• Journal of KIISE
• /
• v.44 no.2
• /
• pp.186-194
• /
• 2017

Depth-image-based rendering is a technique that can be applied in a variety of 3D-display systems. It generates the images that have been captured from virtual viewpoints by using a depth map. However, disoccluded hole-filling problems remain a challenging issue, as a newly exposed area appears in the virtual view. Image inpainting is a popular approach for the filling of the hole region. This paper presents a robust hole-filling method that reduces the error and generates a high quality-virtual view. First, the adaptive-patch size is decided using the color and depth information. Also, a partial filling method for which the patch similarity is used is proposed. These efforts reduce the error occurrence and the propagation. The experiment results show that the proposed method synthesizes the virtual view with a higher visual comfort compared with the existing methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.69-78
• /
• 2002

This paper addresses a method to automatically detect out a person's face from a given image that consists of a hair and face view of the person and a complex background scene. Out method involves an effective detection algorithm that exploits the spatial distribution characteristics of human skin color via an adaptive fuzzy color classifier (AFCC), The universal skin-color map is derived on the chrominance component of human skin color in Cb, Cr and their corresponding luminance. The desired fuzzy system is applied to decide the skin color regions and those that are not. We use RGB model for extracting the hair color regions because the hair regions often show low brightness and chromaticity estimation of low brightness color is not stable. After some preprocessing, we apply convex-hull to each region. Consequent face detection is made from the relationship between a face's convex-hull and a head's convex-hull. The algorithm using the convex-hull shows better performance than the algorithm using pattern method. The performance of the proposed algorithm is shown by experiment. Experimental results show that the proposed algorithm successfully and efficiently detects the faces without constrained input conditions in color images.

• The Journal of the Korea Contents Association
• /
• v.16 no.7
• /
• pp.689-699
• /
• 2016

As the demand for LCD increases, the importance of inspection equipment for improving the efficiency of LCD production is continuously emphasized. The pattern inspection apparatus is one that detects minute defects of pattern quickly using optical equipment such as line scan camera. This pattern inspection apparatus makes a decision on whether a pixel is a defect or not using a single threshold value in order to meet constraint of real time inspection. However, a method that uses an adaptive thresholding scheme with different threshold values according to characteristics of each region in a pattern can greatly improve the performance of defect detection. To apply this adaptive thresholding scheme it has to be known that a certain pixel to be inspected belongs to which region. Therefore, this paper proposes a region matching algorithm that recognizes the region of each pixel to be inspected. The proposed algorithm is based on the pattern matching scheme with the consideration of real time constraint of machine vision and implemented through GPGPU in order to be applied to a practical system. Simulation results show that the proposed method not only satisfies the requirement for processing time of practical system but also improves the performance of defect detection.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.45-56
• /
• 2015

In this paper we propose a very rapid moving object tracking method for an object-based auto focus on a smart phone camera. By considering the limit of non-learning approach on low-performance platforms, we use a sliding-window detection technique based on histogram features. By adapting the integral histogram, we solve the problem of the time-consuming histogram computation on each sub-window. For more speed up, we propose a local candidate search, and an adaptive scaling template method. In addition, we propose to apply a stabilization term in the matching function for a stable detection location. In experiments on our dataset, we demonstrated that we achieved a very rapid tracking performance demonstrating over 100 frames per second on a PC environment.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.05a
• /
• pp.269-276
• /
• 2007

온톨로지 매핑 기술은 시맨틱 웹을 비롯한 여러 분야에서 중요한 기술 중 하나이다. 온톨로지 매핑은 두 개의 온톨로지를 입력으로 받고, 이를 몇 개의 매개변수로 구성된 특정 알고리즘을 이용하여 두 온톨로지 간의 매칭 관계를 알아내고 이를 표현하는 절차를 말한다. 온톨로지 매핑을 이용하여 대용량 온톨로지의 통합이나, 지능화된 통합 검색을 구현할 수 있고, 여러 응용프로그램이 하나의 도메인을 공유하는 등 여러가지 방안으로 사용할 수 있다. 일반적으로 온톨로지 매핑의 성능을 판단하는데 있어서 매핑 결과를 측정하는 방법론의 측정 값을 주로 고려해왔다. 본 연구에서는 매핑을 수행할 때 두 개의 파라미터를 사용하였는데 하나는 알파이고 하나는 Threshold이다. 이것은 매핑의 정확성을 판단하는데 많은 영향을 미친다. 앞서 언급했듯이 매핑결과에 대한 측정값을 중요하게 여기기 때문에 많은 매핑관련 연구에서 알고리즘이 좋은 측정값을 도출할 수 있도록 파라미터를 조절하는 것에 초점을 맞춰왔다. 본 연구에서 측정방법에 따른 높은 측정결과를 지향하는 것이 아닌 온톨로지의 성격과 매핑결과의 사용처에 따라 파라미터를 적절히 변화시켜야 한다는 점에 주목하고, 주어진 환경과 매핑의 사용처에 알맞게 파라미터를 조정하는 방법론을 제안하고자 한다.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.2
• /
• pp.157-162
• /
• 2015

In this paper, we propose an audio fingerprinting using robust hash based on the MCLT (Modulated Complex Lapped Transform) peak-pair. In existing methods, the robust audio fingerprinting is not generated if various distortions occurred; time-scaling, pith-shifting and equalization. To solve this problem, we used the spectrum of the MCLT, an adaptive thresholding method for detection of prominent peaks and the novel hash function in the audio fingerprinting. Experimental results show that the proposed method is highly robust in various distorted environments and achieves better identification rates compared to other methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.148-151
• /
• 2010

심장관련 질환은 현대사회에서 업무 과중과 스트레스에 의해 발병 가능성이 높아지고 있으며, 일상생활 중 건강상태를 지속적으로 모니터링하여 심장질환 관련 응급상황에 대처하기위한 많은 연구들이 수행되고 있다. 본 연구에서는 가정 또는 사무실에서 무구속적인 방법으로 지속적인 심장 활동상태의 모니터링이 가능한 무구속 의자형 심탄도 계측 시스템을 구현하였다. 구현된 시스템에서 계측된 심탄도 신호로부터 건강모니터링을 위한 특징성분을 검출하기위해 웨이브렛 변환과 템플릿 매칭을 혼합한 신호처리방법을 제안하였다. 또한 적응 문턱치를 통해 심탄도 신호에서 심박동을 검출하였으며 심박동의 간격으로부터 HRV(heart rate variabillity)를 계산하였다. 구현된 시스템의 성능평가를 위하여 심전도와 동시에 심탄도를 측정하였으며, 두 신호로부터 심박동 검출 성능을 비교하여 구현된 무구속 의자형 심탄도 계측 시스템의 유용성 및 무자각 건강모니터링의 가능성을 확인하였다. 또한 스트레스에 따른 HRV의 변화를 관찰하기 위하여 피실험자로부터 인위적으로 숨을 참고 강제호기를 통해 흉강내압을 증가시켜 인위적인 육체적 스트레스를 가하는 발살바를 유도하였으며, HRV의 시간 및 주파수 영역에서 도출되는 파라미터들을 평가하여 심탄도 모니터링을 통해 안정 상태와 스트레스 상태의 판별 및 무구속 건강모니터링의 가능성을 평가하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.63-68
• /
• 2010

The Color Management System in recent printers adopts ICC profiles for both monitors and printers. However, the ICC profile doesn't contain the characteristics of reproduced color on each monitor, because the color on each monitor is changed by user adjustment such as color temperature, brightness, and contrast adjustment. It is also depended on the backlight type and lifetime. As a result, unwanted color is reproduced on the printed paper, not like that on the monitor. To overcome the color difference between monitors and printers, it is needed to control the information of ICC profile. That is, first, the ICC profile is generated by the measurement of monitors having user set, then, through the CMS, the color on monitors can be produced on printed paper. However, it is difficult to apply the above system for normal users due to absence of measuring equipment and time consuming process. Therefore, this paper proposes a novel color matching technique based on the estimation of condition for each monitor having user set. The estimation is performed by a simple comparison visual test using a test image on printed paper and monitor. Then, the condition of monitor is applied to the ICC profile. As a result, the new ICC profile contains the color difference between user monitor and printer. The experimental results show the printed images using our proposed method have almost similar color with those on monitors.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.535-542
• /
• 2021

Purpose: The purpose of this study is to prevent recidivism by recognizing the seriousness of recidivism against sexual offenders under the age of 13 and providing customized social adaptation services based on risk. Method: The study evaluate the efficiency of existing models and proposed model systems, and compare and review what features and operational differences exist from existing models. Result: The proposed model will collect data from related agencies on sexual violence offenders with a high risk of recidivism and classify them into three risk groups through risk algorithms to provide social adaptation services for each risk group. In addition, by monitoring primary social support matching data, storing and re-analyzing the results data to rematch social support services, the model differs from the existing model in preventing recidivism of sexual violence offenders from a long-term perspective. Conclusion: The proposed model of this study is meaningful in that it proposed the basic data of a response system to prevent recidivism from a long-term perspective of sexual offenders with the highest risk of recidivism by collecting and analyzing data on sexual offenders.

• The KIPS Transactions:PartA
• /
• v.14A no.7
• /
• pp.409-420
• /
• 2007

Software adaptation may be required to interact between heterogeneous platforms and to react to rapid change of environment in ubiquitous computing. Web service provides a way to use heterogeneous and distributed services or resources to utilize and organize them. But it is not easy to retrieve appropriate services when we search services because web service lacks of semantic information. Semantic web service provides additional information of services, but it does not support a method to match them in various ways. We can adapt and extend web applications by using web service, but a method for management and administration is still needed. Therefore in this paper, we propose a framework for dynamic growing of web service applications based on ESB(Enterprise Service Bus) and agent and provide a prototype to show its usefulness.