• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.275-278
• /
• 2007

In this paper, we proposed a automatic extraction method as a preprocessing stage for extraction of basic insect footprint segments. In general, sizes and strides of footprints may be different according to type and size of an insect for recognition. Therefore we proposed an improved algorithm for extraction of basic insect footprint segments regardless of size and stride of footprint pattern. In the proposed algorithm, threshold value for clustering is determined automatically using contour shape of the graph created by accumulating distances between all the spots of footprint pattern. In the experimental results applying the proposed method, The basic footprint segments should be extracted from a whole insect footprint image using significant information in order to find out appropriate features for classification.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.1-10
• /
• 2018

This paper presents an autonomous detection and aiming point computation of a battle tank by using RGB images. Maximally stable extremal regions algorithm was implemented to find features of the tank, which are matched with images extracted from streaming video to figure out the region of interest where the tank is present. The median filter was applied to remove noises in the region of interest and decrease camouflage effects of the tank. For the tank segmentation, k-mean clustering was used to autonomously distinguish the tank from its background. Also, both erosion and dilation algorithms of morphology techniques were applied to extract the tank shape without noises and generate the binary image with 1 for the tank and 0 for the background. After that, Sobel's edge detection was used to measure the outline of the tank by which the aiming point at the center of the tank was calculated. For performance measurement, accuracy, precision, recall, and F-measure were analyzed by confusion matrix, resulting in 91.6%, 90.4%, 85.8%, and 88.1%, respectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.724-732
• /
• 2001

In this paper, a new method of feature extraction of major objects to represent an image using Vector Quantization(VQ) is proposed. The principal features of the image, which are used in a content-based image retrieval system, are color, texture, shape and spatial positions of objects. The representative color and texture features are extracted from the given image using VQ(Vector Quantization) clustering algorithm with a general feature extraction method of color and texture. Since these are used for content-based image retrieval and searched by objects, it is possible to search and retrieve some desirable images regardless of the position, rotation and size of objects. The experimental results show that the representative feature extraction time is much reduced by using VQ, and the highest retrieval rate is given as the weighted values of color and texture are set to 0.5 and 0.5, respectively, and the proposed method provides up to 90% precision and recall rate for 'person'query images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2313-2326
• /
• 2018

The method of operating a game could determine the psychological distance between the player and the game character, and thus, in the Virtual Reality, players' control methodologies are important to enhance their immersion. This study has the objective of examining the difference in games according to the method of operation based on the player's movements. This study researched the effect of the method of operating movement conforming to the movement of the character and the physical operation of the body on forming game experiences for the player. The result of performing an experiment increased reality for the game player through a controller in the shape of the actual control, to increase focus in the game. As so, game play through movements, including actual movements by the player displayed to enhance game satisfaction. In the part of media remediation field, Game can be defined as media which has their own unique hypermediacy. Especially, in the motion based game, players' movement mediates players and the game, therefore, players' movement could make players' experience augmented or immediate in accordance with the characteristics of movements. Even though sports and dances genres of motion-based games are common, RPG or adventure genres are rare. It can be explained that the characteristics of the action have been explained in the immediacy. In a game of fantasy, which is difficult to experience in real-life situations, the nature of the player's motion can increase the immersion of the game, which can contribute to utilization of players' motion and experience design in the various genres and suggestion of grounds theory. In addition, through this study, it is able to design motion-based games of various genres.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.329-331
• /
• 2021

Recently, as various cases of using deep learning in the health-care field are increasing, functions such as electrocardiogram examination and body composition analysis through wearable device can be provided to provide rational decision-making and a process tailored to the individual. In order to utilize deep learning, it it most important to secure refined data, and this data is being made through human intervention or unsupervised learning. In this paper, we propose a model that conducts unsupervised learning by clusters according to gender and age using human body data such as chest and waist circumferences, which are easy to measure, and classifies them with CNN. For data, the 7th human body data provided by Korean Agency for Technology and Standards was used. Through this, it it thought that it can be applied to various application cases such as personalized body shape management service and obesity analysis.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.81-90
• /
• 2007

This paper shows an intelligent disease diagnosis system for public. Our system deals with 30 diseases and their typical symptoms selected based on the report from Ministry of Health and Welfare, Korea. Technically, the system uses a modified FCM algorithm for clustering diseases and the input vector consists of the result of user-selected questionnaires. The modified FCM algorithm improves the quality of clusters by applying symmetrically measure based on the fuzzy theory so that the clusters are relatively sensitive to the shape of the pattern distribution. Furthermore, we extract the highest 5 diseases only related to the user-selected questionnaires based on the fuzzy membership function between questionnaires and diseases in order to avoid diagnosing unrelated disease.

• 한국균학회소식:학술대회논문집
• /
• 2014.10a
• /
• pp.34-34
• /
• 2014

Filamentous fungi of the genus Colletotrichum (teleomorph, Glomerella) are considered major plant pathogens worldwide. Cereals, legumes, vegetables, and fruit trees may be seriously affected by this pathogen (1). Colletotrichum species cause typical disease symptoms known as anthracnoses, characterized by sunken necrotic tissue, where orange conidial masses are produced. Anthracnose appears in both developing and mature plant tissues (2). We investigated disease occurrence in apple orchards from 2013 to 2014 in northern Gyeongbuk province, Korea. Typical anthracnose with advanced symptoms was observed in all apple orchards studied. Of late, static fruit spot symptoms are being observed in apple orchards. A small lesion, which does not expand further and remains static until the harvesting season, is observed at the beginning of fruit growth period. In our study, static symptoms, together with the typical symptoms, were observed on apples. The isolated fungus was tested for pathogenicity on cv. 'Fuji apple' (fully ripe fruits, unripe fruits, and cross-section of fruits) by inoculating the fruits with a conidial suspension ($10^5$ conidia/ml). In apple inoculated with typical anthracnose fungus, the anthracnose symptoms progressed, and dark lesions with salmon-colored masses of conidia were observed on fruit, which were also soft and sunken. However, in apple inoculated with fungi causing static symptoms, the size of the spots did not increase. Interestingly, the shape and size of the conidia and the shape of the appressoria of both types of fungi were found to be similar. The conidia of the two types of fungi were straight and cylindrical, with an obtuse apex. The culture and morphological characteristics of the conidia were similar to those of C. gloeosporioides (5). The conidia of C. gloeosporioides germinate and form appressoria in response to chemical signals such as host surface wax and the fruitripening hormone ethylene (3). In this study, the spores started to germinate 4 h after incubation with an ethephon suspension. Then, the germ tubes began to swell, and subsequently, differentiation into appressoria with dark thick walls was completed by 8 h. In advanced symptoms, fungal spores of virtually all the appressoria formed primary hyphae within 16 h. However, in the static-symptom fungus spores, no primary hyphae formed by 16 h. The two types of isolates exhibited different growth rates on medium containing apple pectin, Na polypectate, or glucose as the sole carbon. Static-symptom fungi had a >10% reduction in growth (apple pectin, 14.9%; Na polypectate, 27.7%; glucose, 10.4%). The fungal isolates were also genetically characterized by sequencing. ITS regions of rDNA, chitin synthase 1 (CHS1), actin (ACT), and ${\beta}$-tubulin (${\beta}t$) were amplified from isolates using primer pairs ITS 1 and ITS 4 (4), CHS-79F and CHS-354R, ACT-512F and ACT-783R, and T1 and ${\beta}t2$ (5), respectively. The resulting sequences showed 100% identity with sequences of C. gloeosporioides at KC493156, and the sequence of the ${\beta}$t gene showed 100% identity with C. gloeosporioides at JX009557.1. Therefore, sequence data from the four loci studied proves that the isolated pathogen is C. gloeosporioides. We also performed random amplified polymorphic DNA-PCR, which showed clearly differentiated subgroups of C. gloeosporioides genotypes. The clustering of these groups was highly related to the symptom types of the individual strains.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.121-130
• /
• 2011

This paper highlights the reconstruction of the rectilinear type of 3D rooftop model from satellite image data using centroid neural network. The main idea of the proposed 3D reconstruction method is based on the grouping of 3D line segments. 3D lines are extracted by 2D lines and DEM (Digital Elevation Map) data evaluated from a pair of stereo images. Our grouping process consists of two steps. We carry out the first grouping process to group fragmented or duplicated 3D lines into the principal 3D lines, which can be used to construct the rooftop model, and construct the groups of lines that are parallel each other in the second step. From the grouping result, 3D rooftop models are reconstructed by the final clustering process. High-resolution IKONOS images are utilized for the experiments. The experimental result's indicate that the reconstructed building models almost reflect the actual position and shape of buildings in a precise manner, and that the proposed approach can be efficiently applied to building reconstruction problem from high-resolution satellite images of an urban area.

• Development and Reproduction
• /
• v.10 no.4
• /
• pp.227-238
• /
• 2006

Genomic DNAs(gDNAs) were isolated from the venus clam(Gomphina aequilatera) from Samcheok(venus clam from Samcheok; VCS) and Wonsan(venus clam from Wonsan; VCW) located in the East Sea of the Korean Peninsula. The amplified products were generated by agarose gel electrophoresis(AGE) with oligonucleotides primer, detected by staining with ethidium bromide and viewed by ultraviolet ray. The seven arbitrarily selected primers BION-21, BION-23, BION-25, BION-27, BION-29, BION-31 and BION-33 generated the shared loci, polymorphic, and specific loci, with the molecular sizes ranging from 150 bp to 2,400 bp. In this study, 147 polymorphic loci(147/954 loci, 15.41%) in VCS population and 274(274/996 loci, 27.51%) in VCW population were generated with seven primers. These results suggest the genetic variation in VCW population is higher than in VCS population. Especially, the 700 bp bands generated by the primer BION-21 were identified commonly in two Gomphina populations, which identified populations and/or species. This specific primer was found to be useful in the identification of individuals and/or population, resulting from the different DNA polymorphism among individuals/species/population. Two Gomphina populations between the individual SAMCHEOK no. 03 and WONSAN no. 22 showed the longest genetic distance(0.696) in comparison with other individuals used. The complete linkage cluster analysis indicating three genetic groupings and dendrogram revealed close relationships among individual identities within two geographical populations of venus clam(G. aequilatera) from the Samcheok and Wonsan. The intra-species classification and clustering analyses inferred from molecular markers supported the traditional taxonomy of the species based on morphological characters such as shell size, shape and color. Accordingly, as mentioned above, RAPD analysis showed that VCS population was more or less separated from VCW population.

• Applied Microscopy
• /
• v.32 no.4
• /
• pp.345-360
• /
• 2002

Pollen morphology of four genera, 22 species of Korean Crassulaceae has been examined with light and scanning electron microscopy. The presence/absence of the aperture margo and granules was useful characters to clarify the generic boundaries, and the shapes of the streate were significant to delineate taxonomic relationships within the genus Sedum. The pollen grains of Korean Crassulaceae were small and medium in size. Hylotelephium viviparum has the smallest pollen grains, and H. viridescens the largest. The pollen grains are tricolporate, circular in polar view and were prolate to prolate-spheroidal in equatorial shape. Korean Crassulaceae species have striate grains. The close pollen morphological relationships among Hylotelephium, Meterostachys and Orostachys species were concordant to the results based on the previous molecular and morphological studies. The results of the clustering analysis using pollen characters support the segregation of Sedum sensu lato which has been proposed by the previous authors. Within the genus Sedum, S. kamtschatium is closely related to S. middendorffianum with granules on the surface of the pollen grains. Sedum polytrichoides, a member of the Sedum, was clustered to the species of the Meterostachys, Hylotelephium and Orostachys, and needs to reexamine the taxonomic status. O. malacophyllus collected at Chungdong-Jin was significantly differ from the same species from Gampo in pollen and morphological characters.