the first image had to be selected either interactively or semi-automatically, the same GCPs in all other images were successively detected automatically using a tiny sub-image around each GCP and a dilated mask of each linear feature in the first image as the reference data.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.913-915
• /
• 2005

임의의 영상에서 얼굴을 검출하는 것은 얼굴을 인식하는데 있어서 선행되어야 할 필수과정이다. 본 논문은 조명의 변화가 심한 컬러영상에서 얼굴을 검출하는 것을 목적으로 한다. 본 논문은 기존의 기하학적 밝기분포 마스크만을 사용한 방법이 조명 변화에 취약한 단점을 보완하는데 중점을 두었다. 히스토그램 평활화(Histogram Equalization : HE)와 감마 크기 보정 (Gamma Intensity Correction : GIC) 방법을 이용해서 조명에 대한 간섭을 줄인 후, 영상 전체에서 피부 영역을 추출하고 이어서 눈 후보들을 검출한다. 검출된 눈 후보들로부터 기하학적 밝기분포 마스크를 적용하여 효과적으로 얼굴 후보들을 찾을 수 있고, 이렇게 찾아진 얼굴 후보들은 주성분분석법(Principal Component Analysis : PCA)를 이용해서 얼굴인지 여부를 판별하게 된다. 본 알고리즘은 조명 밝기 등으로 인해 검출률이 떨어졌던 단점을 보완할 수 있었고, 향후 얼굴 검출 분야에 있어서도 활용 가치가 있을 것으로 생각된다.

• Journal of the Optical Society of Korea
• /
• v.17 no.6
• /
• pp.513-517
• /
• 2013

Recently, maskless lithography (ML) systems have become popular in digital manufacturing technologies. To achieve high-throughput manufacturing processes, digital micromirror devices (DMD) in ML systems must be driven to their operational limits, often in harsh conditions. We propose an instrument and algorithm to detect DMD malfunctions to ensure perfect mask image transfer to the photoresist in ML systems. DMD malfunctions are caused by either bad DMD pixels or data transfer errors. We detect bad DMD pixels with $20{\times}20$ pixel by white and black image tests. To analyze data transfer errors at high frame rates, we monitor changes in the frame rate of a target DMD pixel driven by the input data with a set frame rate of up to 28000 frames per second (fps). For our data transfer error detection method, we verified that there are no data transfer errors in the test by confirming the agreement between the input frame rate and the output frame rate within the measurement accuracy of 1 fps.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.