• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.179-184
• /
• 2024

In the car industry, welding is a fundamental linking technique used for joining components, such as steel, molds, and automobile parts. However, accurate inspection is required to test the reliability of the welding components. In this study, we investigate the detection of weld beads using 2D image processing in an automatic recognition system. The sample image is obtained using a 2D vision camera embedded in a lighting system, from where a portion of the bead is successfully extracted after image processing. In this process, the soot removal algorithm plays an important role in accurate weld bead detection, and adopts adaptive local gamma correction and gray color coordinates. Using this automatic recognition system, geometric parameters of the weld bead, such as its length, width, angle, and defect size can also be defined. Finally, on comparing the obtained data with the industrial standards, we can determine whether the weld bead is at an acceptable level or not.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.9 no.3
• /
• pp.47-57
• /
• 2007

This study focused on the properties natural dyeing and natural material and on the development of functional material for well-being in apparel industry. Comus officinalis Siebold et Zuccarini is used as natural dyeing material which had been reported that have curable effect for unbalanced immunity, geriatric diseases like urinary tract system, diabetes, hypertension, arthritis, tinnitus, hyperhidrosis and women's diseases like hypermenorrhea. And this material also has anti-cancer effect so that can restraint cancer cells. 3 kinds tester of cotton, wool and silk are dyed by boiled with each dye (flower, fruits, bark of tree) as first dyeing and dried in the shade. These testers are done by post-mordanting method. Aluminium Potassium(Alk(SO4)2), Cuprie Sulfate($CuSO4{\cdot}5H2O$), Stannous Chloride($SnCl2{\cdot}2H2O$), Ferrous Sulfate($FeCl2{\cdot}4H2O$), Titanium Sulfate 24% aqueous solution(Ti(SO4)2) are used as mordants. Dyeing results of Comus officinalis Siebold et Zuccarini flower and bark are shown as yellow color series. And dyeing result of fruits is pink color series. Silk shows the best dyeing property. As the point of view for dyeing property, Ti, Sn, Fe would be the properchoice for mordant. Following results are extracted in this study. Yellow color is resulted in dyeing with Cornus officinalis flower as non-mordanting condition. Yellowish red color is come from dyeing with Comus officinalis fruit as non-mordanting condition. Grayish yellow tone is resulted in dyeing with bark as non-mordanting condition. Orange tone color with Ti-mordanting, green tone color with Sn-mordanting and gray tone color with Fe-mordanting is resulted respectively. However light-fastness of Comus officinalis(flower, fruit, bark) is very low as 1 or 2 level in non-mordanting condition, Comus officinalis flower dyeing is turned out 3 or 4 level and fruit dyeing is 4 or 5 level, bark dyeing is 2 or 3 level with Ti-mordanting respectively. Eventually Comus officinalis fruit has the best light-colorfastness property among all of dyes. dry cleaning colorfastness of Cornus officinalis(flower, fruit, bark) is good as 4 or 5 level in Ti-mordanting condition, perspiration-colorfastness of Cornus officinalis(flower, fruit, bark) is good as 4 or 5 level in Ti-mordanting condition, With these results, this study could conclude that dye-ability, colorfastness problem is getting better after mordanting process and practical usage would be possible.

• Economic and Environmental Geology
• /
• v.50 no.4
• /
• pp.287-302
• /
• 2017

The carbonate rocks of the Daegi Formation are composed of the limestone at the upper and lower zones, and the dolomite at the middle zone, in which the upper zone has higher CaO content than others. The colors of carbonate rock in the Daegi Formation can be divided into five types; white, light brown, light gray, gray, and dark gray. The white to light gray colored rocks correspond to the high purity limestone with 53.15 ~ 55.64 wt. % CaO, and the light brown colored rocks contain 20.71 ~ 21.67 wt. % MgO. The bleaching of carbonate rocks are not related to CaO composition of the rocks, as light gray rocks tend to be higher in CaO content than those of the white rocks at the lower zone. The pelitic components are also occasionally increased in white limestone than light grey one. $Al_2O_3$ is one of the most difficult content to remove during hydrothermal processes, so the interpretation that the limestone is purified together with hydrothemral bleaching, has little merit. The wide range (over 16 ‰) of ${\delta}^{18}O_{SMOW}$, smaller variation (within 2 ‰) of ${\delta}^{13}C_{PDB}$ are apparent in both the upper and lower zones, which indicate the Daegi Formation had been affected overall by hydrothermal fluids. The K-Ar isotopic age of hydrothermal alteration in the GMI limestone mine is $85.1{\pm}1.7Ma$. Gradual change from grey through light grey to white limestone is accompaned by lower oxygen stable isotope values, which is major evidence that the hydrothermal effect is the main process of the bleaching. Although the Daegi Formation has suffered from hydrothermal activity and increase in whiteness, there is no clear evidence demonstrating the relationship between bleaching and high purity of limestone. The purification of limestone has nothing to do with the hydrothermal activity in this area. Instead, it should be considered that the change of sedimentary environment related to see-level fluctuation which can prevent deposition of pelitic components especially $Al_2O_3$ contrbuted to the formation of the high purity limestone in the upper zone of the Daegi Formation. Considering the evidences such as increase in CaO content of limestone by depth, gradual change from calcite to dolomite at the lower zones, and occurring the high purity limestone at the upper zone, the interpretation of sequence stratigraphic aspect to the formation of the high purity Daegi limestone appears to be more suitable than that of hydrothermal alteration origin.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.2
• /
• pp.65-69
• /
• 2001

Edge detection is the most important process that belongs to the first step in image recognition or vision system and can determine the efficiency valuation. The edge detection with color images is very difficult. because color images have lots of information that contain not only general information representing shape, brightness and so on but also that representing colors. In this paper, we propose architecture of universalized Color Morphological Pyramids(CMP) which is able to give effective edge detection. Image pyramid architecture is a successive image sequence whose area ratio 2$\^$-1/(ι= 1, 2, . . . ,N) after filtering and subsampling of input image. In this technique, noise removed by sequential filtering and resolution is degraded by downsampling using CMP in various color spaces. After that, new level images are constructed that apply formula using distance of neighbor vectors in close level images and detection its image.

• Journal of Biomedical Engineering Research
• /
• v.24 no.2
• /
• pp.61-68
• /
• 2003

This paper presents a quantitative analysis method for fall in sick times of the cerebral infarction patients using three types of magnetic resonance image, which play an important role in deciding method of medical treatment. For this object, image characteristics obtained by three radiographic methods of MRI and their relation were analyzed by means of object centered hierarchical Planning method. This methode presents an approach to the knowledge based processes for image interpretation and analysis. To compare three type of MRI. a multiple warping algorithm and affine transform method performed for image matching. Then each fall in sick times level of cerebral infarction was quantified and pseudo-color mapping performed by comparing gray level value one another according to Previously obtained hand maid data. The result of this study was compared to a medical doctors decision.

• Food Science of Animal Resources
• /
• v.38 no.2
• /
• pp.362-375
• /
• 2018

This study proposed a rapid microscopic examination method for pork freshness evaluation by using the self-assembled hyperspectral microscopic imaging (HMI) system with the help of feature extraction algorithm and pattern recognition methods. Pork samples were stored for different days ranging from 0 to 5 days and the freshness of samples was divided into three levels which were determined by total volatile basic nitrogen (TVB-N) content. Meanwhile, hyperspectral microscopic images of samples were acquired by HMI system and processed by the following steps for the further analysis. Firstly, characteristic hyperspectral microscopic images were extracted by using principal component analysis (PCA) and then texture features were selected based on the gray level co-occurrence matrix (GLCM). Next, features data were reduced dimensionality by fisher discriminant analysis (FDA) for further building classification model. Finally, compared with linear discriminant analysis (LDA) model and support vector machine (SVM) model, good back propagation artificial neural network (BP-ANN) model obtained the best freshness classification with a 100 % accuracy rating based on the extracted data. The results confirm that the fabricated HMI system combined with multivariate algorithms has ability to evaluate the fresh degree of pork accurately in the microscopic level, which plays an important role in animal food quality control.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.137-138
• /
• 2008

This paper proposes the modified image contrast enhancement technique for small-sized display of mobile handset. Sample images are user interface images, in which scaled up wVGA($800{\times}480$) from qVGA($320{\times}240$) that we can see easily in mobile handset. The display size of mobile handset is relatively small, so the goal of this paper is to simplify image contrast enhancement algorithm based on conventional HE (Histogram Equalization) algorithm and improve computational effectiveness to minimize power consumption in real hardware IC. In this paper, we adopt HE technique, which is classical and widely used for image contrast enhancement. At first, the input frame image is partitioned to temporal sub-frames and then analyzes gray level histogram of each sub-frame. In case that the analyzed histogram of some sub-frames deviates so much from reference level (it means that the sub-frame image components consist of too bright ones or dark ones), apply DHE(Dynamic Histogram Equalization) algorithm. In the other case, apply classical Histogram Linearization (or Global HE) algorithm. Also we compare the HE technique with gamma LUT (Look-Up Table) method, which is known as the simplest technique to enhance image contrast.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.49 no.4
• /
• pp.459-468
• /
• 2013

In the application of the ecosystem-based fisheries assessment Jeonnam marine ranching ecosystem, two fisheries, funnel fishery and trap fishery, were selected as target fisheries. Black seabream, Acanthopagru schlegelii, rock bream, Sebastes inermis, gray mullet, Mugil cephalus, were selected as target species for the funnel fishery, and conger eel, Conger myriaster, was target species for the trap fishery. For assessing indicators of four management objectives, that is the maintenance of sustainability, biodiversity, habitat quality and socio-economic benefits, indicators were selected considering the availability of data, which were 5 indicators for sustainability, 3 indicators for biodiversity, 4 indicators for habitat, 2 indicators for socio-economic benefit. The Objective risk indices for sustainability and biodiversity of two fisheries were estimated at yellow zone, medium risk level. The objective risk indices for habitat and socio-economic benefit were estimated at green zone, safe level. The species risk indices (SRI) were estimated at yellow zone. The fishery risk indices (FRIs) were estimated at 1.143 and 1.400 for funnel net fishery and trap fishery, respectively. Finally the ecosystem risk index estimated at 1.184.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.116-123
• /
• 2007

This paper proposed a new amplitude width modulation for OLED data driver IC. The data driver controls brightness of OLED by adjusting amplitude and width of the data drive current pulse. There were two conventional methods; pulse amplitude modulation(PAM) and pulse width modulation(PWM). The PWM method suffered from lower light emitting time efficiency at low luminance signal. The PAM method suffered from large chip area using DACs for each column. The proposed method was aiming at accurately controlling of the current level by MSB data and light emitting efficiency by LSB data to improve the inefficiencies of the PAM and a PWM. The proposed AWM driver circuit implemented using $0.35-{\mu}m$ 3-poly 4-metal CMOS high voltage process. The simulation result shows the improvement in the accuracy of the gray level control even though the driver circuit is smaller than the PAM.