• Nuclear Engineering and Technology
• /
• v.38 no.4
• /
• pp.383-390
• /
• 2006

Having its roots in medical applications, industrial gamma ray CT has opened up new roads far investigating and modeling industrial processes. Using a line of research related to industrial gamma ray CT, the authors set up a system of single source and detector gamma transmission tomography for wood timber and a packed bed phantom. The hardware of the CT system consists of two servo motors, a data logger, a computer, a radiation source and a radiation detector. One motor simultaneously moves the source and the detector for a parallel beam scanning, whereas the other motor rotates the scan table at a preset projection angle. The image is reconstructed from the measured projections by the filtered back projection method. The phantom was designed to simulate a cross section of a packed bed with a void. The radiation source was 20mCi of Cs-137 and the detector was a 1 inch $\times$ 1 inch NaI (TI) scintillator shielded by a lead collimator. The experimental gamma ray CT image has sufficient resolution to reveal air holes and the density distribution inside the phantom. The system could possibly be applied to a packed bed column or a pipe flow in a petrochemical plant.

• Journal of the Optical Society of Korea
• /
• v.17 no.5
• /
• pp.384-391
• /
• 2013

We propose a split-encryption scheme on converting original images to multiple ciphertexts. This conversion introduces one random phase-only function (POF) to influence phase distribution of the preliminary ciphertexts. In the encryption process, the original image is mathematically split into two POFs. Then, they are modulated on a spatial light modulator one after another. And subsequently two final ciphertexts are generated by utilizing two-step phase-shifting interferometry. In the decryption process, a high-quality reconstructed image with relative error $RE=7.6061{\times}10^{-31}$ can be achieved only when the summation of the two ciphertexts is Fresnel-transformed to the reconstructed plane. During the verification process, any silhouette information was invisible in the two reconstructed images from different single ciphertexts. Both of the two single REs are more than 0.6, which is better than in previous research. Moreover, this proposed scheme works well with gray images.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.5
• /
• pp.389-395
• /
• 2019

Unlike aerial images covering small region, satellite data show high potential to detect urban scale geospatial changes. The change detection using satellite images can be carried out using single image or stereo images. The single image approach is based on radiometric differences between two images of different times. It has limitations to detect building level changes when the significant occlusion and relief displacement appear in the images. In contrast, stereo satellite data can be used to generate DSM (Digital Surface Model) that contain information of relief-corrected objects. Therefore, they have high potential for the object change detection. Therefore, we carried out a study for the change detection over an urban area using stereo satellite data of two different times. First, the RPC correction was performed for two DSMs generation via stereo image matching. Then, D-DSM (Differential DSM) was generated by differentiating two DSMs. The D-DSM was used for the topographic change detection and the performance was checked by applying different height thresholds to D-DSM.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.215-218
• /
• 2009

In this paper, we analyze the performance of interpolation in demosaicing techniques for single sensor digital camera. We choose BI(bilinear interpolation), ACPI(adaptive color plane interpolation), ECI(effective color interpolation), Ideal ACPI, and EECI(Enhanced effective color interpolation) in the literature of demosacing techniques since they provide low-complexity and substantial image quality. We survey the algorithms and simulate them. To evaluate the methods in terms of objective image quality and complexity, 24 Kodak images will be used in this experiment. Experimental results show that the ECI method is better than others in terms of image quality versus complexity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1166-1186
• /
• 2022

Artistic font design has become an integral part of visual media. However, without prior knowledge of the font domain, it is difficult to create distinct font styles. When the number of characters is limited, this task becomes easier (e.g., only Latin characters). However, designing CJK (Chinese, Japanese, and Korean) characters presents a challenge due to the large number of character sets and complexity of the glyph components in these languages. Numerous studies have been conducted on automating the font design process using generative adversarial networks (GANs). Existing methods rely heavily on reference fonts and perform font style conversions between different fonts. Additionally, rather than capturing style information for a target font via multiple style images, most methods do so via a single font image. In this paper, we propose a network architecture for generating multilingual font sets that makes use of geometric structures as content. Additionally, to acquire sufficient style information, we employ multiple style images belonging to a single font style simultaneously to extract global font style-specific information. By utilizing the geometric structural information of content and a few stylized images, our model can generate an entire font set while maintaining the style. Extensive experiments were conducted to demonstrate the proposed model's superiority over several baseline methods. Additionally, we conducted ablation studies to validate our proposed network architecture.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1527-1532
• /
• 2023

The noise reduction algorithm using the non-local means (NLM) approach is very efficient in nuclear medicine imaging. In this study, the applicability of the NLM noise reduction algorithm in single-photon emission computed tomography (SPECT) images with a brain phantom and the optimization of the NLM algorithm by changing the smoothing factors according to various reconstruction methods are investigated. Brain phantom images were reconstructed using filtered back projection (FBP) and ordered subset expectation maximization (OSEM). The smoothing factor of the NLM noise reduction algorithm determined the optimal coefficient of variation (COV) and contrast-to-noise ratio (CNR) results at a value of 0.020 in the FBP and OSEM reconstruction methods. We confirmed that the FBP- and OSEM-based SPECT images using the algorithm applied with the optimal smoothing factor improved the COV and CNR by 66.94% and 8.00% on average, respectively, compared to those of the original image. In conclusion, an optimized smoothing factor was derived from the NLM approach-based algorithm in brain SPECT images and may be applicable to various nuclear medicine imaging techniques in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.553-555
• /
• 2022

This paper is about a real-time automatic face recognition system based on one-shot panoramic scanning. It detects multiple faces in real time through a single panoramic scanning process and recognizes pre-registered faces. Instead of recognizing multiple faces within a single panoramic image, multiple faces are recognized using multiple images obtained in the scanning process. This reduces the panorama image creation time and stitching error, and at the same time can improve the face recognition performance by using the accumulated information of multiple images. It is expected that it can be used in various applications such as a multi-person smart attendance system with only a simple image acquisition device.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.3
• /
• pp.1-7
• /
• 2024

In this paper, we propose an innovative super-resolution technique to address the issue of reduced accuracy in license plate recognition caused by low-resolution images. Conventional vehicle license plate recognition systems have relied on images obtained from fixed surveillance cameras for traffic detection to perform vehicle detection, tracking, and license plate recognition. However, during this process, image quality degradation occurred due to the physical distance between the camera and the vehicle, vehicle movement, and external environmental factors such as weather and lighting conditions. In particular, the acquisition of low-resolution images due to camera performance limitations has been a major cause of significantly reduced accuracy in license plate recognition. To solve this problem, we propose a Single Image Super-Resolution (SISR) model with a parallel structure that combines Multi-Scale and Attention Mechanism. This model is capable of effectively extracting features at various scales and focusing on important areas. Specifically, it generates feature maps of various sizes through a multi-branch structure and emphasizes the key features of license plates using an Attention Mechanism. Experimental results show that the proposed model demonstrates significantly improved recognition accuracy compared to existing vehicle license plate super-resolution methods using Bicubic Interpolation.

• Journal of Korea Multimedia Society
• /
• v.19 no.2
• /
• pp.112-121
• /
• 2016

ADAS(Advanced Driver Assistance Systems) and street furniture information collecting car like as MMS(Mobile Mapping System), they require object location estimation method for recognizing spatial information of object in road images. But, the case of conventional methods, these methods require additional hardware module for gathering spatial information of object and have high computational complexity. In this paper, for a coordinate of road sign in single camera image, a position estimation scheme of object in road images is proposed using the relationship between the pixel and object size in real world. In this scheme, coordinate value and direction are used to get coordinate value of a road sign in images after estimating the equation related on pixel and real size of road sign. By experiments with test video set, it is confirmed that proposed method has high accuracy for mapping estimated object coordinate into commercial map. Therefore, proposed method can be used for MMS in commercial region.

• The Journal of Korea Robotics Society
• /
• v.8 no.4
• /
• pp.238-246
• /
• 2013

In this paper, a robot vision technique is presented to detect obstacles, particularly approaching humans, in the images acquired by a mobile robot that autonomously navigates in a narrow building corridor. A single low-cost color camera is attached to the robot, and a trapezoidal area is set as a region of interest (ROI) in front of the robot in the camera image. The lower parts of a human such as feet and legs are first detected in the ROI from their appearances in real time as the distance between the robot and the human becomes smaller. Then, the human detection is confirmed by detecting his/her face within a small search region specified above the part detected in the trapezoidal ROI. To increase the credibility of detection, a final decision about human detection is made when a face is detected in two consecutive image frames. We tested the proposed method using images of various people in corridor scenes, and could get promising results. This method can be used for a vision-guided mobile robot to make a detour for avoiding collision with a human during its indoor navigation.