แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Luqman Ali. Performance evaluation of different inpainting techniques and detection of inpainting in remotely sensed images using neural networks. Master's Degree(Information and Communication Technology for Embedded System). Kasetsart University. Office of the University Library. : Kasetsart University, 2017.
Performance evaluation of different inpainting techniques and detection of inpainting in remotely sensed images using neural networks
Name: Luqman Ali
Classification :.DDC: TA1637
LCSH:
Image processing
LCSH:
Remote sensing
LCSH:
Inpainting
Abstract:
Image inpainting refers to a technique in which missing areas of an image are filled in such a way that the resulting images appears plausible to the human eye by retrieving information from the surrounding pixels. Degradation in remote sensing images is usually caused by dead pixels, noise, clouds, sensor problem or communication system problem. Image inpainting filled the missed parts of the satellite images in such a way that the images appear not only plausible to human eye but also authenticated to machinery. The inpainting can be considered as a part of satellite image forgery in which fake satellite image is generated by the creation and alternation of new image contents. Hence a well-designed inpainting algorithm is similar to a sophisticated forgery technique, i.e., it is hard to detect by human and machine. With enough training it is possible to authenticate every image but it is difficult to force image distributor to provide images that embedded authentications. The aim of this research is to evaluate the performance of different inpainting algorithms for remote sensing images. Satellite Images are tested on different inpainting algorithms and efficiency of each algorithm is evaluated on the basis of processing time, Root mean square error and peak signal to noise ratio. This research also proposes an algorithm for the identification of inpainted remote sensing images. The proposed algorithm is the connection of two major processes: feature extraction followed by use of classifiers based on k-nearest neighbors algorithm (KNN) and evolutionary artificial neural networks algorithm (EANN) separately. The proposed algorithm can efficiently identify whether a satellite image is inpainted or not. The experimental results reveal that the proposed method has better performance with faster speed for various kinds of satellite inpainting images.
Kasetsart University. Office of the University Library
Address:
Bangkok
Email:
tdckulib@ku.ac.th
Name: Teerasit Kasetkasem
Role:
Thesis Advisor
Name: Thitiporn Chanwimaluang
Role:
Thesis Co-Advisor
Created:
2017
Modified:
2023-05-31
Issued:
2023-05-31
วิทยานิพนธ์/Thesis
application/pdf
URL: https://kasetsart.idm.oclc.org/login?url=https://www.lib.ku.ac.th/KUthesis/2560/luqman-ali-all.pdf
CallNumber:
TA1637.A45
eng
DegreeName: Master of Engineering
Level: Master's Degree
Grantor: Kasetsart University
©copyrights Kasetsart University
RightsAccess:
ใช้เวลา
0.034915 วินาที
Luqman Ali
| Title | Contributor | Type |
|---|---|---|
| Performance evaluation of different inpainting techniques and detection of inpainting in remotely sensed images using neural networks
มหาวิทยาลัยเกษตรศาสตร์ Luqman Ali | Teerasit Kasetkasem Thitiporn Chanwimaluang | วิทยานิพนธ์/Thesis |
Teerasit Kasetkasem
Thitiporn Chanwimaluang
| Title | Creator | Type and Date Create |
|---|---|---|
| Planar surface area calculation using camera and orientation sensor
มหาวิทยาลัยเกษตรศาสตร์ Miti Ruchanurucks;Supakorn Siddhichai;Sato, Makoto;Thitiporn Chanwimaluang | Surangrak Sutiworwan | วิทยานิพนธ์/Thesis |
| Rice phenology estimation using SAR time-series data
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Thitiporn Chanwimaluang;Preesan Rakwatin | Napat Cota | วิทยานิพนธ์/Thesis |
| SAR speckle removal using multitemporal speckle filtering and segmentation
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem ;Thitiporn Chanwimaluang ;Preesan Rakwatin | Poompat Rattanasuwan | วิทยานิพนธ์/Thesis |
| Urban mapping using NPP-VIIRS nighttime light data and SAR data
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem ;Thitiporn Chanwimaluang ;Preesan Rakwatin | Raveerat Jaturapitpornchai | วิทยานิพนธ์/Thesis |
| Land cover mapping classification based on deep-learning
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Thitiporn Chanwimaluang;Itsuo Kumazawa;Preesan Rakwatin | Apiwat Lekfuangfu | วิทยานิพนธ์/Thesis |
| Land cover mapping using a random forest classification
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Thitiporn Chanwimaluang;Itsuo Kumazawa;Preesan Rakwatin | Panyanat Aonpong | วิทยานิพนธ์/Thesis |
| Thaichote images natural color correction
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Thitiporn Chanwimaluang;Akinori Nishihara | Wilawun Punmanee | วิทยานิพนธ์/Thesis |
| Performance evaluation of different inpainting techniques and detection of inpainting in remotely sensed images using neural networks
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem ;Thitiporn Chanwimaluang | Luqman Ali | วิทยานิพนธ์/Thesis |
| A super-resolution land cover mapping based on a random forest and markov random field model
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Thitiporn Chanwimaluang;Tsuyoshi Isshiki;Preesan Rakwatin | Manatsawee Sanpayao | วิทยานิพนธ์/Thesis |
| Remote sensing image classification using deep convolutional
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem ;Thitiporn Chanwimaluang;Itsuo Kumazawa;Preesan Rakwatin | Watsana Bupphawat | วิทยานิพนธ์/Thesis |
| Pipeline direction extraction algorithm using level set method
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Yodyium Tipsuwan;Tsuyoshi Isshiki;Thitiporn Chanwimaluang | Apinya Leangaramkul | วิทยานิพนธ์/Thesis |
| A cloud detection and removal algorithm for optical satellite images
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem ;Thitiporn Chanwimaluang | Duangkamol Tedlek | วิทยานิพนธ์/Thesis |
| A multi-temporal convolutional autoencoder neural network for cloud removal in remote sensing images
มหาวิทยาลัยเกษตรศาสตร์ Teerasit Kasetkasem;Thitiporn Chanwimaluang | Wassana Sintarasirikulchai | วิทยานิพนธ์/Thesis |