• MALSORI
• /
• no.66
• /
• pp.87-103
• /
• 2008

We describe a new active learning method in conditional random fields (CRFs) framework for keyphrase extraction. To save elaboration in annotation, we use diversity and representative measure. We select high diversity training candidates by sentence confidence value. We also select high representative candidates by clustering the part-of-speech patterns of contexts. In the experiments using dialog corpus, our method achieves 86.80% and saves 88% training corpus compared with those of supervised method. From the results of experiment, we can see that the proposed method shows improved performance over the previous methods. Additionally, the proposed method can be applied to other applications easily since its implementation is independent on applications.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2002.11a
• /
• pp.66-71
• /
• 2002

In Generally, a imbedding and extracting is good as watermark using a random dot image. In this paper, when the autostreogram which has some randomness is used watermark image, distortion rate is low and extraction rate is high. Using this quality, when any logo image is transformed to same image domain randomly, distortion rate is low and extraction rate is high, more over the robustness is good in spite of hard clipping.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.11a
• /
• pp.66-71
• /
• 2002

In Generally, a imbedding and extracting is good as watermark using a random dot image. In this paper, when the autostreogram which has some randomness is used watermark image, distortion rate is low and extraction rate is high. Using this quality, when any logo image is transformed to same image domain randomly, distortion rate is low and extraction rate is high, more over the robustness is good in spite of hard clipping.

• Journal of Ocean Engineering and Technology
• /
• v.20 no.3 s.70
• /
• pp.15-23
• /
• 2006

On this study, realtime GPS technique and combination of GPS/GLONASS technique are used to extracting coastline. Th￡ object of coastline is Gwanganri beach located in Busan. The coastline is observed along the traces of coastline when high wave of scar by using digital map of 1:1,000 and at random time zone, coastline is surveyed along the boundary line that is contacting with sea water level. When the coastline of random time zone is converted by height of tide table, the coastline when high wave of scar and converted coastline are shown as coincident approximately.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.489-495
• /
• 2010

Hyperspectral imaging obtains information with a wider wavelength range a large number of bands. However, a high correlation between each band, computation cost, and noise causes inaccurate results in cases of no pre-processing. The noises of band extraction and elimination positively necessary in hyperspectral imaging. Since the previous studies have used a characteristic the whole image, a local characteristic of the image is considered for the noise band extraction. In this study, the Quadtree, which is a data structure algorithm. and the fractal dimension are adopted for noise band extraction in Hyperion images. The fractal dimensions of the segments divided by the Quadtree structure are calculated, and variation is used. We focused on the extraction of random noise bands in Hyperion images and compared them with the reference data made by visual decisions. The proposed algorithm extracts the most bands, including random noises. It is possible to eliminate more than 30 noise bands, regardless of images.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.63-66
• /
• 2009

Automatic segmentation of foreground from background in video sequences has attracted lots of attention in computer vision. This paper proposes a novel framework for the background subtraction that the foreground is segmented from the background by directly subtracting a background image from each frame. Most previous works focus on the extraction of more reliable seeds with threshold, because the errors are occurred by noise, weak color difference and so on. Our method has good segmentations from the approximate seeds by using the Random Walks with Restart (RWR). Experimental results with live videos demonstrate the relevance and accuracy of our algorithm.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.29 no.6
• /
• pp.761-769
• /
• 1996

The random amplified polymorphic DNA (RAPD) technique was used to characterize 18 reference strains of microalgae, mostly Chlorella species, collected from various localities around Korea peninsular. Eighteen strains consist of four genera of the family marine Chlorella from 12 samples, two genera of fresh water Chlorella from three samples, and three genera on Nannochloris. Twenty 10-mer anonymous primers were screened for amplification of genomic DNA extracted from samples using the CTAB extraction method. Nineteen of these oligonucleotide primers were positive or band producing. Three of 20 random primers (OPA 10, OPA 12, and OPA 18) resulted in both clear band and a high degree of reproducibility and showed some potential to be used to discriminate individual samples of both genetically hetero-and homogeneous populations, in determining phylogenetic relationships between species within a genus and developing individual fingerprints for each samples.

• Journal of Information Processing Systems
• /
• v.8 no.3
• /
• pp.421-436
• /
• 2012

Different types of fingerprint detection algorithms that are based on extraction of minutiae points are prevalent in recent literature. In this paper, we propose a new algorithm to locate the virtual core point/centroid of an image. The Euclidean distance between the virtual core point and the minutiae points is taken as a random variable. The mean, variance, skewness, and kurtosis of the random variable are taken as the statistical parameters of the image to observe the similarities or dissimilarities among fingerprints from the same or different persons. Finally, we verified our observations with a moment parameter-based analysis of some previous works.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.599-613
• /
• 2022

Non-proliferative diabetic retinopathy is a representative complication of diabetic patients and is known to be a major cause of impaired vision and blindness. There has been ongoing research on automatic detection of diabetic retinopathy, however, there is also a growing need for research on an automatic severity classification system. This study proposes an automatic detection system for pathological symptoms of diabetic retinopathy such as microaneurysms, retinal hemorrhage, and hard exudate by applying the Faster R-CNN technique. An automatic severity classification system was devised by training and testing a Random Forest classifier based on the data obtained through preprocessing of detected features. An experiment of classifying 228 test fundus images with the proposed classification system showed 97.8% accuracy.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.45 no.2
• /
• pp.93-98
• /
• 2022

To assess the feasibility of silk sericin for non-textile application, the storage stability and biological safety of sericin were examined. It was extracted at 37℃, 70℃, 100℃, and 121℃ for 1, 3, and 5 h to elucidate the effect of extraction condition on the stability and safety of silk sericin. The solubility was increased till approximately 26% with extraction temperature of 121℃ for 1 h. Sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE) showed that the molecular weight distribution depended on the extraction conditions. Extracted sericin displayed typical UV absorption bands upon spectrometric analysis. To examine the reproducibility of its obtained conformation, sericin was extracted thrice and its circular dichroism (CD) spectra was measured each time. Most CD spectra showed reproducibility regardless of temperature and time except under 100℃ extraction condition. The diversity of CD spectrum showed gradual reduction and was finally coincident with extraction time from 1 to 5 h. Notably, sericin has a negative peak of approximately 200 nm attributed to random coil conformation, regardless of extraction condition. However, at the 100℃ extraction condition, sericin showed both bands to be negative bands of approximately 200 and 220 nm, respectively. Sericin was centrifuged to determine the stability of storage conditions. The sericin extracted at 100℃ and 121℃ for 1 h was found to form gel rapidly within 1 h, but at 121℃ condition, the gel fraction was approximately 20% within 1 h which retained its phase regardless of storage time. The gel fraction of sericin extracted at 100℃ for 5 h increased with time, however at the 121℃ for 5 h condition, the gel fraction was measured to be less than 10% regardless of increase in storage time. Petriflim^TM AC plates test showed that sericin was safe from aerobic bacteria activity by extraction under high temperature.