• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.5
• /
• pp.64-74
• /
• 2019

Although a non-rigid registration has high demands in clinical practice, it has a high computational complexity and it is very difficult for ensuring the accuracy and robustness of registration. This study proposes a method of applying a non-rigid registration to 3D magnetic resonance images of brain in an unsupervised learning environment by using a deep-learning network. A feature vector between two images is produced through the network by receiving both images from two different patients as inputs and it transforms the target image to match the source image by creating a displacement vector field. The network is designed based on a U-Net shape so that feature vectors that consider all global and local differences between two images can be constructed when performing the registration. As a regularization term is added to a loss function, a transformation result similar to that of a real brain movement can be obtained after the application of trilinear interpolation. This method enables a non-rigid registration with a single-pass deformation by only receiving two arbitrary images as inputs through an unsupervised learning. Therefore, it can perform faster than other non-learning-based registration methods that require iterative optimization processes. Our experiment was performed with 3D magnetic resonance images of 50 human brains, and the measurement result of the dice similarity coefficient confirmed an approximately 16% similarity improvement by using our method after the registration. It also showed a similar performance compared with the non-learning-based method, with about 10,000 times speed increase. The proposed method can be used for non-rigid registration of various kinds of medical image data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.6C
• /
• pp.349-354
• /
• 2011

Passive millimeter wave imaging has the capability of detecting concealed objects under clothing. Also, passive millimeter imaging can obtain interpretable images under low visibility conditions like rain, fog, smoke, and dust. However, the image quality is often degraded due to low spatial resolution, low signal level, and low temperature resolution. This paper addresses image registration and fusion between passive millimeter images and visual images. The goal of this study is to combine and visualize two different types of information together: human subject's identity and concealed objects. The image registration process is composed of body boundary detection and an affine transform maximizing cross-correlation coefficients of two edge images. The image fusion process comprises three stages: discrete wavelet transform for image decomposition, a fusion rule for merging the coefficients, and the inverse transform for image synthesis. In the experiments, various types of metallic and non-metallic objects such as a knife, gel or liquid type beauty aids and a phone are detected by passive millimeter wave imaging. The registration and fusion process can visualize the meaningful information from two different types of sensors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1785-1791
• /
• 2003

This paper presents the mosaic method that the video sequence with shift and rotation information after Mellin Transform. The results are used to compute the projection matrix for each image registration. So before registration, we process camera calibration in order to reduce the image warp by camera and then compute the global projection matrix for image registration for reducing errors from rut image to last image. This paper describes the mosaic method that compute duplication and movement information quickly and robust noise using projection matrix on Mellin Transform.

• Journal of Astronomy and Space Sciences
• /
• v.24 no.3
• /
• pp.235-248
• /
• 2007

We developed a software for simulations and analyses of the Image Navigation and Registration (INR) system, and compares the characteristics of Image Motion Compensation (IMC) algorithms for the INR system. According to the orbit errors and attitude errors, the capabilities of the image distortions are analyzed. The distortions of images can be compensated by GOES IMC algorithm and Modified IMC (MIMC) algorithm. The capabilities of each IMC algorithm are confirmed based on compensated images. The MIMC yields better results than GOES IMC although both the algorithms well compensate distorted images. The results of this research can be used as valuable asset to design of INR system for the Communication, Ocean, Meteorological Satellite (COMS).

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.238-244
• /
• 2021

Image mosaicking is a common and useful technique to visualize a global map by stitching a large number of local images obtained from visual surveys in underwater environments. In particular, visual inspection of underwater structures using underwater robots can be a potential application for image mosaicking. Feature-based pairwise image registration is a commonly employed process in most image mosaicking algorithms to estimate visual odometry information between compared images. However, visual features are not always uniformly distributed on the surface of underwater structures, and thus the performance of image registration can vary significantly, which results in unnecessary computations in image matching for poor-conditioned image pairs. This study proposes a pairwise registrability measure to select informative image pairs and to improve the overall computational efficiency of underwater image mosaicking algorithms. The validity and effectiveness of the image mosaicking algorithm considering the pairwise registrability are demonstrated using an experimental dataset obtained with a full-scale ship in a real sea environment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.481-489
• /
• 2019

Change detection, one of the main applications of multi-temporal satellite images, is an indicator that directly reflects changes in human activity. Change detection can be divided into pixel-based change detection and object-based change detection. Although pixel-based change detection is traditional method which is mostly used because of its simple algorithms and relatively easy quantitative analysis, applying this method in VHR (Very High Resolution) images cause misdetection or noise. Because of this, pixel-based change detection is less utilized in VHR images. In addition, the sensor of acquisition or geographical characteristics bring registration noise even if co-registration is conducted. Registration noise is a barrier that reduces accuracy when extracting spatial information for utilizing VHR images. In this study object-based change detection of VHR images was performed considering registration noise. In this case, object-based change detection results were derived considering various pixel-based change detection methods, and the major voting technique was applied in the process with segmentation image. The final object-based change detection result applied by the proposed method was compared its performance with other results through reference data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.1
• /
• pp.21-30
• /
• 2012

When two bands have different look angle in a space-borne camera system, the registration between two bands is required. The registration cannot be modeled with constant parameters because of dynamic of platform and parallax effect. The parallax effect is caused by terrain relief, hence it causes local distortion between two bands. Therefore, the terrain relief correction in order to reduce the parallax effect is required for better registration result, especially for high resolution image data. Such terrain relief correction also can be applied to image data acquired from multiple detectors with different look angle within a band, which is a one of commonly used configuration for a wider swath in space-borne camera system, in order to reduce the distortion between detectors. The RFM is a popular abstract model in remote sensing field, which gives us the relationship between the image plane and geodetic coordinate system. Therefore, we propose a terrain relief correction method based on the RFM. The experiment showed very promising result.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1143-1153
• /
• 2018

For TOPS InSAR processing, high-precision image co-registration is required. We propose an image co-registration method suitable for the TOPS mode by comparing the performance of cross correlation method, the geometric co-registration and the enhanced spectral diversity (ESD) matching algorithm based on the spectral diversity (SD) on the Sentinel-1 TOPS mode image. Using 23 pairs of interferometric pairs generated from 25 Sentinel-1 TOPS images, we applied the cross correlation (CC), geometric correction with only orbit information (GC1), geometric correction combined with iterative cross-correlation (GC2, GC3, GC4), and ESD iteration (ESD_GC, ESD_1, ESD_2). The mean of co-registration errors in azimuth direction by cross correlation and geometric matching are 0.0041 pixels and 0.0016 pixels, respectively. Although the ESD method shows the most accurate result with the error of less than 0.0005 pixels, the error of geometric co-registration is reduced to 0.001 pixels by repetition through additional cross correlation matching between the reference and resampled slave image. The ESD method is not applicable when the coherence of the burst overlap areas is low. Therefore, the geometric co-registration method through iterative processing is a suitable alternative for time series analysis using multiple SAR data or generating interferogram with long time intervals.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.39 no.4
• /
• pp.197-199
• /
• 2013

Three-dimensional (3D) computed tomography image models are helpful in reproducing the maxillofacial area; however, they do not necessarily provide an accurate representation of dental occlusion and the state of the teeth. Recent efforts have focused on improvement of dental imaging by replacement of computed tomography with other detailed digital images. Unfortunately, despite the advantages of medical simulation software in dentofacial analysis, diagnosis, and surgical simulation, it lacks adequate registration tools. Following up on our previous report on orthognathic simulation surgery using computer-aided design/computer-aided manufacturing (CAD/CAM) software, we recently used the registration functions of a CAD/CAM platform in conjunction with surgical simulation software. Therefore, we would like to introduce a new technique, which involves use of the registration functions of CAD/CAM software followed by transfer of the images into medical simulation software. This technique may be applicable when using various registration function tools from different software platforms.

• The Journal of Korean Society for Radiation Therapy
• /
• v.29 no.2
• /
• pp.119-128
• /
• 2017

Purpose: The purpose of this study was to measure the average actual treatment time at the time of Tomotherapy treatment. We want to investigate the time required for the procedure in the treatment process that affects the actual treatment time. Patients and Methods: We measured the time required by the procedure in 31 patients who were treated with tomography therapy. Beam-on time, Image registration time, Set-up with scan time and Actual treatment time were measured and stepwise regression analysis was performed. Result: The average treatment time per a patient was 21.44 - 23.92 minutes. Beam-on time, Image registration time, and Set-up with Scan time were the important factors affecting the actual treatment time. The biggest influence was Beam-on time and Registration time was less affected by analysing. Conclusion: The average treatment time per a patient in tomotherapy treatment was $22.68{\pm}3.37$ minutes. The Approximately 21 patients are expected to be treated within 8 hours of regular work time. However, if the treatment is interrupted or the time of the procedure is changed during the treatment process, it affects the schedule of the daily treatment patients and the workload is expected to increase.