• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.812-818
• /
• 2020

Cervical cancer is the second most common female cancer in the world. In Korea, cervical cancer accounts for 13 percent of female cancers and 4,200 cases occur annually[1]. The purpose of this study is to use a deep learning model to identify the possibility of lesions in the cervix and to evaluate the efficient image preprocessing in order to diagnose diverse types of cervix in form. The study used 4,107 normal photographs of uterine cervix and 6,285 abnormal photographs of uterine cervix. Two types of image preprocessing were resized to square. The methods are cropping based on height and filling the space up and down with black images. In addition, all images were resampled to 256×256. The average accuracy of cropped cases is 94.15%. The average accuracy of the filled cases is 93.41%. According to the study, the model performance of cropped data was slightly better. But there were several images that were not accurately classified. Therefore, the additional experiment with pre-treatment process based on cropping is needed to cover images of the cervix in more detail.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.62-70
• /
• 2013

DIBR(Depth Image Based Rendering) is a kind of view synthesis algorithm to generate images at free view points from the reference color image and its depth map. One of the main challenges of DIBR is the occurrence of holes that correspond to uncovered backgrounds at the synthesized view. In order to cover holes efficiently, two main approaches have been actively investigated. One is to develop preprocessing algorithms for depth maps or parallax maps to reduce the size of possible holes, and the other is to develop hole filling methods to fill the generated holes using adjacent pixels in non-hole areas. Most conventional preprocessing algorithms for reducing the size of holes are based on the smoothing process of depth map. Filtering of depth map, however, attenuates the resolution of depth map and generates geometric distortions. In this paper, we proposes a novel preprocessing algorithm for parallax map to improve the performance of hole-filling by avoiding the drawbacks of conventional methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.19 no.1
• /
• pp.96-96
• /
• 2001

The aim of this study was to find out and confirm the project formulation, feasibility, scale and locations on the farmland development projects such as planned and ongoing tideland reclamation and irrigation facilities along the western coast of North Korea using satellite image data, Landsat TM, JERS OPS and SPOT PAN and aged maps. In order to apply to the study, remote sensing technologies such as geometric correction. digital mosaicking, image merging, linear extraction and land cover classification were studied. As the results of the study, the reclaimable tidal flats are recognized at about 178,000 ha equivalent to 59% of announced 300,000ha. and 16,000 ha of completed, 17,000 ha of ongoing project areas although 27,000 ha were revealed to be completed during 1987-1993. Almost planned projects are appeared to be shortage of water supply due to their small watersheds, however, most projects are connected with 2000 mile canal system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.397-404
• /
• 2012

Jeju where concentrates on agriculture and tourism, conversion of outdoor culture into cultivation under structure happens actively for the purpose of increasing profit so continuous examination on house cultivation area is very important for this region. This paper is to suggest the effective image classification method using high resolution satellite image to detect the greenhouse. We carried out classification of greenhouse using the supervised classification and rule-based classification method about Formosat-2 images. Connecting result of two classification try to find accuracy improvement for greenhouse detection. Results about each classification method were calculated the accuracy by comparing with the result of visual detection. As a result, mahalanobis distance among the supervised methods was resulted in the highest detection. Also, it could be checked that detection accuracy was improved by tying with result of supervised method and result of rule-based classification. Therefore, it was expected that effective detection of greenhouse would be feasible if henceforward further study is performed in the process of connecting supervised classification and rule-based classification.

• Spatial Information Research
• /
• v.2 no.2
• /
• pp.135-145
• /
• 1994

The primary purpose of this study is, using Landsat remote sensing data and a image processing software, ERDAS, to generate real data and image photographs on physical land use of the Seoul metropolitan region. The remote sensing data used in this study are Landsat MSS data (August 28, 1979) and TM data (May 31, 1991) which cover the Seoul metropolitan region of Korea. The spatial resolutions of MSS data and TM data are 57m X 79m and 30m X 30m respectively. In addition, this study aims at contrasting urbanization phases of the Seoul metropolitan region in 1979 with those in 1991, by making image photographs and statistics on physical land use. Summing up the major results, built-up area ratio within the Seoul city had been expanded from 41.9% in 1979 to 64.5% in 1991 and that within the radius of 40km of Seoul city hall had been expanded from 10.5% In 1979 to 19.8% in 1991. The data and technique developed in this study could serve as a useful tool in making various kinds of spatial plannings, that is, urban and regional planning, selection of optimal new town location, evaluation of public facilities location alternatives, etc..

• Journal of Broadcast Engineering
• /
• v.16 no.5
• /
• pp.801-810
• /
• 2011

This paper proposes a new lossless data embedding algorithm on spatial domain of digital images. A single key parameter is required to embed and extract data in the algorithm instead of embedding any additional information such as the location map. A $3{\times}3$ window slides over the cover image by one pixel unit, and one bit can be embedded at each position of the window. So, the ideal embedding capacity equals to the number of pixels in an image. For further increase of embedding capacity, new weight parameters for the estimation of embedding target pixels have been used. As a result, significant increase in embedding capacity and better quality of the message-embedded image in high capacity embedding have been achieved. This algorithm is verified with simulations.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.561-566
• /
• 2019

In the Internet space, integrity and security must be maintained for secure and confidential communication, which ensures reliability between sender and receiver. Cryptography is an important factor in maintaining robustness against external attacks. For this purpose, encryption and steganography methods are used. Steganography is a method of hiding confidential information without making statistically significant changes to digital media. I propose a method of transforming the Hangul-Jamo consisting of choseong, jungseong and jongseong, and inserting them into RGB pixel values of the cover image. In order to improve security, a new blending method was used to hide the altered information in the lowest region. In this case, a mixture of LSB and LDR techniques was applied. PSNR was calculated for image quality. The PSNR of the proposed method is 43.225dB, which satisfies the lowest level.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.19 no.1
• /
• pp.95-106
• /
• 2001

The aim of this study was to find out and confirm the project formulation, feasibility, scale and locations on the farmland development projects such as planned and ongoing tideland reclamation and irrigation facilities along the western coast of North Korea using satellite image data, Landsat TM, JERS OPS and SPOT PAN and aged maps. In order to apply to the study, remote sensing technologies such as geometric correction. digital mosaicking, image merging, linear extraction and land cover classification were studied. As the results of the study, the reclaimable tidal flats are recognized at about 178, 000 ha equivalent to 59% of announced 300, 000ha. and 16, 000 ha of completed, 17, 000 ha of ongoing project areas although 27, 000 ha were revealed to be completed during 1987-1993. Almost planned projects are appeared to be shortage of water supply due to their small watersheds, however, most projects are connected with 2000 mile canal system.

• Applied Microscopy
• /
• v.41 no.1
• /
• pp.69-73
• /
• 2011

High-voltage electron microscope (HVEM) has higher resolution and penetration power than conventional transmission electron microscope that could be load thick specimen. Some researchers have taken this advantage of HVEM to explore 3-dimensional configuration of the biological structures including tissue and cells. Whole mount preparations has been employed to study some cell lines and primary culture cells. In this study, we would like to introduce useful whole mount preparation method for neuronal studies. The plastic coverslips were punched, covered by formvar membrane and coated with carbon. The neurons obtained embryonic 18 rat hippocampus were seeded on the prepared cover slip. The coverslips were fixed, dried in freeze drier and kept in a descicator until HVEM observation. We could observe detailed neuronal structures such as soma, dendrite and spine under HVEM without conventional thin section and heavy metal stain. The anaglyphic image based on stereo paired image ($-8^{\circ},+8^{\circ}$) provides three dimensional perception of the neuronal dendrites and their spines. This method could be applied to sophisticated analysis of dendritic spine under the various experimental conditions.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.2 s.25
• /
• pp.47-52
• /
• 2003

Change detection and analysis is a powerful application of remote sensing, in that the spectral resolution of multi-band sensors can be used to advantage in monitoring both significant and subtle land cover changes over time. In this study, the LANDSAT TM data was used to detect the change areas affected by flood from a heavy rainfall. The study area is the Nakdong River located in the Korea peninsular. Among the several change detection techniques, change vector analysis(CVA), principle component analysis(PCA) and image difference approach are utilized in this paper. CVA uses any number of spectral bands from multi-date satellite data to produce change image that yield information of the magnitude and direction of differences pixel values. And accuracy assessment was carried out with a change image produced from three techniques. In result, CVA was found to be the most accurate for detecting areas affected by flood. CVA with the overall accuracy and Kappa coefficient of 97.27 percent and 94.45 percent, respectively.