• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.3
• /
• pp.207-218
• /
• 2006

The extraction of horizontal alignment and cross-section of roads is very important task in road safety diagnosis. Existing road safety diagnosis methods by investigators need much time and expense but don't provide various data. Therefor, we need road shape classification automatically and extraction method of horizontal alignment and cross-section of roads through digital photogrammetry system using GPS-VAN with laser scanner. In this paper, we propose a method of mobile laser scanning data acquisition, processing and developing extraction methods of horizontal alignment and cross-section of roads using mobile laser scanning data by GPS-VAN.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.3
• /
• pp.42-52
• /
• 2010

The purpose of this study is to produce digital elevation model (DEM) in the Jebu tidal flat, one of the west coast of the Korean Peninsula, by means of photogrammetric techniques from aerial digital stereo-images. Produced DEM would be become the fundamental data for change detection of the sediment and erosion. To do so, epipolar line is established by relative orientation. Area-based matching is then carried out based on this line and matching size according to surface property of tidal flat after a classified image is produced from reflectance and texture of the surface. As the results, DEM generated by the proposed method showed subtle changes in height more precisely than DEM using the fixed matching size and DEM by the commercial S/W in the region, such as tidal flats having few level differences.

• Korean Journal of Plant Taxonomy
• /
• v.45 no.2
• /
• pp.178-182
• /
• 2015

Stellaria sessiliflora Y. Yabe (Caryophyllaceae), which is known to be distributed throughout Japan excluding Okinawa, was recently found on Jeju Island in Korea. Reports on the Japanese flora state that this species is distributed on Jeju Island, and a photograph of one specimen (Slide No. 6294) collected from Jeju Island by Ohwi in May 1935 confirms this. Additionally, specimens at the National Arboretum and Korea Forest Research Institute indicate that S. sessiliflora has occurred on Jeju Island for a considerable amount of time. However, the species has never been officially listed in the flora of Korea. Stellaria sessiliflora is distinguished from S. media by having broader leaves with a slightly undulate margin, petiolate leaves on the upper part of the stem, and 10 stamens. The local name 'Geu-Neul-Byeol-Kkot' is given to the species based on its shady habitat under deciduous broadleaf forest. Details of the morphological characters, an illustration, the type specimen, voucher specimen data, and photographs of Stellaria sessiliflora in Korea are presented.

• Journal of Korea Water Resources Association
• /
• v.52 no.spc2
• /
• pp.791-799
• /
• 2019

This study explained the historical changes in the habitat structures based on the aerial photographs (1948, 1967, 1973, 1989 and 2010) of the mid-stream reach of the Mangyeong River. The habitat structure was divided into landforms and aquatic habitats. The landform was classified into bare land, vegetated land, water surface, farmland and artificial land. The aquatic habitat was classified into natural riffle, artificial riffle, run, head wando, tail wando, mid wando, pond and chute channel. The ratio of bareland decreased, and water surface and vegetated land increased after the excavation in 1970s and since the construction of weir in 1980s. As historical changes of aquatic habitat, ratio of run decreased sharply while mid wando increased sharply. aquatic habitats such as head wando, tail wando, and pond located on bars decreased dramatically.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.32-38
• /
• 2021

Image classification through deep learning on the image from photographs has been a very active research field for the past several years. In this paper, we propose a method of automatically discriminating stone images from domestic source through deep learning, which is to use Python's hash library to scan 300×300 pixel photo images of granites such as Hwangdeungseok, Goheungseok, and Pocheonseok, performing data preprocessing to create learning images by examining duplicate images for each stone, removing duplicate images with the same hash value as a result of the inspection, and deep learning by stone. In addition, to utilize VGGNet, the size of the images for each stone is resized to 224×224 pixels, learned in VGG16 where the ratio of training and verification data for learning is 80% versus 20%. After training of deep learning, the loss function graph and the accuracy graph were generated, and the prediction results of the deep learning model were output for the three kinds of stone images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.2
• /
• pp.122-129
• /
• 2014

In this study, emotion-classification gathered from users was performed, classification-experiments were then conducted using SVM(Support Vector Machine) and K-means algorithm. Total 15 numbers of channels; CP6, Cz, FC2, T7. PO4, AF3, CP1, CP2, C3, F3, FC6, C4, Oz, T8 and F8 among 32 members of the channels measured were adapted in Brain signals which indicated obvious the classification of emotions in previous researches. To extract emotion, watching DVD and IAPS(International Affective Picture System) which is a way to stimulate with photos were applied and SAM(Self-Assessment Manikin) was used in emotion-classification to users' emotional conditions. The collected users' Brain-wave signals gathered had been pre-processing using FIR filter and artifacts(eye-blink) were then deleted by ICA(independence component Analysis) using. The data pre-processing were conveyed into frequency analysis for feature extraction through FFT. At last, the experiment was conducted suing classification algorithm; Although, K-means extracted 70% of results, SVM showed better accuracy which extracted 71.85% of results. Then, the results of previous researches adapted SVM were comparatively analyzed.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.703-712
• /
• 2003

With the explosive growth n the numbers and sizes of imaging technologies, Content-Based Image Retrieval (CBIR) has been attacked the interests of researchers in the fields of digital libraries, image processing, and database systems. In general, in the case of query-by-image, in user has to select an image from database to query, even though it is not his completely desired one. However, since query-by-sketch approach draws a query shape according to the user´s desire it can provide more high-level searching interface to the user compared to the query-b-image. As a result, query-by-sketch has been widely used. In this paper, we propose a Java-based image retrieval system that consists of sketch query and image classification. We use two features such as color histogram and Haar wavelets coefficients to search similar images. Then the Leave-One-Out method is used to classify database images. The categories of classification are photo & painting, city & nature, and sub-classification of nature image. By using the sketch query and image classification, w can offer convenient image retrieval interface to user and we can also reduce the searching time.

• Korean Journal of Plant Taxonomy
• /
• v.42 no.1
• /
• pp.64-67
• /
• 2012

Drosera spathulata Labill., belonging to the family Droseraceae, was recently recorded for the first time in a forest wetland in Busan-si, Gijang-gun, Cheolma-myeon. This plant is distributed from eastern Australia throughout South East Asian, Japan, China, Taiwan, and now, Korea. This species, related by taxa to D. rotundifolia, is distinguished by possessing a smaller leaf size (10-20 mm long, 2.5-4.5 mm wide), racemes that are glandular-hairy, and pinkish petals. The newly given Korean name, 'Jom-kkeun-kkeun-yi-ju-geok' reflects the small size as compared to related taxa. A description of the key characteristics, an illustration, and photographs of the habitats of this plant are provided in this report.

• Korean Journal of Plant Taxonomy
• /
• v.44 no.4
• /
• pp.257-260
• /
• 2014

While preparing a floristic study of Korean Pteridophytes, we discovered the following two unrecorded species from Jeju Island: Cyclosorus penangianus (Hook.) Copel. and Pteris fauriei Hieron. C. penangianus can be distinguished from other Korean congeners of the genus Cyclosorus by having exindusiate sori, toward with sinus of ultimate segments of veinlets more than 4. P. fauriei can be distinguished from other Korean congeners of the genus Pteris by having ultimate segments with entire margins, veins reaching to leaf margin and membraneous petiolar scales.

• Korean Journal of Plant Taxonomy
• /
• v.43 no.3
• /
• pp.171-180
• /
• 2013

Two newly recorded species, Cyrtomium laetevirens and Dryopteris simasakii var. paleacea (Dryopteridaceae) were collected from forests in Jeonnam, Geongnam and Jeju-do, with the latter also, found addedly in Gwanaksan, Seoul. C. laetevirens (vernacular name: 'Yun-soe-go-bi) was distinguished from other Korean congeners of the genus Cyrtomium by having glossy laminae, narrow lanceolate, yellow-green pinnae with minutely serrated margin and gradually narrowing shape from base to apex, along with entire, unicolor, and white grayish indusia. D. simasakii var. paleacea (vernacular name: Cheung-cheung-ji-ne-go-sa-ri'), was distinguished by shining leaves, opposite pinnae arrangement, no falcate pinnules, and densely adpressed scaly wholly along with irregular dark brown scales on stipe and rachis. Descriptions and illustrations of the two taxa and their photographs in the habitat are provided along with a key to the species of Cyrtomium and sect. Hirpedes of Dryopteris from Korea.