• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.205-214
• /
• 2006

Texts in images have significant and detailed information about the scenes, and if we can automatically detect and recognize those texts in real-time, it can be used in various applications. In this paper, we propose a new text detection method that can find texts from the various camera-captured images and propose a text segmentation method from the detected text regions. The detection method proposes color variance as a detection feature in RGB color space, and the segmentation method suggests an improved K-means color clustering in RGB color space. We have tested the proposed methods using various kinds of document style and natural scene images captured by digital cameras and mobile-phone camera, and we also tested the method with a portion of ICDAR[1] contest images.

• Journal of Korean Neurosurgical Society
• /
• v.29 no.4
• /
• pp.500-506
• /
• 2000

Objective : To determine the role of preoperative embolization on postoperative neurological outcome in the treatment of cerebral AVMs, we retrospectively evaluated an effectiveness of combining preoperative embolization and microsurgery for arteriovenous malformations(AVM) of the brain. Method : Two groups(10 patients who underwent preoperative superselective embolization and surgery versus 27 patients who underwent surgery only) were compared and categorized by Spetzler-Martin grade, the size of AVM and postoperative clinical outcome using Glasgow Outcome Scale. The 37 patients included 23 males and 14 females, ranging in age from 11 to 74 years(mean 36 years). Results : The arteriovenous malformations in preoperative embolization and surgery group had a larger average greatest diameter(4.45cm versus 3.83cm) and were of higher Spetzler-Martin grade(80% versus 52% grade III through V). At 1 week after surgery, the preoperative embolization and surgery group represented a better outcome(60% versus 44% with Glasgow Outcome Scale score of 5). And over 6 months after surgery, the embolization and surgery group displayed more favorable clinical outcome(80% versus 63% with Glasgow Outcome Scale score of 5). Conclusion : Combined treatment with superselective preoperative embolization using N-butyl cyanoacrylate and direct surgery may help neurosurgeon treating the high grade AVMs thus improving the postsurgical outcome.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.63-71
• /
• 2003

This paper describes a color image segmentation algorithm based on region merging using hue difference as a restrictive condition. The proposed algorithm using mathematical morphology and a modified watershed algorithm does over-segmentation in the RGB space to preserve contour information of regions. Then, the segmentation result of color image is acquired by repeated region merging using hue differences as a restrictive condition. This stems from human visual system based on hue, saturation, and intensity. Hue difference between two regions is used as a restrictive condition for region merging because it becomes more important factor than color difference if intensity is not low. Simulation results show that the proposed color image segmentation algorithm provides efficient segmentation results with the predefined number of regions for various color images.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.272-276
• /
• 2002

본 논문은 영역을 병합할 때 두 영역의 색상 차를 영역 병합의 제한 조건으로 사용하는 칼라 영상 분할 기법을 제안하였다. 이는 먼저 영역의 경계선 정보를 잘 보존하기 위해서 RGB 공간상에서 수리형태학 필터와 변형된 워터쉐드 알고리즘을 이용하여 칼라 영상을 과분할 한다. 그리고 영역 간의 색상 차를 제한 조건으로 사용하는 영역 병합 과정을 반복 수행하여 칼라 영상의 분할 결과를 얻는다. 이는 인간 시각 시스템이 색상, 채도, 명도의 형태로 색을 구분하는 것을 기반으로 한다. 명도가 낮지 않는 경우에 색차 보다 색상 차가 중요한 요소로 작용하기 때문에 이를 영역 병합의 제한 조건으로 사용한다. 실험결과에서 제안된 칼라 영상 분할 기법은 다양한 칼라 영상에 대하여 적은 개수의 영역으로 동일한 색상을 가지는 영역의 경계선을 유지하는 효율적인 분할을 보임을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.46-48
• /
• 2004

차량항법장치(Car Navigation System ： CNS)나 지리정보시스템(Geographic Information System ： CIS)에서 공간 객체를 효율적으로 다루는 색인기법에 대한 다양한 논의가 있어왔다 기존의 방법에서는 공간 객체의 인접성(cluster)과 밀집성 만을 고려해서 색인 트리를 생성하므로, 편향된 접근 빈도론 가진 공간 객체이 대해서 효과적인 탐색시간을 제공하지 못한다. 접근 빈도를 반영한 색인 기법은 공간 데이터가 갖는 특성-2개 이상의 차원에 대한 순서 할당이 불가능-에 의해서 지리적으로 인접된 객체들을 묶지 못하고, 이로 인해서 공간 객체에 대한 효율적인 색인 기법을 제공할 수 없다. 지리 데이터에 대한 위치와 접근 빈도가 주어질 매, 색인 트리는 좌표 정보뿐 아니라 공간 객체에 대한 접근 빈도도 고려해서 생성되어야 한다 본 논문에서 제안하는 기법을 전체 영역을 세부영역으로 분할하고, 각 세부 영역에 대해서 편향색인 트리를 생성한 뒤에 트리를 병합함으로써 밀집도와 접근 빈도를 반영한, 편향된(skewed) 색인 트리를 생성하도록 한다. 편향된 색인 트리는 접근 빈도가 높은 공간객체를 상위계층(level)에 위치시킴으로써 탐색비용을 줄인다.

• Journal of KIISE:Databases
• /
• v.33 no.5
• /
• pp.495-512
• /
• 2006

Recently, researches on a future position prediction of moving objects have been progressed as the importance of the future position retrieval increases. New index structures are required to efficiently retrieve the consecutive positions of moving objects. Existing index structures significantly degrade the search performance of the moving objects because the search operation makes the unnecessary extension of the node in the index structure. To solve this problem, we propose a space partition based index structure considering the mobility of moving objects. To deal with the overflow of a node, our index structure first merges it and the sibling node. If it is impossible to merge them, our method splits the overflow node in which moving properties of objects are considered. Our index structure is always partitioned into overlap free subregions when a node is split. Our split strategy chooses the split position by considering the parameters such as velocities, the escape time of the objects, and the update time of a node. In the internal node, the split position Is determined from preventing the cascading split of the child node. We perform various experiments to show that our index structure outperforms the existing index structures in terms of retrieval performance. Our experimental results show that our proposed index structure achieves about $17%{\sim}264%$ performance gains on current position retrieval and about $107%{\sim}19l%$ on future position retrieval over the existing methods.

• Food Science and Preservation
• /
• v.21 no.4
• /
• pp.581-586
• /
• 2014

With the current consumer trend toward health and wellbeing, the demand for consumption of fresh cut vegetables has been increasing. As a popular vegetable with functional components, sedum (Sedum sarmentosum) is widely used in Korea as a side dish that needs no cooking. In this study, to provide a hurdle technology for postharvest sedum, the effects of combined treatment of 1% acetic acid for washing and $10kJ/m^2$ UV-C irradiation on the microbial growth and quality of sedum were examined. After the treatment, the sedum samples were stored at $10^{\circ}C$ for six days, and the results of their microbial analysis as well as their color, vitamin C content, and antioxidant activity were analyzed. The combined treatment with acetic acid and UV-C irradiation reduced the initial populations of the total aerobic bacteria and the yeast and molds in the sedum by 3.28 and 4.22 log CFU/g, respectively, compared to those in the control. The Hunter L, a, and b values of the sedum did not significantly differ across the treatments. In addition, the vitamin C content and the antioxidant activity decreased significantly during the storage, regardless of the treatment. These results suggest that the combined treatment with 1% acetic acid and $10kJ/m^2$ UV-C irradiation can be useful as a hurdle technology for retaining the microbiological safety and quality of sedum during its storage.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.45 no.11
• /
• pp.1696-1700
• /
• 2016

In this study, acorn pomace extract (APE) was developed as a natural chemical sanitizer and substitute for chlorine-based sanitizers such as sodium hypochlorite containing harmful substances. Antimicrobial activities of APE and its combined treatments with fumaric acid (FA) and mild heat against Listeria monocytogenes inoculated on red chard were examined. Among the treatments, combined treatment of 0.5% APE at $50^{\circ}C$ and 0.5% FA was the most effective, causing reduction of L. monocytogenes populations by 3.36 log CFU/g compared to the control. After combined treatment, populations of aerobic mesophilic bacteria in the red chard decreased by 2.89 log CFU/g during storage at $4^{\circ}C$ for 8 days compared to the control. Regarding color changes in red chard upon combined treatment, there was no significant change among the red chard samples. These results indicate that combined treatment of APE, FA, and mild heat can improve microbial safety of red chard without affecting quality such as color during storage.

• Journal of Applied Biological Chemistry
• /
• v.59 no.1
• /
• pp.69-74
• /
• 2016

The objective of this study was to examine the combined effect of fumaric acid with mild heat on the inactivation of microorganisms on spinach. Spinach leaves were inoculated with Escherichia coli O157:H7 and Listeria monocytogenes. Based on the results of single treatment of fumaric acid (0.1, 0.3, and 0.5%) or mild heat (40, 50, and $60^{\circ}C$) regarding the inactivation of the inoculated bacteria, the optimal condition for the combined treatment was suggested to be 0.5% fumaric acid and mild heat treatment at $50^{\circ}C$ for 5 min. The combined treatment of fumaric acid with mild heat caused 2.53 and 2.62 log reductions of the populations of L. monocytogenes and E. coli O157:H7, respectively. In addition, during storage of fresh spinach at $4^{\circ}C$ for 12 d, the combined treatment reduced initially the populations of total aerobic bacteria by 2.77 log CFU/g compared with the control. In particular, after 12 d of storage, the population of total aerobic bacteria for the combined treatment sample was 4.84 log CFU/g, whereas the control sample had 6.66 log CFU/g. Color and vitamin C content of spinach samples were not altered significantly by the combined treatment during storage. These results indicate that the combined treatment of fumaric acid with mild heat is an effective method to control microorganisms on spinach during storage.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1597-1599
• /
• 2015

본 논문에서는 곡물이나 광석 등의 원료들 중에서 양품 및 불량품을 검출하기 위해, Color CCD 카메라로 촬영한 원료영상에서 Mean-Shift 클러스터링 알고리즘과 단계별 병합 방법을 제안하고 있다. 먼저 원료 학습 영상에서 배경을 제거하고 영상 색 분포정도를 기준으로 모폴로지를 이용하여 영상의 전경맵을 얻는다. 전경맵 영상에 대해서 Mean-Shift 군집화 알고리즘을 적용하여 영상을 N개의 군집으로 나누고, 단계별로 위치 근접성, 색상대푯값 유사성을 비교하여 비슷한 군집끼리 통합한다. 이렇게 통합된 원료 객체는 영상채널마다의 연관관계를 반영할 수 있도록 RG/GB/BR의 2차원 컬러분포도로 표현한다. 원료 객체별로 변환된 2차원 컬러 분포도에서 분포의 주성분의 기울기와 타원들을 생성한다. 객체별 분포 타원은 테스트 원료 영상데이터에서 양품과 불량품을 검출하는 임계값이 된다. 본 논문에서 제안한 방법으로 다양한 원료영상에 실험한 결과, 기존 선별방식에 비해 사용자의 인위적 조작이 적고 정확한 원료 선별 결과를 얻을 수 있었다.