• Title/Summary/Keyword: Restoration Image

Search Result 735, Processing Time 0.025 seconds

Feasibility of Optical Character Recognition (OCR) for Non-native Turtle Detection (UAV 기반 외래거북 탐지를 위한 광학문자 인식(OCR)의 가능성 평가)

  • Lim, Tai-Yang;Kim, Ji-Yoon;Kim, Whee-Moon;Kang, Wan-Mo;Song, Won-Kyong
    • Journal of the Korean Society of Environmental Restoration Technology
    • /
    • v.25 no.5
    • /
    • pp.29-41
    • /
    • 2022
  • Alien species cause problems in various ecosystems, reduce biodiversity, and destroy ecosystems. Due to these problems, the problem of a management plan is increasing, and it is difficult to accurately identify each individual and calculate the number of individuals, especially when researching alien turtle species such as GPS and PIT based on capture. this study intends to conduct an individual recognition study using a UAV. Recently, UAVs can take various sensor-based photos and easily obtain high-definition image data at low altitudes. Therefore, based on previous studies, this study investigated five variables to be considered in UAV flights and produced a test paper using them. OCR was used to monitor the displayed turtles using the manufactured test paper, and this confirmed the recognition rate. As a result, the use of yellow numbers showed the highest recognition rate. In addition, the minimum threat distance was confirmed to be 3 to 6m, and turtles with a shell size of 6 to 8cm were also identified during the flight. Therefore, we tried to propose an object recognition methodology for turtle display text using OCR, and it is expected to be used as a new turtle monitoring technique.

Deep learning-based monitoring for conservation and management of coastal dune vegetation (해안사구 식생의 보전 및 관리를 위한 딥러닝 기반 모니터링)

  • Kim, Dong-woo;Gu, Ja-woon;Hong, Ye-ji;Kim, Se-Min;Son, Seung-Woo
    • Journal of the Korean Society of Environmental Restoration Technology
    • /
    • v.25 no.6
    • /
    • pp.25-33
    • /
    • 2022
  • In this study, a monitoring method using high-resolution images acquired by unmanned aerial vehicles and deep learning algorithms was proposed for the management of the Sinduri coastal sand dunes. Class classification was done using U-net, a semantic division method. The classification target classified 3 types of sand dune vegetation into 4 classes, and the model was trained and tested with a total of 320 training images and 48 test images. Ignored label was applied to improve the performance of the model, and then evaluated by applying two loss functions, CE Loss and BCE Loss. As a result of the evaluation, when CE Loss was applied, the value of mIoU for each class was the highest, but it can be judged that the performance of BCE Loss is better considering the time efficiency consumed in learning. It is meaningful as a pilot application of unmanned aerial vehicles and deep learning as a method to monitor and manage sand dune vegetation. The possibility of using the deep learning image analysis technology to monitor sand dune vegetation has been confirmed, and it is expected that the proposed method can be used not only in sand dune vegetation but also in various fields such as forests and grasslands.

Generation of Mosaic Image using Aerial Oblique Images (경사사진을 이용한 모자이크 영상 제작)

  • Seo, Sang Il;Park, Byung-Wook;Lee, Byoung Kil;Kim, Jong In
    • Journal of Korean Society for Geospatial Information Science
    • /
    • v.22 no.3
    • /
    • pp.145-154
    • /
    • 2014
  • The road network becomes more complex and extensive. Therefore, the inconveniences are caused in accordance with the time delay of the restoration of damaged roads, demands for excessive costs on information collection, and limitations on acquisition of damage information of the roads. Recently, road centric spatial information is gathered using mobile multi sensor system for road inventory. But expensive MMS(Mobile Mapping System) equipments require high maintenance costs from beginning and takes a lot of time in the data processing. So research is needed for continuous maintenance by collecting and displaying the damaged information on a digital map using low cost mobile camera system. In this research we aim to develop the techniques for mosaic with a regular ground sample distance using successive image from oblique camera on a vehicle. For doing this, mosaic image is generated by estimating the homography of high resolution oblique image, and the ground sample distance and appropriate overlap are analyzed using high resolution aerial oblique images which contain resolution target. Based on this we have proposed the appropriate overlap and exposure interval for mobile road inventory system.

Study of Condition Analysis and Diagnosis on Oil Paintings with Terahertz Imaging (테라헤르츠 이미징기법을 이용한 유화의 상태분석 및 진단)

  • Baek, Na Yeon;Song, You Na;Kim, Moon Jeong;Chung, Yong Jae;Lee, Han Hyoung
    • Journal of Conservation Science
    • /
    • v.35 no.3
    • /
    • pp.237-244
    • /
    • 2019
  • In this study, we applied terahertz imaging technology to three Korean modern oil paintings ('Boy,' 'Girl,' and 'Hyehwadong Landscape'); investigated the types of inner layer information in the pictures that can be extracted with terahertz imaging technology; and analyzed the conditions for extracting them. The biggest problem in the terahertz imaging analysis we encountered was the image distortion caused by the change of the distance between the target surface and the terahertz detector, depending on the surface curvature of the target paintings. We then developed a 'working distance maintaining device' to solve this problem. As a result, the terahertz imaging technique was used to identify the base material characteristics and any patterns of damage inside, and presented the optimal conditions for identifying each characteristic. In addition, it was useful to employ the terahertz frequency-division image to check the characteristics of the background materials. To confirm coloring techniques such as brush strokes, it is effective to compare the maximum reflection peak image with the cross-section image; and to detect damage information inside the paintings that cannot be observed on the surface, to compare the cross-section image with the frequency-division image. On the other hand, according to the terahertz imaging analysis of the oil paintings, the internal structural damage marks of 'Boy' and 'Girl' were confirmed, and the artist's painting style was confirmed in 'Hyehwadong Landscape.' The above results are expected to be useful for the analysis and diagnosis of Korean modern oil paintings for their preservation.

An Algorithm of Fingerprint Image Restoration Based on an Artificial Neural Network (인공 신경망 기반의 지문 영상 복원 알고리즘)

  • Jang, Seok-Woo;Lee, Samuel;Kim, Gye-Young
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.21 no.8
    • /
    • pp.530-536
    • /
    • 2020
  • The use of minutiae by fingerprint readers is robust against presentation attacks, but one weakness is that the mismatch rate is high. Therefore, minutiae tend to be used with skeleton images. There have been many studies on security vulnerabilities in the characteristics of minutiae, but vulnerability studies on the skeleton are weak, so this study attempts to analyze the vulnerability of presentation attacks against the skeleton. To this end, we propose a method based on the skeleton to recover the original fingerprint using a learning algorithm. The proposed method includes a new learning model, Pix2Pix, which adds a latent vector to the existing Pix2Pix model, thereby generating a natural fingerprint. In the experimental results, the original fingerprint is restored using the proposed machine learning, and then, the restored fingerprint is the input for the fingerprint reader in order to achieve a good recognition rate. Thus, this study verifies that fingerprint readers using the skeleton are vulnerable to presentation attacks. The approach presented in this paper is expected to be useful in a variety of applications concerning fingerprint restoration, video security, and biometrics.

Clinical convergence angle and rounding radius on tooth preparation for zirconia all-ceramic crown (지르코니아 전부도재관 지대치 삭제시 축면 경사각과 만곡 반경에 대한 조사)

  • Kim, Hye-Eun;Woo, Yi-Hyung;Pae, Ah-Ran;Kim, Hyeong-Seob
    • The Journal of Korean Academy of Prosthodontics
    • /
    • v.49 no.1
    • /
    • pp.22-28
    • /
    • 2011
  • Purpose: This article attempted to examine how teeth for restoration is made in a clinical practice and utilize it as future educational material of teeth formation and basic data for additional research. Materials and methods: This experiment investigated the models sent to milling center for production of zirconia crowns. After scanned with Lava CAD/CAM System (3M ESPE, Seefeld, Germany), they are measured on 'ImageJ (version 1.32j, National Institutes of Health, USA)' program and compared and analyzed. Convergence angle from mesio-distal surfaces and bucco-lingual surfaces of each teeth are measured. Also, bucco-lingual diameter of the region lowered as much as 0.4 mm from incisal edge in anterior teeth except canines.(This measure is defined as the Peak 0.4) The analysis of data between each group was conducted by Windows SPSS statistic program, and was proved significant on 95% confidence level by independent t-test, one-way ANOVA and multiple analysis (Sheff${\'{e}}$ test). Results: The mean value of convergence angle was $18.67^{\circ}$ It is ranked as molar ($26.70^{\circ}$) > premolar ($16.87^{\circ}$) > anterior teeth ($14.81^{\circ}$) in the order of mesio-distal convergence angle; anterior teeth ($22.32^{\circ}$) > molar ($20.93^{\circ}$) > premolar ($15.41^{\circ}$) in the order of bucco-lingual convergence angle. The mean value of Peak 0.4 was 1.18 mm. Conclusion: Convergence angle of abutment of zirconia all ceramic crown has difference depending on the location in the arch. Due to the nature of production of zirconia all ceramic crown, convergence angle of abutment and line angle finishing degree can have an effect on internal suitability of restoration.

Utilization of the Old Big Tree and Its Surrounding Space Pertaining to Cultural Value in Seoul (서울시 보호수를 대상으로 한 노거수 공간의 문화적 활용 가치 연구)

  • Jeong, Wook-Ju;Yoon, Sang-Jun
    • Journal of the Korean Society of Environmental Restoration Technology
    • /
    • v.17 no.1
    • /
    • pp.215-233
    • /
    • 2014
  • Seoul is an ancient city with a long history but there is hesitancy over referring to as a historic city due to the lack of traceable historic urban landscape elements which resulted from numerous invasions and general destruction. From a diachronic perspective, the nature which was survived the influence of development, could be the key element that links the past with the city's radically changed image in modern times. Although "old big trees" may be not a dominant influence with regards to the historical authenticity of the city, they are objects which contribute towards the historical authenticity by providing a sense of place in terms of connected narratives, as well as their natural image. However, the protection policy for an "old big tree" would place too much emphasis on the aspect of the ecological value rather than its cultural value. Generally, trees have been protected by installing a fence and a signboard around them as well as receiving additional care. However, it is difficult to find that surrounding space around the "law-protected tree" is connected with its original historical and cultural values. Even though the space around trees are no longer utilized in the same way as was so in the past, they still have high-potential in terms of cultural utilization. Therefore, the subject of this study is the "old big tree" as a natural object which contributed to the historical authenticity of Seoul. The current status of these "old big trees", aged between 100 and 800 years old, currently indicate that there are 215 trees designated as "law-protected tree" by the Seoul metropolitan government. This study aims to investigate the status of protection and utilization of the existing "law-protected trees" in the city of Seoul and find a way to increase both ecological preservation and cultural utilization for the high-potential "law-protected trees" within the city itself. In order to achieve this, previously researched papers shall be reviewed and surveyed pertaining to present usage patterns of the 215 "law-protected trees". In addition, five cases have been reviewed which focus on a few of utilizing the "protected trees" and their surrounding spaces. The results of the research indicate that 21 "old big trees" have high-potential in terms of cultural utilization as well as ecological value. However, it was revealed that there are limitations to pursue the value of preservation and utilization simultaneously throughout current regimental management. In order to cope with the current situation, it is pointed out that management facilities should be designed and installed by creative and flexible methods of organizing with consideration to the surrounding space and context. Even though in the case where there may not be a connecting history or legendary stories, the "old big trees" can serve as the fundamental features of small scale parks -dependent on their location, condition and environment- which will be of value to the local communities. This study could serve as a practical reference for the management and utilization of "old big trees" nationwide with numbers reaching 12,300 besides the city of Seoul.

Estimation of the Original Location of Haechi (Haetae) Statues in Front of Gwanghwamun Gate Using Archival Photos from Early 1900s and Newly Taken Photos by Image Analysis (1900년대 초반의 기록사진과 디지털 카메라 사진분석을 활용한 광화문 앞 해치상의 원위치 추정)

  • Oh, Hyundok;Nam, Ho Hyun;Yoo, Yeongsik;Kim, Jung Gon;Kang, Kitaek;Yoo, Woo Sik
    • Journal of Conservation Science
    • /
    • v.37 no.5
    • /
    • pp.491-504
    • /
    • 2021
  • Gwanghwamun Gate of Gyeongbokgung Palace was dismantled and relocated during the Japanese colonial period, destroyed during the Korean War, reconstructed with reinforced concrete in 1968, and finally erected at its present location in 2010. A pair of Haechi statues located in front of Gwanghwamun was dismantled and relocated several times, and the statues have yet to be returned precisely to their original positions. This study assesses the historical accuracy of their current placement under the Gwanghwamun Square Restructuring Project of the Seoul Metropolitan Government and the Cultural Heritage Administration based on archival photos from the early 1900s, and proposes a method to estimate the original positions of the Haechi through image analysis of contemporary photographs and recent digital camera photos. We estimated the original position of the Haechi before the Japanese colonial period by identifying the shooting location of the archival photo and reproducing contemporary photographs by calculating the angle and distance to the Haechi from the shooting location. The leftmost and rightmost Haechi were originally located about 9.6 m to the east and 7.4 m to the north and about 1.9 m to the west and 8.0 m to the north, respectively, of their current location indicators. As the first attempt to determine the original location of a building and its accessories using archival photos, this study launches a new scientific methodology for the restoration of cultural properties.

Restoration of Missing Data in Satellite-Observed Sea Surface Temperature using Deep Learning Techniques (딥러닝 기법을 활용한 위성 관측 해수면 온도 자료의 결측부 복원에 관한 연구)

  • Won-Been Park;Heung-Bae Choi;Myeong-Soo Han;Ho-Sik Um;Yong-Sik Song
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.29 no.6
    • /
    • pp.536-542
    • /
    • 2023
  • Satellites represent cutting-edge technology, of ering significant advantages in spatial and temporal observations. National agencies worldwide harness satellite data to respond to marine accidents and analyze ocean fluctuations effectively. However, challenges arise with high-resolution satellite-based sea surface temperature data (Operational Sea Surface Temperature and Sea Ice Analysis, OSTIA), where gaps or empty areas may occur due to satellite instrumentation, geographical errors, and cloud cover. These issues can take several hours to rectify. This study addressed the issue of missing OSTIA data by employing LaMa, the latest deep learning-based algorithm. We evaluated its performance by comparing it to three existing image processing techniques. The results of this evaluation, using the coefficient of determination (R2) and mean absolute error (MAE) values, demonstrated the superior performance of the LaMa algorithm. It consistently achieved R2 values of 0.9 or higher and kept MAE values under 0.5 ℃ or less. This outperformed the traditional methods, including bilinear interpolation, bicubic interpolation, and DeepFill v1 techniques. We plan to evaluate the feasibility of integrating the LaMa technique into an operational satellite data provision system.

A Study on the Restoration of the Language of the Time for a Historical Drama (역사극 공연을 위한 시대언어 복원의 의미 연구)

  • Pyo, Won-Soub;Park, Yoon-Hee
    • Journal of Korea Entertainment Industry Association
    • /
    • v.13 no.2
    • /
    • pp.133-143
    • /
    • 2019
  • When writing historical dramas, there was an argument that restoring the language of the times was the responsibility of the playwright, but no full-scale research was done. There was no collaborative study between playwrights and Korean Language scholars. So far, many playwrights have considered it the responsibility of Korean Language scholars to discover and restore language. However, it is a medium that can easily meet the public like a play or movie, and it should have a great responsibility for creation. Language changes with time, so restoring the language of the time in plays and scenarios can lead to difficulties in communicating with modern audiences. However, the change of language according to the times means that it captures the social image and fashion of the time Therefore, language restoration in historical dream means that scenes and backgrounds can be described more realistically. Restore of language is not just necessary to improve the creative environment; it should be understood as the responsibility of the artist to meet the ability of the audience to understand the language of the times already learned. The playwright who writes the historical drama should not only learn the grammar of the background era, but also find out the lost pronunciation and the changed vocabulary so that he can use various dialogues.