• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.655-658
• /
• 2021

The purpose of multimodal medical image fusion (MMIF) is to integrate images of different modes with different details into a result image with rich information, which is convenient for doctors to accurately diagnose and treat the diseased tissues of patients. Encouraged by this purpose, this paper proposes a novel method based on a two-scale decomposer and detail preservation model. The first step is to use the two-scale decomposer to decompose the source image into the energy layers and structure layers, which have the characteristic of detail preservation. And then, structure tensor operator and max-abs are combined to fuse the structure layers. The detail preservation model is proposed for the fusion of the energy layers, which greatly improves the image performance. The fused image is achieved by summing up the two fused sub-images obtained by the above fusion rules. Experiments demonstrate that the proposed method has superior performance compared with the state-of-the-art fusion methods.

• Korean Journal of Radiology
• /
• v.24 no.4
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• Journal of Korea Multimedia Society
• /
• v.18 no.8
• /
• pp.901-908
• /
• 2015

Methods of detecting, describing, matching image features, like corners and blobs, have been actively studied as a fundamental step for image processing and computer vision applications. As one of feature description/matching methods, LLAH(Locally Likely Arrangement Hashing) describes image features based on the geometric relationship between their neighbors, and thus is suitable for scenes with poor texture. This paper presents a modified LLAH algorithm, which includes the image features themselves for robustly describing the geometric relationship unlike the original LLAH, and employes a voting-based feature matching scheme that makes feature description much simpler. Then, this paper quantitatively analyzes its performance with synthetic images in the presence of Gaussian noise.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.421-424
• /
• 2022

Hough transform is a representative algorithm for detecting straight lines in an edge image. It corresponds the parameters of straight lines that may occur in the edge pixel into a parameter space, and detects valid parameters satisfying a given condition as straight lines. In general Hough transform, the parameters of the line are calculated with the image origin as the reference point. However, in this paper, the Hough transform based on the image center as a reference point is performed and its performance is compared and analyzed with the conventional Hough transform.

• Current Optics and Photonics
• /
• v.1 no.4
• /
• pp.336-343
• /
• 2017

A wide field-of-view (FOV) image contains more visual information than a conventional image. This study proposes a new type of hyperbolic mirror for wide FOV image acquisition. The proposed mirror consists of a hyperbolic cylindrical section and a bowl-shaped hyperbolic omnidirectional section. Using an imaging system with this mirror, it is possible to achieve a $213.8^{\circ}$ horizontal and a $126.94^{\circ}$ vertical maximum FOV. Parameters of each section of the mirror are designed to be continuous at the junction of the two parts, and the resultant image is seamless. The image-acquisition model is obtained using ray-tracing optics. To rectify the geometrical distortion of the original image due to the mirror, an image-restoration algorithm based on conformal projection is presented in this study. The performance of the proposed imaging system with the hyperbolic mirror and its image-restoration algorithm are verified by experiments.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1417-1424
• /
• 2018

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.260-270
• /
• 2023

We introduce a novel Visual Inertial Odometry (VIO) algorithm designed to improve the performance of thermal-inertial odometry. Thermal infrared image, though advantageous for feature extraction in low-light conditions, typically suffers from a high noise level and significant information loss during the 8-bit conversion. Our algorithm overcomes these limitations by approximating a 14-bit raw pixel histogram into a Gaussian mixture model. The conversion method effectively emphasizes image regions where texture for visual tracking is abundant while reduces unnecessary background information. We incorporate the robust learning-based feature extraction and matching methods, SuperPoint and SuperGlue, and zero velocity detection module to further reduce the uncertainty of visual odometry. Tested across various datasets, the proposed algorithm shows improved performance compared to other state-of-the-art VIO algorithms, paving the way for robust thermal-inertial odometry.

• Health Policy and Management
• /
• v.24 no.2
• /
• pp.153-163
• /
• 2014

Background: This study aims to explore the effects of quality of care, image, and role performance perceived by community residents on medical service satisfaction to public hospitals. Methods: The subjects of this study were selected in the community residents around 39 district public hospitals. The questionnaire were included 4 factors and 16 items. The data were collected utilizing call-interview by a survey company. Results: The community satisfaction was positively correlated with quality of care, image, and role performance of public hospitals (p<0.001). As the results of multiple logistic regression, the significant variables of community satisfaction were quality of care (odds ratio [OR], 1.353; 95% confidence interval [CI], 1.211 to 1.511), image (OR, 1.487; 95% CI, 1.280 to 1.727), role performance (OR, 1.240; 95% CI, 1.085 to 1.416) among subjects having use experience of public hospitals. The significant variables of community satisfaction were quality of care (OR, 1.240; 95% CI, 1.175 to 1.309), image (OR, 1.328; 95% CI, 1.232 to 1.432), age (OR, 3.051; 95% CI, 1.385 to 6.724), monthly incomes (OR, 0.420; 95% CI, 0.198 to 0.892) among subjects not-having use experience of public hospitals. Conclusion: Public hospitals have to effort to improve image and satisfaction of community through providing quality of care, and role performance. It is possible to support them by the central and local government.

• Fashion & Textile Research Journal
• /
• v.12 no.6
• /
• pp.843-850
• /
• 2010

To evaluate the heating performance of commercial heated vests, we investigated the thermal images and the temperature between body and vest for three heated vests. We captured infrared thermography by FT-IR Spectrometer to analyzed the heating temperature of the heating elements taken from the vests, and the maximum heating temperature of the vests was compared with thermal image in the room temperature($18^{\circ}C$). In outdoor experiment($-4.7^{\circ}C$), we measured the inner temperature as well as the thermal image of heated vests. Four healthy men participated in this experiment, and the ANOVA and Duncan test was performed for statistical analysis. As the results, the heating temperature range of the heated vests used in this experiment was $32{\sim}42^{\circ}C$, much lower than the displayed temperature range in their specifications, so the exact specification for heating performance of heated clothing was required. In comparisons of the heating performance among the heated vests, we found out that the insulation of clothing is very important to design the heated clothing, because the inner temperature of the vest had good insulation by itself was higher than that of the vest shown higher temperature over $7^{\circ}$ than another vests at the heating temperature.

• Journal of Radiation Protection and Research
• /
• v.41 no.2
• /
• pp.111-115
• /
• 2016

Background: The scattered photons cause reduction of the contrast of radiographic image and it results in the degradation of the quality of the image. In order to acquire better quality image, an anti-scattering x-ray gird should be equipped in radiography system. Materials and Methods: The X-ray anti-scattering grid of the inclined type based on the hybrid concept for that of parallel and focused type was tested by MCNP code. The MCNPX 2.7.0 was used for the simulation based test. The geometry for the test was based on the IEC 60627 which was an international standard for diagnostic X-ray imaging equipment-Characteristics of general purpose and mammographic anti-scatter grids. Results and Discussion: The performance of grids with four inclined shielding material types was compared with that of the parallel type. The grid with completely tapered type the best performance where there were little performance difference according to the degree of inclination. Conclusion: It was shown that the grid of inclined type had better performance than that of parallel one.