• Journal of the Korea Convergence Society
• /
• v.10 no.6
• /
• pp.7-14
• /
• 2019

In this paper, we propose a Cascade Classifier face detection method using the Haar-like feature, which is complemented by the Flood Fill algorithm for lossy areas due to illumination and shadow in YCbCr color space extraction. The Cascade Classifier using Haar-like features can generate noise and loss regions due to lighting, shadow, etc. because skin color extraction using existing YCbCr color space in image only uses threshold value. In order to solve this problem, noise is removed by erosion and expansion calculation, and the loss region is estimated by using the Flood Fill algorithm to estimate the loss region. A threshold value of the YCbCr color space was further allowed for the estimated area. For the remaining loss area, the color was filled in as the average value of the additional allowed areas among the areas estimated above. We extracted faces using Haar-like Cascade Classifier. The accuracy of the proposed method is improved by about 4% and the detection rate of the proposed method is improved by about 2% than that of the Haar-like Cascade Classifier by using only the YCbCr color space.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.337-342
• /
• 2002

This paper proposes a new adaptive image labeling algorithm fur object analysis of the binary images. The proposed labeling algorithm need not merge/order of complex equivalent labels like classical labeling algorithm and the processing is done during only 1 Pass. In addition, this algorithm can be extended for gray-level image easily. Experiment result with HIPR image library shows that the proposed algorithm process more than 2 times laster than compared algorithm.

• Smart Media Journal
• /
• v.2 no.4
• /
• pp.20-26
• /
• 2013

This paper presents an approach to Mongolian car plate recognition using artificial neural network. Our proposed method consists of two steps: detection and recognition. In detection step, we implement Flood fill algorithm. In recognition step we proceed to segment the plate for each Cyrillic character, and use an Artificial Neural Network (ANN) machine - learning algorithm to recognize the character. We have learned the theory of ANN and implemented it without using any library. A total of 150 vehicles images obtained from community entrance gates have been tested. The recognition algorithm shows an accuracy rate of 89.75%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.9
• /
• pp.20-29
• /
• 2018

Owing to the changing climate and recent flood events, flood damage caused by river levee collapse and overflow is on the rise in Korea, making it necessary to enhance river levee maintenance technologies to deal with various flood damage scenarios. This paper proposes the evaluation system of a river-levee safety map to improve maintenance efficiency and disaster responsiveness. A river-levee safety map, indicating sliding, piping, visual inspection, scouring, and safety index of a levee fill material on a GIS map will enable the dangerous zone to be identified visually and the development of proactive measures to deal with it. This will maximize the river-levee maintenance efficiency, which is a break from traditional practice in that restoration measures are taken only after the damage has occurred. This study includes scouring and levee fill material in addition to previously-proposed sliding, piping and visual inspections. The research activities conducted in the study include 1) categorization of scouring and levee fill material based on document and data examination, 2) evaluation of sliding and piping at 5 locations on the left levee in the Nam river according to the duration time of the flood water level, and 3) evaluation of the characteristics of scouring and levee fill material at 9 locations on the left/right levee in the Nam River. The river levee safety map proposed in this study would be more useful and practical but further study on the manual for river management organization, repair and reinforcement methods, and budget is required.

• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1603-1613
• /
• 2017

This paper proposes a method for effectively segmenting the hand region using a widely popular RGB color-based webcam. This performs the empirical preprocessing method four times to remove the noise. First, we use Gaussian smoothing to remove the overall image noise. Next, the RGB image is converted into the HSV and the YCbCr color model, and global fixed binarization is performed based on the statistical value for each color model, and the noise is removed by the bitwise-OR operation. Then, RDP and flood fill algorithms are used to perform contour approximation and inner area fill operations to remove noise. Finally, ROI (hand region) is selected by eliminating noise through morphological operation and determining a threshold value proportional to the image size. This study focuses on the noise reduction and can be used as a base technology of gesture recognition application.

• Journal of information and communication convergence engineering
• /
• v.12 no.1
• /
• pp.60-65
• /
• 2014

This paper describes an efficient framework for the extraction of a brain tumor from magnetic resonance (MR) images. Before the segmentation process, a median filter is used to filter the image. Then, the morphological gradient is computed and added to the filtered image for intensity enhancement. After the enhancement process, the thresholding value is calculated using the mean and the standard deviation of the image. This thresholding value is used to binarize the image followed by the morphological operations. Moreover, the combination of these morphological operations allows to compute the local thresholding image supported by a flood-fill algorithm and a pixel replacement process to extract the tumor from the brain. Thus, this framework provides a new source of evidence in the field of segmentation that the specialist can aggregate with the segmentation results in order to soften his/her own decision.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.188-191
• /
• 2011

Path finding and path planning is crucial in today's world where time is an extremely valuable element. It is easy to plan the optimum path to a destination if provided a map but the same cannot be said for an unknown and unexplored environment. It will surely be exhaustive to search and explore for paths to reach the destination, not to mention planning for the optimum path. This is very much similar to finding for an exit of a maze. A very popular competition designed to tackle the maze solving ability of autonomous called Micromouse will be used as a guideline for us to design our maze. There are numerous ways one can think of to solve a maze such as Dijkstra's algorithm, flood fill algorithm, modified flood fill algorithm, partition-central algorithm [1], and potential maze solving algorithm [2]. We will analyze these algorithms from various aspects such as maze solving ability, computational complexity, and also feasibility to be implemented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.514-516
• /
• 2016

사람은 개인마다 선호색이 다르다. 때문에 색채를 통해서 개인의 성향을 분석하기도 한다. 일반적으로 난색은 밝고 따뜻한 색으로 활기와 적극성을 띄며 한색은 차갑고 냉정함, 차분함 등과 같은 의미를 지닌다. 이러한 색채가 가지는 의미는 개인의 환경, 성향, 성별, 연령 등에 따라 다르게 나타난다. 색채 선호는 일반적으로 개인이 색채에 대해 좋아하는 정도를 의미하는 것으로 개인의 성향이나 상황, 경험 등에 의해 형성된 지극히 개인적인 색을 말한다. 본 논문에서는 색채 선호를 분석하는 심리 검사 CRR와 Flood Fill 알고리즘을 적용하여 그림에 색채를 채워서 주조색과, 보조색을 각각 Decision Tree에 적용한다. Decision Tree의 결과를 기반으로 데이터베이스와 연동하여 개인의 심리 상태를 분석할 수 있는 방법을 제안한다.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.12 no.4
• /
• pp.2090-2123
• /
• 1970

This paper is a report on the research of experimental model test of Andong Fill Dam, which has been planned by the Government of Korea as a project, of its over-flowing capacity in spillway, creation of minus pressure and structure of anti-water impulse in over-flow weir. Andong Fill Dam is one of the project of master development plant for water resources, locating at Nakdong River side of Korea, and is aimed to have a multi-purpose dam for flood-control, irrigation, water power, urban and industrial water supply. This dam is planned to erect in fill-dam type due to the improper soil foundation and condition for concrete dam. The refore for the proper and advantageous points, this is designed as center core fill dam. By a model minimized of Andong Fill Dam, held an experimental model test on water quentity of reservir, discharges of overflow part, low pressure and anti-water impulse of overflow part, which was conducted an experiment by flowing aspects through each section of spillway to find the changes of water pressure and that of water level, and corrected the section of each part in order to conduct a check on the creation of minus pressure not to be over acted to the allowable bundary of the section structure; and for the prevention of concentated scouring at the down stream side of flow.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.2
• /
• pp.19-25
• /
• 2013

In this paper, we propose an approach to tracking road regions from video sequences. The proposed method segments and tracks road regions by utilizing the prior information from the result of the previous frame. For the efficiency of the system, we have a simple assumption that the road region is usually shown in the lower part of input images so that lower 60% of input images is set to the region of interest(ROI). After initial segmentation using flood-fill algorithm, we merge neighboring regions based on color similarity measure. The previous segmentation result, in which seed points for the successive frame are extracted, is used as prior information to segment the current frame. The similarity between the road region of the previous frame and that of the current frame is measured by the modified Jaccard coefficient. According to the similarity we refine and track the detected road regions. The experimental results reveal that the proposed method is effective to segment and track road regions in noisy and non-noisy environments.