• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1326-1335
• /
• 2021

As part of the cell division method, we proposed a method for segmenting images generated by topography microscopes through deep learning-based feature generation and graph segmentation. Hybrid vector shapes preserve the overall shape and boundary information of cells, so most cell shapes can be captured without any post-processing burden. NIH-3T3 and Hela-S3 cells have satisfactory results in cell description preservation. Compared to other deep learning methods, the proposed cell image segmentation method does not require postprocessing. It is also effective in preserving the overall morphology of cells and has shown better results in terms of cell boundary preservation.

• The Korean Journal of Mycology
• /
• v.29 no.2
• /
• pp.91-98
• /
• 2001

The mycelial morphology during submerged cultivation of Ganoderma ludium using by air-lift fermenter system were analyzed by image processing system and the characterization of mycelial morphology were investigated. In submerged culture using medium with different ammonium phosphate concentrations, the various morphological forms of G. lucidum mycelium were observed. The filamentous forms such as non-branched long filamentous mycelium, non-branched short mycelium, branched long filamentous mycelium, branched short mycelium, entangled mycelium and clump were observed, and also, and also, the pelleted forms such as smooth pellet, rough pellet and hollow rough pellet were observed. The mycelial morphology was changed from the filamentous to the pelleted forms by addition of ammonium phosphate. The fractal dimensions of pelleted and filamentous forms were 1.05 and 1.3, respectively, while the fractal dimension of mixtures of pelleted and filamentous forms was 1.16. Therefore, the fractal dimension was found to be more effective index for the detection of the mycelial morphology and morphological change during batch cultivation. The circularity was also found to be useful for evaluating the surface growth of pelleted mycelium.

• Journal of Korea Multimedia Society
• /
• v.18 no.9
• /
• pp.997-1007
• /
• 2015

In this paper, we propose a method for automatically analyzing the bone formation in a mouse model of frontal bone defect. We perforate two holes of 0.8mm diameter in the frontal bone and observe the bone formation process using a micro CT. Because the conventional analysis software of the micro CT does not support automatic analysis of the bone formation status, we have to use a manual analysis method. However the manual analysis is very cumbersome and requires a lot of time, we propose an automatic analysis method. It rotates the image around three axes directions so that the mouse's skull come into regular position. It calculates the cumulative image of the voxel values for the perforated bone surface. It estimates the hole location by finding the darkest point in the cumulative image. The proposed method was applied to 24 CT images of saline administration group and PTH administration group and hole location was estimated. BV/TV index was calculated for the estimated hole to evaluate the bone formation status. Experimental results showed that bone formation process is more active in PTH administration group. The method proposed in this paper could replace successfully the cumbersome and time consuming manual job.

• Journal of Biomedical Engineering Research
• /
• v.20 no.2
• /
• pp.149-154
• /
• 1999

In anatomical aspects, magnetic resonance image offers more accurate information than other medical images such as X ray, ultrasonic and CT images. This paper introduces a method that segments and detects lesion for 2 dimensional axial MR brain images automatically. Image segmentation process consists of 2 stages. First stage extracts cerebrum region using thresholding and morphology. In the second stage, white matter, gray matter and cerebrospinal fluid in the cerebrum are extracted using FCM, We could improve processing time as removing uninterested region. Finally symmetry measure and anatomical Knowledge are used to detect lesion.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2004.11a
• /
• pp.312-315
• /
• 2004

A lubricated state of an automobile transmission can not be inspected directly with eyes. Thus, it needs to develop a more general method. Wear debris can be collected from the lubricants of operating transmission of an automobile and its morphology is directly related to the fiction condition of the interacting materials from which the wear particles originated in lubricated transmission. In this paper, to identify the friction condition for transmission gear by neural network, the wear test of ball-on-disk type and the analysis of friction state were carried out for carburized SCM420 and nitrocarburized NT100 under different experimental conditions. The four shape parameters($50\%$ volumetric diameter, aspect, roundness and reflectivity) of wear debris were calculated by the image processing system. They were used as input values to identify the moving condition of transmission gear by the neural network.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.261-267
• /
• 2007

The research about Intelligence Transport Systems(ITS) is actively studied for the traffic problem solution recently. Also, the various methods to detect vehicles moving in the roads are studied. This research using image processing technology is to give the drivers the road information quickly by developing Vehicle Detection System that detects through traffics. Purpose or this research is developing efficient algorithm to facilitate hardware composition. We use morphology method to extract corner points in the images captured by CCD camera. Also, the proposed algorithm detects vehicle's moving area by using motion vectors between corner points. The experiments of the proposed algorithm whose processing time was shortened show good results in vehicle detection on the live road images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.353-361
• /
• 2012

In this paper, we propose a improvement method of vision inspector for T type welding nut using an auto sorting system. We used edge and thread detection with histogram of image which is captured by machine vision camera. We also used a binary morphology operation for a detection of spot. A major problem in this vision inspector is abnormal operation caused by degradation of image acquired. These degradations caused by oil pollution on conveyer belt. For overcome this problem, we introduce a pre-processing using a masked histogram equalization on the image acquired. Histogram equalization is applied on masked region (nut part) for increase contrast. As a result, we can remove features caused by oil pollution on background and reduce a ratio of abnormal operation from 10.0 % to 0.2 %.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.660-663
• /
• 2004

Recently in the automotive industries, light and high quality material is strongly required because of emissions regulation issues. In the electromagnetic stirring process, it has many merits that are the exact control ability about material processing and a good point of the protection of environment. In this paper, the morphology of the change of primary Al phase in A356 alloy by electro magnetic stirrer was investigated to obtain the globular structure. The parameters are the current, stirring time, pouring temperature and cooling rate of different wall thickness; 5mm, 15mm, 25mm respectively. By proper selection of the processing parameters, globular primary particles can be obtained by electromagnetic stirrer.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.615-618
• /
• 2019

Visual saliency detection is an important part in various vision-based applications. There are a myriad of techniques for saliency detection in color images. However, the number of methods for saliency detection in infrared images is inadequate. In this paper, we introduce a simple approach for pedestrian identification in infrared images using saliency. The input image is thresholded into several Boolean maps, an initial saliency map is then calculated as a weighted sum of created Boolean maps. The initial map is further refined by using thresholding, morphology operation, and Gaussian filter to produce the final, high-quality saliency map. The experiment showed that the proposed method produced high performance results when applied to real-life data.

• Annual Conference of KIPS
• /
• 2004.05a
• /
• pp.699-702
• /
• 2004

단층촬영에 의해 획득된 흉부영상의 폐 영역은 기관지, 폐동맥, 폐정맥으로 구성된 복잡한 형태를 가지고 있다. 또한 이들 조직과 폐 영역 내에 존재하는 악성 종양과 같은 질병들 사이의 공간정보의 유사성으로 인해 방사선 전문의조차도 질병을 간단히 구분 해내는데 많은 어려움이 따른다. 따라서 본 논문에서는 이러한 유사한 공간정보를 갖는 폐 영역을 수리형태학 필터인 모폴로지(morphology)와 국부적인 워터쉐드(watershed) 알고리즘을 이용하여 분할하고, 분할된 폐 영역으로부터 색전 또는 종양 등의 결절(nodule)의 정보를 가지고 있는 혈관들을 추출하는 효과적인 알고리즘을 제안한다.