• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.3
• /
• pp.8-13
• /
• 2010

Shape form focus (SFF) is a technique that reconstructs 3D shape of an object using image focus. Although many SFF methods have been proposed, there are still notable inaccuracy effects due to noise and non-optimization of image characteristics. In this paper, we propose a noise filter technique for noise reduction and genetic algorithm (GA) for focus measure optimization. The proposed method is analyzed with a statistical criteria such as Root Mean Square Error (RMSE) and correlation.

• The KIPS Transactions:PartC
• /
• v.8C no.4
• /
• pp.389-396
• /
• 2001

기존의 라우터 기반의 패킷 스크리닝 방식은 ATM 네트워크 상에서는 패킷 수준의 스크리닝 기능의 적용을 위하여 SAR(Segmentation And Reassembly) 과정을 필요로 하기 때문에 고속의 셀 처리를 수행하는 ATM Switch의 셀 처리 속도를 저하시킨다는 문제점을 안고 있다. 본 논문에서는 셀 스크리닝 방식에 기반한 병렬 처리 구조의 ATM Firewall Switch를 제안한다. 제안된 Enhanced ATM Firewall Switch는 셀 단위로 분할된 패킷의 1, 2번 셀들에 대한 검사만을 통하여 스크리닝 기능을 수행하기 때문에 셀 단위의 스크리닝 수행이 가능하며, 정책 캐쉬의 도입을 통해 셀 스크리닝 수행속도를 향상하였다. 또한 독립적인 User Cells Filter 기능 블록의 설계를 통하여 병렬 처리 구조의 셀 스크리닝 수행이 가능하도록 구성하여 셀 지연 시간을 최소화하였다.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1392-1405
• /
• 2019

The cathode voltage of aluminum electrolytic cell is relatively stable under normal conditions and fluctuates greatly when it has an anomaly. In order to detect the abnormal range of cathode voltage, an anomaly detection algorithm based on sliding window was proposed. The algorithm combines the time series segmentation linear representation method and the k-nearest neighbor local anomaly detection algorithm, which is more efficient than the direct detection of the original sequence. The algorithm first segments the cathode voltage time series, then calculates the length, the slope, and the mean of each line segment pattern, and maps them into a set of spatial objects. And then the local anomaly detection algorithm is used to detect abnormal patterns according to the local anomaly factor and the pattern length. The experimental results showed that the algorithm can effectively detect the abnormal range of cathode voltage.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.743-746
• /
• 2002

바이오 인포매틱스(bioinformatics) 분야 중 한 분야인 셀 기반 분석(cell-based assay) 시스템 구축의 필요성이 최근 대두되고 있다. 특정 시약 또는 시험 물질을 셀 세포에 투여했을 때 시간 축 변화에 따라 변화하는 세포의 변화를 감지하기 위해서 세포 영상의 영역 분할이 선행되어야 한다. 본 논문에서는 전체 영상에 대하여 셀 공통 영역을 추출하고, 추출된 공통영역을 스네이크(snake) 기법을 이용하여 세포 영역을 분할하는 방법을 제안하고자 한다.

• Mycobiology
• /
• v.32 no.4
• /
• pp.164-169
• /
• 2004

Development of oidia, a type of thallic spores from monokaryotic mycelium of Coprinus cinereus was examined with electron microscope and light microscopes. Oidia formation in this fungus is unique in its mode of formation compared with other types of asexual sporogenesis. Oidiogenesis in C. cinereus is carried out in three steps: 1) Formation of oidiophore from the parent mycelium, 2) Formation of initials of oidial cells from swollen oidiophore, 3) Segmentation and detachment of mature oidial cell. Oidiophores appear to spring out singly as a swollen hyphal branches from the normal foot hyphae or sometimes coiled hypha. From the oidiophore, oidial branches sprout out forming a group of $2{\sim}6$, most often 4 oidial cells and each oidial cell undergoes a single mitosis resulting in 2 oidia. One of the sibling oidial cells in a group is frequently transformed into a new oidiophore, thus oidiogenic structures are tandemly produced at the several different levels.

• Journal of Biomedical Engineering Research
• /
• v.15 no.4
• /
• pp.419-427
• /
• 1994

A new method of digital image analysis technique for discrimination of cancer cell was presented in this paper. The object image was the Thyroid Gland cells image that was diagnosed as normal and abnormal (two types of abnormal : follicular neoplastic cell, and papillary neoplastic cell), respectively. By using the proposed region segmentation algorithm, the cells were segmented into nucleus. The 16 feature parameters were used to calculate the features of each nucleus. As a consequence of using dominant feature parameters method proposed in this paper, discrimination rate of 91.11 % was obtained for Thyroid Gland cells.

• Biomedical Science Letters
• /
• v.17 no.1
• /
• pp.69-77
• /
• 2011

In this study, we evaluated the protective effects of supercritical extracts and two step ethanol extracts after supercritical extraction from Schizandra chinensis on antioxidant activities and oxidative DNA and cell damages. Supercritical extracts removed DPPH (1,1-diphenyl-2-picryldrazyl) radical by 85.5% at 200 ${\mu}g$/ml, but showed low activities of scavenging and chelating the hydroxyl radical and ferrous iron. However, two step ethanol extracts showed low activities of scavenging the DPPH radical, but removed the hydroxyl radical by 86% at 200 ${\mu}g$/ml. In addition, we tested the activities of extracts for reducing hydroxyl radical-induced DNA and cell damage. Two step ethanol extracts showed protective effect against the oxidative DNA damage by reducing DNA segmentation, inhibiting DNA migration and decreasing the expression of phospho-H2AX. Also, two step ethanol extracts showed protective effect against the oxidative cell damage by inhibiting lipid peroxidation and increasing the expression of p21 protein. Taken together, we suggest that two step ethanol extracts from S. chinensis have a role as useful inhibitors against oxidative damages.

• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1150-1161
• /
• 2018

Classification is widely used in medical images to categorize patients and non-patients. However, conventional classification requires a complex procedure, including some rigid steps such as pre-processing, segmentation, feature extraction, detection, and classification. In this paper, we propose a novel convolutional neural network (CNN), called LeukemiaNet, to specifically classify two different types of leukemia, including acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML), and non-cancerous patients. To extend the limited dataset, a PCA color augmentation process is utilized before images are input into the LeukemiaNet. This augmentation method enhances the accuracy of our proposed CNN architecture from 96.9% to 97.2% for distinguishing ALL, AML, and normal cell images.

• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.39-46
• /
• 2015

This paper presents an automatic method to detect and count the cells from microorganism images based on mobile environments. Cell counting is an important process in the field of biological and pathological image analysis. In the past, cell counting is done manually, which is known as tedious and time consuming process. Moreover, the manual cell counting can lead inconsistent and imprecise results. Therefore, it is necessary to make an automatic method to detect and count cells from biological images to obtain accurate and consistent results. The proposed multi-step cell counting method automatically segments the cells from the image of cultivated microorganism and labels the cells by utilizing topological analysis of the segmented cells. To improve the accuracy of the cell counting, we adopt watershed algorithm in separating agglomerated cells from each other and morphological operation in enhancing the individual cell object from the image. The system is developed by considering the availability in mobile environments. Therefore, the cell images can be obtained by a mobile phone and the processed statistical data of microorganism can be delivered by mobile devices in ubiquitous smart space. From the experiments, by comparing the results between manual and the proposed automatic cell counting we can prove the efficiency of the developed system.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.369-378
• /
• 2005

Document image is segmented and classified into text, picture, or table by a document layout analysis, and the words in table regions are significant for keyword spotting because they are more meaningful than the words in other regions. This paper proposes a method to extract words from table regions in document images. As word extraction from table regions is practically regarded extracting words from cell regions composing the table, it is necessary to extract the cell correctly. In the cell extraction module, table frame is extracted first by analyzing connected components, and then the intersection points are extracted from the table frame. We modify the false intersections using the correlation between the neighboring intersections, and extract the cells using the information of intersections. Text regions in the individual cells are located by using the connected components information that was obtained during the cell extraction module, and they are segmented into text lines by using projection profiles. Finally we divide the segmented lines into words using gap clustering and special symbol detection. The experiment performed on In table images that are extracted from Korean documents, and shows $99.16\%$ accuracy of word extraction.