• Journal of Korea Multimedia Society
• /
• v.19 no.4
• /
• pp.736-746
• /
• 2016

In this paper, we propose an automatic prostate cancer detection method using position, signal intensity and texture feature based on SVM in multi-parametric MR images. First, to align the prostate on DWI and ADC map to T2wMR, the transformation parameters of DWI are estimated by normalized mutual information-based rigid registration. Then, to normalize the signal intensity range among inter-patient images, histogram stretching is performed. Second, to detect prostate cancer areas in T2wMR, SVM classification with position, signal intensity and texture features was performed on T2wMR, DWI and ADC map. Our feature classification using multi-parametric MR imaging can improve the prostate cancer detection rate on T2wMR.

• Fisheries and Aquatic Sciences
• /
• v.16 no.4
• /
• pp.303-309
• /
• 2013

Microsatellite markers are important for gene mapping and for marker-assisted selection. Sixty-five polymorphic microsatellite markers were developed with an enriched partial genomic library from olive flounder Paralichthys olivaceus an important commercial fish species in Korea. The variability of these markers was tested in 30 individuals collected from the East Sea (Korea). The number of alleles for each locus ranged from 2 to 33 (mean, 17.1). Observed and expected heterozygosity as well as polymorphism information content varied from 0.313 to 1.000 (mean, 0.788), from 0.323 to 0.977 (mean, 0.820), and from 0.277 to 0.960 (mean, 0.787), respectively. Nine loci showed significant deviation from the Hardy-Weinberg equilibrium after sequential Bonferroni correction. Analysis with MICROCHECKER suggested the presence of null alleles at five of these loci with estimated null allele frequencies of 0.126-0.285. These new microsatellite markers from genomic libraries will be useful for constructing a P. olivaceus linkage map.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5112-5129
• /
• 2019

Image enhancement is a challenging problem in the field of image processing, especially low-light color images enhancement. This paper proposed a robust and comprehensive enhancement method based several points. First, the idea of bright channel is introduced to estimate the illumination map which is used to attain the enhancing result with Retinex model, and the color constancy is keep as well. Second, in order eliminate the illumination offsets wrongly estimated, morphological closing operation is used to modify the initial estimating illumination. Furthermore, in order to avoid fabricating edges, enlarged noises and over-smoothed visual features appearing in enhancing result, a multi-scale closing operation is used. At last, in order to avoiding the haloes and artifacts presented in enhancing result caused by gradient information lost in previous step, guided filtering is introduced to deal with previous result with guided image is initial bright channel. The proposed method can get good illumination map, and attain very effective enhancing results, including dark area is enhanced with more visual features, color natural and constancy, avoiding artifacts and over-enhanced, and eliminating Incorrect light offsets.

• The Korean Journal of Ecology
• /
• v.11 no.3
• /
• pp.145-152
• /
• 1988

The potential natural vegetation of Naejangsan national park area, southwestern Korea, was inferred from the actual vegetation. With the phytosociological classification, ordinatins and field surveys, the actual vegetation map of the area was made in scale 1:25, 000, including ten communities of Pinus densiflora, quercus mongolica, Quercus variabilis, Carpinus laxiflora, Daphnipyllum macropodum, Carpinus tschonoskii, Quercus aliena-Carpinus tschonoskii, Cornus controversa-Lindera erythrocarpa, Torreya mucifera-Zelkova serrate and Acer mono-Zelkova serrata community. The analyses of species richness, age structure and various informations on vegetation changes suggest the three pathways of late stage succession from P. densiflora forest to climatic climax. The first of them is through Q. variabilis forest to Q. monogolica forest in the upper parts of the mountain, the second through Q. variabilis and Q. serrata forest to C. laxiflora forest in the middle parts and the third through Q. aliena forest to C. tschonoskii forest in lower parts. Considering the actual vegetation and informations on the vegetation changes including human activities, the potential natural vegetation of the mountain mainly composed of Q. monogolica, C. laxiflora, C. tschonoskii, P. densiflora and Z. serrata forest as climatic climax and/or edaphic climax was inferred. The present situration of nature conservation in the area was estimated by the examination on the actual vegetation and potential natural vegetation map.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.1
• /
• pp.286-295
• /
• 2000

We present a novel statistically adaptive method using the Minimum Description Length(MDL) principle for unsupervised segmentation of magnetic resonance(MR) images. In the method, Markov random filed(MRF) modeling of tissue region accounts for random noise. Intensity measurements on the local region defined by a window are modeled by a finite Gaussian mixture, which accounts for image inhomogeneities. The segmentation algorithm is based on an iterative conditional modes(ICM) algorithm, approximately finds maximum ${\alpha}$ posteriori(MAP) estimation, and estimates model parameters on the local region. The size of the window for parameter estimation and segmentation is estimated from the image using the MDL principle. In the experiments, the technique well reflected image characteristic of the local region and showed better results than conventional methods in segmentation of MR images with inhomogeneities, especially.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.11 no.2
• /
• pp.193-204
• /
• 1999

Performance of a variable-speed, roller-type vane compressor was evaluated at low evaporating temperature. First, an experimental investigation was conducted to examine the performance variation as functions of both outdoor temperature and rotating speed. For this purpose, a typical heat pump was implemented as a test apparatus to measure mass flow rate and power input. Secondly, computational investigations corresponding to the heat pump test conditions were performed to predict compressor performance using ORNL Map-Based compressor model. Results obtained from the heat-pump experiments showed that both mass flow rate and power consumption were sensitively dependent on both evaporating temperature and compressor speed as was predicted from the computational results. From the comparisons of both experimental and computational results, it was well recognized that the ORNL model was subjected to larger error in the accuracy of prediction as outdoor temperature decreased. When the outdoor temperature was above $-5^{\cire}C$, errors of predicted values corresponding to both mass flow rate and power consumption were estimated as $\pm$10% and $\pm$ 15%, respectively. Finally, it is suggested that the ORNL model needs to be re-evaluated if compressor map data tested below $-5^{\cire}C$(in evaporating temperature) are available.

• The Korean Journal of Ecology
• /
• v.25 no.4
• /
• pp.205-211
• /
• 2002

For landscape ecological management of the isolated forestlands in Incheon city located in the western tip of South Korea, the forest vegetation of Mt. Cheolma was classified phytosciologically and mapped out its spatial distribution at a scale of 1:5,000. Characteristics of forest landscape structures were discussed in terms of the number and size of patches obtained by analy zing vegetation map. Units to manage the forest vegetation were categorized into eighteen communities, seventeen groups, and sixteen subgroups. Landscape elements were classified into five types: secondary vegetation, introduced vegetation for forestry (IVF), introduced vegetation for agriculture (IVA), and other elements. Two hundred and ninety-three forest landscape patches covers 443.3ha, of which IVF accounted for 316.8ha(71.5$\%$), the largest portion, secondary vegetation for 101.2ha(22.8$\%$), IVA for 6.2ha(1.4$\%$), and others for 19.1ha(4.3$\%$). The ratio of natural forest elements of 31.9$\%$ showed that this area was mainly comprised of artificially introduced vegetation, such as Robinia pseudoacacia plantation and Pinus rigida plantation. Forest landscape patches have a mean area of 4.5ha, a density of 66.1/100ha, and a diversity index of 0.87. It was estimated that differentiation of patches recognized in community level would be related to human interference and those in subordinate level to natural processes.

• Korean Journal of Remote Sensing
• /
• v.25 no.3
• /
• pp.295-309
• /
• 2009

In this study, an iterative maximum a posteriori (MAP) approach using a Bayesian model of Markovrandom field (MRF) was proposed for despeckling images that contains speckle. Image process is assumed to combine the random fields associated with the observed intensity process and the image texture process respectively. The objective measure for determining the optimal restoration of this "double compound stochastic" image process is based on Bayes' theorem, and the MAP estimation employs the Point-Jacobian iteration to obtain the optimal solution. In the proposed algorithm, MRF is used to quantify the spatial interaction probabilistically, that is, to provide a type of prior information on the image texture and the neighbor window of any size is defined for contextual information on a local region. However, the window of a certain size would result in using wrong information for the estimation from adjacent regions with different characteristics at the pixels close to or on boundary. To overcome this problem, the new method is designed to use less information from more distant neighbors as the pixel is closer to boundary. It can reduce the possibility to involve the pixel values of adjacent region with different characteristics. The proximity to boundary is estimated using a non-uniformity measurement based on standard deviation of local region. The new scheme has been extensively evaluated using simulation data, and the experimental results show a considerable improvement in despeckling the images that contain speckle.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3D
• /
• pp.527-534
• /
• 2006

This study estimated the forest damage of Kangwon-Do fire disaster occurred April 2005. For the estimation, the delineation of fire damaged area was performed using SPOT-4 satellite image and DSM (Digital surface model)/DTM (Digital Terrain Model) was generated by airborne and ground LiDAR data to calculate forests height. The damaged amount of money was calculated in forest area using stand volume formula, combining the canopy height from forest height model and digital stock map. The total forest damage amounted to 3.9 billion won.

• Korean Journal of Agricultural Science
• /
• v.50 no.3
• /
• pp.357-364
• /
• 2023

In this study, we propose a ripe tomato bunch localization method based on convolutional neural networks, to be applied in robotic harvesting systems. Tomato images were obtained from a smart greenhouse at the Rural Development Administration (RDA). The sample images for training were extracted based on tomato maturity and resized to 128 × 128 pixels for use in the classification model. The model was constructed based on four-layer convolutional neural networks, and the classes were determined based on stage of maturity, using a Softmax classifier. The localization of the ripe tomato bunch region was indicated on a class activation map. The class activation map could show the approximate location of the tomato bunch but tends to present a local part or a large part of the ripe tomato bunch region, which could lead to poor performance. Therefore, we suggest a recursive method to improve the performance of the model. The classification results indicated that the accuracy, precision, recall, and F1-score were 0.98, 0.87, 0.98, and 0.92, respectively. The localization performance was 0.52, estimated by the Intersection over Union (IoU), and through input recursion, the IoU was improved by 13%. Based on the results, the proposed localization of the ripe tomato bunch area can be incorporated in robotic harvesting systems to establish the optimal harvesting paths.