• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.1-12
• /
• 2012

There are many trees in a roadside, parks or facilities for landscape. Although we are easily seeing a tree in around, it would be difficult to classify it and to get some information about it, such as its name, species and surroundings of the tree. To find them, you have to find the illustrated books for plants or search for them on internet. The important components of a tree are leaf, flower, bark, and so on. Generally we can classify the tree by its leaves. A leaf has the inherited features of the shape, vein, and so on. The shape is important role to decide what the tree is. And texture included in vein is also efficient feature to classify them. This paper evaluates the performance of a leaf classification system using both shape and texture features. We use Fourier descriptors for shape features, and both gray-level co-occurrence matrices and wavelets for texture features, and used combinations of such features for evaluation of images from the Flavia dataset. We compared the recognition rates and the precision-recall performances of these features. Various experiments showed that a combination of shape and texture gave better results for performance. The best came from the case of a combination of features of shape and texture with a flipped contour for a Fourier descriptor.

• Animal cells and systems
• /
• v.13 no.4
• /
• pp.453-460
• /
• 2009

Morphological and molecular classifications were attempted in an effort to establish species-specific classifications of three species of the genus Pholis in Korea; these species were subjected to morphological and molecular methodologies using body measurements, RFLP, RAPD, and phylogenetic trees using the nucleotide sequences of mitochondrial 16S and 12S ribosomal DNAs, cytochrome c oxidase I, and cytochrome b. The data demonstrated that the three species of genus Pholis are distinct from each other, both morphologically and genetically.

• Journal of Plant Biology
• /
• v.2 no.2
• /
• pp.1-21
• /
• 1959

1. The plant communities on Mt. Sulak, a typical alpine mountain in central Korea was researched from the standpoint of ecological survey. 2. The plant on this mountain can largely be classified into 2 categories, the warm zone (below 1100m) and the frigid zone. The former is again classified into a broad-leaved tree formation and a needle-leved tree formation, and the latter is calssified into a broad-leaved tree formation and needle-leaved tree formation, and shrub formation. 3. The broad-leaved tree formation in the warm zone can largely be classified into a Carpinus laxiflora-syringa Palibiniana var. kanibayashi association(1), a Carpinus erosa-Acer Pseudo-sieboldianun association(2), and a Quercus mongolica- Tripterygium Regelii association(3). 4. The needle-leaved tree formation in the warm zone can also largely ben classified into a Pinus densiflora- Miscanthus sinensis association(4), Abies holophylla- Tripterygium regelii association(5), Pinus kordiensis- Rhododendron schlippenbachii association(6) In the association(4), the canopy of the Pinus densiflora is gradually being occupied by the Quercus mongolica which is one kind of broad-leaved trees. 5. We can fully see a DryoPteris type of the flour layer plant type in the association (3) and also see a Sasamorpha type in the association (5). 6. The broad-leaved tree formation in the frigid zone can largely be classified into Quercus mongolica- Rhododendron schlippenbachii association (8). The constituents of tree and subtree layers in (7) and (8) associations are similar to those association (3), but the constituents of the shrub layer are different from those of associtation (3) due to the difference in height. 7. The needle-leaved formation in the frigid zone can largely be classified into Thuja koraiensisRodgersia podophylla var. viritis association (9) and Abies nephrolepis-Acer tschonoskii var. rubripes asscciation (10). The species of alpine plants or subalpine plants are gradually increased in this formation. 8. The shrub formation can also largely be classified into a Rhododendron mucronulatum- Patrinia saniculaefolia association (11) and Pinus pumila associatio (12). Association (12) has largely developed on the windy place. Association (12) was burned due to the bombing during the Korean war, but now we recoginized there occurred an invasion of Tripterygium Regelii in such a place. 9. The herb layer species which constitute the shrub formation are mostly alpine or subalpine plants of small size, and their kinds are also very few. 10. The growth of the Moss layer is especially good because of the varied conditions of the habitat. The kinds which can easily be seen are the genus of Thunidium, Haplocladium, Brachythecium, Macromitrium, Holonitrium, Atrichum, Schwstchkeopsis, Grimmia, Hedwigia, Rhynchostegium and Mnium. 11. The genus of the Sphagnum densly grows like a mat at the acid and moisturous place above 1100m. The authors should express their thanks to father. Yang Kisup, Dean of Catholic Medical College, Prof. Yoon Doksuen, from their valuable advice. Thanks arealso due to Prof. Numata, Chiba University, Prof. Takagi, Nagoya University and Prof. Ando, Hiroshima University in Japan for his kind help and identification of Bryophytes.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.155-164
• /
• 2021

Many studies have been conducted on developing automatic plant identification algorithms using machine learning to various plant features, such as leaves and flowers. Unlike other plant characteristics, barks show only little change regardless of the season and are maintained for a long period. Nevertheless, barks show a complex shape with a large variation depending on the environment, and there are insufficient materials that can be utilized to train algorithms. Here, in addition to the previously published bark image dataset, BarkNet v.1.0, images of barks were collected, and a dataset consisting of 53 tree species that can be easily observed in Korea was presented. A convolutional neural network (CNN) was trained and tested on the dataset, and the factors that interfere with the model's performance were identified. For CNN architecture, VGG-16 and 19 were utilized. As a result, VGG-16 achieved 90.41% and VGG-19 achieved 92.62% accuracy. When tested on new tree images that do not exist in the original dataset but belong to the same genus or family, it was confirmed that more than 80% of cases were successfully identified as the same genus or family. Meanwhile, it was found that the model tended to misclassify when there were distracting features in the image, including leaves, mosses, and knots. In these cases, we propose that random cropping and classification by majority votes are valid for improving possible errors in training and inferences.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.

• Journal of Korean Society of Forest Science
• /
• v.31 no.1
• /
• pp.53-61
• /
• 1976

Though it is not easy for those who study dendrology to memorize all the scientific names of trees, the names remaines in their memory can facilitate the understanding of foreign technical books. The scientific name of a tree indicates characteristics of shape, color, and other aspects of the tree and by analyzing the name we can see common element found in other scientific names of trees. It is helpful to those who want to memorize and study the scientific names of trees if they understand their etymology. The preseut study is the seconds report of the investigation which aims at examining the etymology of the scientific names of native and foreign trees growing in Korea and their original names not only at the habitat but in Japan, China, England, Germany, and France. While the first report, which was made known in Theses Vol. 9. (The City College of Seoul 1975), is the examination of the scientific names of trees belonging to Gymnospermae, the present report is that of scientific names of trees belonging to Piperales: 2 families, 2 genera and 2 species; and trees belonging to Salicales: 1 family, 3 genera, 44 species, 16 varieties, and 3 forms. As the etymology of the scientific names of trees is made clear, this study will help those who want memorize the scientific names and study foreign technical books and it is also useful for international interchange of trees. The classification is depended chiefly on Dendrology by Prof. Lee Tchang-bok and "Plant Resources of Korea" shown in Biblography No. 10; the native names of trees on Jumoku Daizusetsu by Dr. Uehara; and etymology on A source-Book of Biological Names and Terms by E.C. Jager. In the column of etymology of the scientific names for genera, species, varieties and forms, Gr. stands for Greek, L. for Latin, NL. for New Latin, and genit. for genitive.

• Korean Journal of Environment and Ecology
• /
• v.15 no.4
• /
• pp.369-378
• /
• 2002

To investigate the forest structure and to suggest the basic data of forest in the Baekcheon Valley, fifty plots were set up and surveyed According to the analysis of classification by TWINSPAN. the community was divided by five groups of Quercus mongolica-Pinus densiflora(I), P. densiflora-Q. mongolica(II), Acer pseudosieboldianum-Q. mongolica(III). Betula schmidtii-A. pseudosieboldianum(IV), and Cornus controversa community(V). The structure of communities was investigated using importance value by layers The survey results were summarized as follows: 1) the results of annual ring analysis revealed that the age of Pinus densiflora forest was about 50~75 years old and Q. mongolica forest was about 40 years. 2) number of the average species was 11 1$\pm$2.2 and number of average individual was 74.6$\pm$28 1 per a plot(100$m^2$). From the above results including DBH distribution analysis it was anticipated that the deciduous broad leaf tree like C. controversa and B. schmidtii will be climax species instead of Q. mongolica. and P. densiflora.

• Journal of Korean Society of Forest Science
• /
• v.102 no.3
• /
• pp.407-414
• /
• 2013

This study was conducted to classify forest cover types using the multivariate statistical analysis in the natural forest of western Mt. Jiri. On the basis of the vegetation data by point quarter sampling, the adopted analytical methods were species-area curve (SAC), hierarchical cluster analysis (HCA), indicator species analysis (ISA), and multiple discriminant analysis (MDA). SAC selected the outlier tree species which was likely to have no influence on the classification of forest cover types, excluded from all analytical process. Based on forest vegetative information, HCA classified the study area into 2 to 10 clusters and ISA indicated that the optimal number of clusters were seven. MDA was taken to test the clusters that classified with HCA and ISA. The seven clusters were classified appropriately as overall classification success were 91.3%. The classified forest cover types were named by the ratio of the dominant species in the upper layer of each cluster. They were (1) Quercus mongolica Pure forest, (2) Mixed mesophytic forest, (3) Q. mongolica - Q. serrata forest, (4) Abies koreana - Q. mongolica forest, (5) Fraxinus mandshurica forest, (6) Q. serrata forest, and (7) Carpinus laxiflora forest.

• Korean Journal of Environment and Ecology
• /
• v.15 no.4
• /
• pp.330-343
• /
• 2002

To investigate the vegetation structure of mountain ridge from Pijae to Doraegijae in Baekdudaegan, forty-three sites(size 500$m^2$) were set up and surveyed By using TWINSPAN classification. the plant community was divided into five groups, those are mixed forest on sub-alpine zone. Quercus mongolica - Acer pseudo-sieboldianum community, Q. mongolica-Pinus densiflora community, and Larix leptolepis forest. Quercus mongolica was found as a major woody plant species in the ridge area. And partly the subalpine zone in low elevation was occupied by deciduous tree species and mixed a few conifer such as Abies nephrolepis and Taxus cuspidata etc.. Species diversity index(Area 1,000$m^2$) in the showed calculated 2.0149~3.0139 and it was similar to those of the ridge area of the national parks in Beakdudaegan.

• Journal of Forest and Environmental Science
• /
• v.37 no.4
• /
• pp.269-279
• /
• 2021

This study was carried out to introduce the forest cover types of the Baekdudaegan inhabiting the number of native tree species. In order to understand the vegetation distribution characteristics of the Baekdudaegan, a vegetation survey was conducted on the major 20 mountains of the Baekdudaegan. The vegetation data were collected from 3,959 sample points by the point-centered quarter method. Each mountain was classified into 4-7 forests by using various multivariate statistical methods such as cluster analysis, indicator species analysis, multiple discriminant analysis, and species composition analysis. The forests were classified mainly according to the relative abundance of Quercus mongolica. There was a total of 111 classified forests and these forests were integrated into the following nine forest cover types using the percentage similarity index and by clustering according to vegetation type: 1) Mongolian oak, 2) Mongolian oak and other deciduous, 3) Oaks (Mixed Quercus spp.), 4) Korean red pine, 5) Korean red pine and oaks, 6) ash, 7) mixed mesophytic, 8) subalpine zone coniferous, and 9) miscellaneous forest. Forests grouped within the subalpine zone coniferous and miscellaneous classifications were characterized by similar environmental conditions and those forests that did not fit in any other category, respectively.