• Journal of radiological science and technology
• /
• v.45 no.5
• /
• pp.397-405
• /
• 2022

Computed radiography (CR) systems, which convert an analog signal recorded on a cassette into a digital image, combine the characteristics of analog and digital imaging systems. Compared to digital radiography (DR) systems, CR systems have presented difficulties in evaluating system performance because of their lower detective quantum efficiency, their lower signal-to-noise ratio (SNR), and lower modulation transfer function (MTF). During the step of energy-storing and reading out, a baseline offset occurs in the edge area and makes low-frequency overestimation. The low-frequency offset component in the line spread function (LSF) critically affects the MTF and other image-analysis or qualification processes. In this study, we developed the method of baseline correction using mathematical morphology to determine the LSF and MTF of CR systems accurately. We presented a baseline correction that used a morphological filter to effectively remove the low-frequency offset from the LSF. We also tried an MTF evaluation of the CR system to demonstrate the effectiveness of the baseline correction. The MTF with a 3-pixel structuring element (SE) fluctuated since it overestimated the low-frequency component. This overestimation led the algorithm to over-compensate in the low-frequency region so that high-frequency components appeared relatively strong. The MTFs with between 11- and 15-pixel SEs showed little variation. Compared to spatial or frequency filtering that eliminated baseline effects in the edge spread function, our algorithm performed better at precisely locating the edge position and the averaged LSF was narrower.

• Economic and Environmental Geology
• /
• v.55 no.5
• /
• pp.551-561
• /
• 2022

Geophysical exploration methods are very useful for generating high-resolution images of underground structures, and such methods can be applied to investigation of buried cultural properties and for determining their exact locations. In this study, image feature extraction and image segmentation methods were applied to automatically distinguish the structures of buried relics from the high-resolution ground-penetrating radar (GPR) images obtained at the center of Silla Kingdom, Gyeongju, South Korea. The major purpose for image feature extraction analyses is identifying the circular features from building remains and the linear features from ancient roads and fences. Feature extraction is implemented by applying the Canny edge detection and Hough transform algorithms. We applied the Hough transforms to the edge image resulted from the Canny algorithm in order to determine the locations the target features. However, the Hough transform requires different parameter settings for each survey sector. As for image segmentation, we applied the connected element labeling algorithm and object-based image analysis using Orfeo Toolbox (OTB) in QGIS. The connected components labeled image shows the signals associated with the target buried relics are effectively connected and labeled. However, we often find multiple labels are assigned to a single structure on the given GPR data. Object-based image analysis was conducted by using a Large-Scale Mean-Shift (LSMS) image segmentation. In this analysis, a vector layer containing pixel values for each segmented polygon was estimated first and then used to build a train-validation dataset by assigning the polygons to one class associated with the buried relics and another class for the background field. With the Random Forest Classifier, we find that the polygons on the LSMS image segmentation layer can be successfully classified into the polygons of the buried relics and those of the background. Thus, we propose that these automatic classification methods applied to the GPR images of buried cultural heritage in this study can be useful to obtain consistent analyses results for planning excavation processes.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.127-132
• /
• 2011

In this paper, we propose a novel method of adult image classification by combining skin color regions and edges in an input image. The proposed method consists of four steps. In the first step, initial skin color regions are detected by logical AND operation of all skin color regions detected by the existing methods of skin color detection. In the second step, a skin color probability map is created by modeling the distribution of skin color in the initial regions. Then, a binary image is generated by using threshold value from the skin color probability map. In the third step, after using the binary image and edge information, we detect final skin color regions using a region growing method. In the final step, adult image classification is performed by support vector machine(SVM). To this end, a feature vector is extracted by combining the final skin color regions and neighboring edges of them. As experimental results, the proposed method improves performance of the adult image classification by 9.6%, compared to the existing method.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.9
• /
• pp.91-102
• /
• 1999

It is known that the digital image enlargement technique which only uses spatially neighbored pixels information in a still image can increase the size of the image but the practical enhancement of resolution is small because the frequency bandwidth of the image is basically limited. To solve this problem, this paper proposes the digital image enlargement technique that improves the reconstruction of the edge components by selectively transposing the direction of the subwindows of pseudomedian filter according to the distribution of neighbored pixels to the interpolation point. The pseudomedian filter has the better performance in aspect of the reconstruction of edge information when the pixel values masked by two subwindows parallel to the interpolation point are very similar and the pixel values masked by another subwindow that is orthogonal to the above two subwindows are similar to each other. In this paper, the computer simulation for digital image enlargement was performed with consideration of these characteristics when selecting the subwindows of pseudomedina filter. Based on this simulation result, the performance of the proposed method was analysed and its effectiveness was assessed. According to the proposed method, visual artifacts that result from using the limited samples can be effectively suppressed, and most characteristics and shapes of the original image can be preserved as well.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.4
• /
• pp.82-92
• /
• 2006

In the field of image recognition, research on face recognition has recently attracted a lot of attention. The most important step in face recognition is automatic eye detection researched as a prerequisite stage. Existing eye detection methods for focusing on the frontal face can be mainly classified into two categories: active infrared(IR)-based approaches and image-based approaches. This paper proposes an eye region detection method in non-frontal faces. The proposed method is based on the edge--based method that shows the fastest computation time. To extract eye region in non-frontal faces, the method uses edge orientationhistogram of the global region of faces. The problem caused by some noise and unfavorable ambient light is solved by using proportion of width and height for local information and relationship between components for global information in approximately extracted region. In experimental results, the proposed method improved precision rates, as solving 3 problems caused by edge information and achieves a detection accuracy of 83.5% and a computational time of 0.5sec per face image using 300 face images provided by The Weizmann Institute of Science.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.11 s.353
• /
• pp.26-36
• /
• 2006

In this paper, we propose a cost-effective color filter may (CFA) demosaicing method for digital still cameras in which a single CCD or CMOS image sensor is used. Since a CFA is adopted, we must interpolate missing color values in the red, green and blue channels at each pixel location. While most state-of-the-art algorithms invest a great deal of computational effort in the enhancement of the reconstructed image to overcome the color artifacts, we focus on eliminating the color artifacts with low computational complexity. Using spatial correlation of the adjacent pixels, the edge-directional information of the neighbor pixels is used for determining the edge direction of the current pixel. We apply our method to the state-of-the-art algorithms which use edge-directed methods to interpolate the missing color channels. The experiment results show that the proposed method enhances the demosaiced image qualify from $0.09{\sim}0.47dB$ in PSNR depending on the basis algorithm by removing most of the color artifacts. The proposed method was implemented and verified successfully using verilog HDL and FPGA. It was synthesized to gate-level circuits using 0.25um CMOS standard cell library. The total logic gate count is 12K, and five line memories are used.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.103-113
• /
• 2019

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2003.09a
• /
• pp.67-67
• /
• 2003

It is crucial to minimize setup errors of a cancer treatment machine using a high energy and to perform precise radiation therapy. Usually, port film has been used for verifying errors. The Korea Cancer Center Hospital (KCCH) has manufactured digital electronic portal imaging device (EPID) system to verify treatment machine errors as a Quality Assurance (Q.A) tool. This EPID was consisted of a metal/fluorescent screen, 45$^{\circ}$ mirror, a camera and an image grabber and could display the portal image with near real time KIRAMS has also made the acrylic phantom that has lead line of 1mm width for ligh/radiation field congruence verification and reference points phantom for using as an isocenter on portal image. We acquired portal images of 10$\times$10cm field size with this phantom by EPID and portal film rotating treatment head by 0.3$^{\circ}$, 0.6$^{\circ}$ and 0.9$^{\circ}$. To check field size, we acquired portal images with 18$\times$18cm, 19$\times$19cm and 20$\times$20cm field size with collimator angle 0$^{\circ}$ and 0.5$^{\circ}$ individually. We have performed Flatness comparison by displaying the line intensity from EPID and film images. The 0.6$^{\circ}$ shift of collimator angle was easily observed by edge detection of irradiated field size on EPID image. To the extent of one pixel (0.76mm) difference could be detected. We also have measured field size by finding optimal threshold value, finding isocenter, finding field edge and gauging distance between isocenter and edge. This EPID system could be used as a Q.A tool for checking field size, light/radiation congruence and flatness with a developed video based EPID.

• Journal of KIISE:Databases
• /
• v.36 no.2
• /
• pp.73-83
• /
• 2009

In this paper we propose an object similarity matching method based on shape characteristics of an object in an image. The proposed method extracts edge points from edges of objects and generates a log polar histogram with respect to each edge point to represent the relative placement of extracted points. It performs the matching in such a way that it compares polar histograms of two edge points sequentially along with edges of objects, and uses a well-known k-NN(nearest neighbor) approach to retrieve similar objects from a database. To verify the proposed method, we've compared it to an existing Shape-Context method. Experimental results reveal that our method is more accurate in object matching than the existing method, showing that when k=5, the precision of our method is 0.75-0.90 while that of the existing one is 0.37, and when k=10, the precision of our method is 0.61-0.80 while that of the existing one is 0.31. In the experiment of rotational transformation, our method is also more robust compared to the existing one, showing that the precision of our method is 0.69 while that of the existing one is 0.30.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1850-1857
• /
• 2021

Objective: The purpose of this study was to assess whether a deep learning (DL) algorithm could enable simultaneous noise reduction and edge sharpening in low-dose lumbar spine CT. Materials and Methods: This retrospective study included 52 patients (26 male and 26 female; median age, 60.5 years) who had undergone CT-guided lumbar bone biopsy between October 2015 and April 2020. Initial 100-mAs survey images and 50-mAs intraprocedural images were reconstructed by filtered back projection. Denoising was performed using a vendor-agnostic DL model (ClariCT.AI^TM, ClariPI) for the 50-mAS images, and the 50-mAs, denoised 50-mAs, and 100-mAs CT images were compared. Noise, signal-to-noise ratio (SNR), and edge rise distance (ERD) for image sharpness were measured. The data were summarized as the mean ± standard deviation for these parameters. Two musculoskeletal radiologists assessed the visibility of the normal anatomical structures. Results: Noise was lower in the denoised 50-mAs images (36.38 ± 7.03 Hounsfield unit [HU]) than the 50-mAs (93.33 ± 25.36 HU) and 100-mAs (63.33 ± 16.09 HU) images (p < 0.001). The SNRs for the images in descending order were as follows: denoised 50-mAs (1.46 ± 0.54), 100-mAs (0.99 ± 0.34), and 50-mAs (0.58 ± 0.18) images (p < 0.001). The denoised 50-mAs images had better edge sharpness than the 100-mAs images at the vertebral body (ERD; 0.94 ± 0.2 mm vs. 1.05 ± 0.24 mm, p = 0.036) and the psoas (ERD; 0.42 ± 0.09 mm vs. 0.50 ± 0.12 mm, p = 0.002). The denoised 50-mAs images significantly improved the visualization of the normal anatomical structures (p < 0.001). Conclusion: DL-based reconstruction may enable simultaneous noise reduction and improvement in image quality with the preservation of edge sharpness on low-dose lumbar spine CT. Investigations on further radiation dose reduction and the clinical applicability of this technique are warranted.