• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.42-45
• /
• 2002

A novel characteristic value extraction method based on morphological spatial frequency is proposed. Morphological spatial frequency defined by morphological pattern distribution function is introduced. Superiority of the method was proved for various images by experiment. Furthermore the fact that the proposed method does not need threshold to obtain binary image provides its applicability to content-based image retrieval.

• Journal of Korea Multimedia Society
• /
• v.17 no.10
• /
• pp.1171-1181
• /
• 2014

In this paper, we propose improved methods which are image conversion and extraction method of watershed seed using morphological characteristic of teeth on complement image. Conventional tooth segmentation methods are occurred low detection ratio at molar region and over, overlap segmentation owing to specular reflection and morphological feature of molars. Therefore, in order to solve the problems of the conventional methods, we propose the image conversion method and improved extraction method of watershed seed. First, the image conversion method is performed using RGB, HSI space of tooth image for to extract boundary and seed of watershed efficiently. Second, watershed seed is reconstructed using morphological characteristic of teeth. Last, individual tooth segmentation is performed using proposed seed of watershed by watershed algorithm. Therefore, as a result of comparison with marker controlled watershed algorithm and the proposed method, we confirmed higher detection ratio and accuracy than marker controlled watershed algorithm.

• Korean Journal of Oriental Medicine
• /
• v.9 no.1
• /
• pp.113-122
• /
• 2003

In the present paper, morphological characteristic and PCR analysis were carried not to identify the medicinal origins of Peucedanum decursivum and Anthriscus sylvestris. Some samples in Korean. markets were Peucedanum decursivum misused with rhizomes of Anthriscus sylvestris. The main. origin of Peucedanum decursivum producted was quite different from those of Anthriscus sylvestris in the morphological characteristics. And PCR analysis, the three primer has developed into anew tool for identification of Peucedanum decursivum and Anthriscus sylvestris.

• Journal of Advanced Marine Engineering and Technology
• /
• v.23 no.1
• /
• pp.79-87
• /
• 1999

The most part of the faculty drop a trouble and damage of machine equipment even if whatever cause they break out take place at local and trifling place and the factor dominating their trouble is due to wear debris occurred in the lubricated machine moving surface. This study has been car-ried out to identify morphology of wear debris on the lubricated machine moving system by means of computer image analysis. Namely the wear debris contained in lubricating oil extracted from movable machine equipment will be filtered through membrane filter(void diameter 0.45${\mu}m$) and will be analyzed with its data information such as 50% volume diameter aspect roundness and reflectivity. Morphological characteristic of wear debris is easily distinguished by four shape parameters it is necessary to divide small class of every 100 wear debris in total wear particles in order to distinguish morphological characteristic of wear debris more easily by computer image analysis. We are sure that operation condition diagnosis of the lubricated machine moving surfaces is possible by computer image analysis.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2002.10b
• /
• pp.457-458
• /
• 2002

The fractal dimension is the characteristics that can quantitatively define the irregularity in natural. It is useful in describing the morphology or various rubbed surface for hydraulic piston motor instead of the stylus profiling method. But fractal parameters had not constructed on the morphological characteristic or rubbed surface because of the insufficient knowledge about a conception of fractal dimension. In this study, for the purpose or applying fractal I parameters practically, we have suggested way to establish the morphological characteristic of rubbed surface with fractal parameters, and we carried out an experiment on the lubricant friction and wear by using Ball-ON-Disk type tester. Materials were the brass and the bronze which are used to slipper-pad in the hydraulic piston motor. We searched for fractal parameters or surface structure with the digital image processing, Surface fractal dimension can be determined by sum of intensity difference of surface pixel. Using the image processing and fractal parameters for rubbed surface in the friction and wear test, morphology of rubbed sur race can be effectively obtained by fractal dimensions.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2019.04a
• /
• pp.64-64
• /
• 2019

In order to evaluate the taxonomical relevance of seeds morphological characteristics, a macroand micro-morphological study was conducted on seeds of Korean Vicia (Fabacea). We collected 19 taxa of genus Vicia distributed in Korea and introduced one taxa from USDA. The morphological characteristic and testa texture of seeds were investigated using a Stereo-microscope (SM) and Scanning Electron Microscope (SEM). Most of Vicia seeds were found spherical or oblong and some seeds were oval and subglose. The largest seed was V. chosenensis ($4.3{\times}3.6{\times}2.6mm$), and the smallest was V. teterasperma ($1.7{\times}1.7{\times}1.5mm$). V. chosenensis and V. hirsuta were separated from other Vicia species by having a shiny in seed finish. In hilum shape, 14 species have linear and V. sepium was distinguished by having a circumlinear. In testa texture, they developed papilae, only V. hirsuta has lophate in level type. Deposition of the sheet-like debris between the papilae was observed in V. chosenensis, V. cracca, and V. unijuga. Polymorphism information content (PIC) values of the 13 qualitative morphological characters (QMC) were in the range of 0.0950 to 8863 with an average of 0.4611. PIC value of seed shape, seed colour, hilum colour were 0.7403, 0.8177, 0.883 respectively. Cluster analysis based on QMC detected three main clades. V. cracca, V. amurensis, V. amoena were involved in Group 1 and V. unijuga f. minor, V. unijuga, V. unijuga f. angustifolia, V. sepium, V. hirticalycina, V. hirsuta, V. linearfolia, V. chosenensis, V. pseudorobus, V. venosa var. cuspidata were involved in Group 2. V. nipponica, V. japonica, V. villosa, V. dasicarpa, V. bungei, V. angustifolia, V. tetrasperma were clustered in Group 3. Our research suggests that morphological characteristic and testa texture of seeds could be used as definers for the identification of genus Vicia.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2002.05a
• /
• pp.193-199
• /
• 2002

Analyzing working conditions with shape characteristics of wear debris in a lubricated machine, it can be effect on diagnosis of hydraulic machining system. And it can be recognized that results are processed threshold images of wear debris. But, in order to predict and estimate a working condition of lubricated machine, it is need to analysis a shape characteristic of wear debris and to identify. Therefor, If shape characteristics of wear debris are identified by computer image analysis and the neural network, it is possible to find the cause and effect of wear condition. In this stud)r, wear debris in the lubricant oil are extracted by membrane filter $(0.45{\mu}m)$, and the quantitative value of shape characteristic of wear debris are calculated by the digital image processing. This morphological information are studied and identified by tile artificial neural network. The purpose of this study is to apply morphological characteristic of wear debris to prediction and estimation of working condition in hydraulic machining systems.

• Journal of IKEEE
• /
• v.7 no.2 s.13
• /
• pp.210-217
• /
• 2003

A novel characteristic value extraction method based on mathematical morphology is proposed. Morphological spatial frequency defined by morphological pattern distribution function is introduced and applied to define a new feature called ‘average height.' The average height is used to define a characteristic value which is to be used to generate an index key value for content-based image retrieval. Superiority of the method was proved for various images by experiment. Furthermore the fact that the proposed method does not need threshold to obtain binary image provides its applicability to content-based image retrieval.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.101-107
• /
• 2020

For Korean language processing, morphological analysis is a critical component that requires extensive work. This morphological analysis can be conducted in an end-to-end manner without requiring a complicated feature design using a sequence-to-sequence model. However, the sequence-to-sequence model has a time complexity of O(n²) for an input length n when using the attention mechanism technique for high performance. In this study, we propose a linear-time Korean morphological analysis model using a local monotonic attention mechanism relying on monotonic alignment, which is a characteristic of Korean morphological analysis. The proposed model indicates an extreme improvement in a single threaded environment and a high morphometric F1-measure even for a hard attention model with the elimination of the attention mechanism formula.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.10
• /
• pp.1466-1473
• /
• 2013

This experiment was conducted to study the variation laws and correlations of shearing force and feed characteristics including morphological characteristic, chemical composition and in situ degradability of wheat straw. Feasibility of evaluating the nutritional value of wheat straws with shearing force values was analyzed in this study. Six hundred wheat straw plants (Jimai 22) were randomly selected and placed in a cool and ventilated place. Samples were collected in the 1st, 15th, 30th, 45th, 60th d after harvest to measure shearing force, morphological characteristic, nutritional composition. Rumen degradation of dry matter (DM), neutral detergent fiber (NDF) and acid detergent fiber (ADF) of wheat straws were determined by the nylon bags method. The results demonstrated that linear and quadratic effects of storage time on all the tested morphological characteristics were significantly correlative (p<0.01). As storage time goes on, all the tested nutrients and their rumen degradations of wheat straw was linearly (p<0.01) and quadratic (p<0.01) correlative except ADF content and rumen degradation of ADF. Significant correlations were determined in linear effect of shearing force on morphological characteristics (p<0.01), and linear density and diameter were a more sensitive predictor than stem thickness for shearing force. There were strong correlations between storage time and all the measured physical characteristics (shearing force, morphological characteristics and shearing force standardized by morphological characteristics) (p<0.01). Nutrition compositions were linearly correlative with shearing force and standardized shearing force (p<0.01). The linear correlation between rumen degradation of DM and NDF and shearing force and standardized shearing force were evident (p<0.01). In conclusion, shearing force, nutrition compositions and their rumen degradation of wheat straw were still dynamic with storage time after harvest. Correlation could be found between shearing force and nutritional characteristics of wheat straw. Nutrient content, morphological index and rumen degradation of DM and NDF could be predicted by changes in shearing force. Shearing force should be applied according to a standardized storage time when it is used to forecast the feed value of wheat straws.