• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.725-737
• /
• 2021

Although the performance of cameras is gradually improving now, there are noise in the acquired digital images from the camera, which acts as an obstacle to obtaining high-resolution images. Traditionally, a filtering method has been used for denoising, and a convolutional neural network (CNN), one of the deep learning techniques, has been showing better performance than traditional methods in the field of image denoising, but the details in images could be lost during the learning process. In this paper, we present a CNN for image denoising, which improves image details by learning the details of the image based on wavelet transform. The proposed network uses two subnetworks for detail enhancement and noise extraction. The experiment was conducted through Gaussian noise and real-world noise, we confirmed that our proposed method was able to solve the detail loss problem more effectively than conventional algorithms, and we verified that both objective quality evaluation and subjective quality comparison showed excellent results.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.176-182
• /
• 2021

This paper evaluates and compares the performance of the Deep Nerual Network (DNN)-based speech enhancement models according to various loss functions. We used a complex network that can consider the phase information of speech as a baseline model. As the loss function, we consider two types of basic loss functions; the Mean Squared Error (MSE) and the Scale-Invariant Source-to-Noise Ratio (SI-SNR), and two types of perceptual-based loss functions, including the Perceptual Metric for Speech Quality Evaluation (PMSQE) and the Log Mel Spectra (LMS). The performance comparison was performed through objective evaluation and listening tests with outputs obtained using various combinations of the loss functions. Test results show that when a perceptual-based loss function was combined with MSE or SI-SNR, the overall performance is improved, and the perceptual-based loss functions, even exhibiting lower objective scores showed better performance in the listening test.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.301-307
• /
• 2024

This study introduces a novel cascade fusion architecture aimed at enhancing thermal images across various scale conditions. The processing of thermal images at multiple scales has been challenging due to the limitations of existing methods that are designed for specific scales. To overcome these limitations, this paper proposes a unified framework that utilizes cascade feature fusion to effectively learn multi-scale representations. Confidence maps from different image scales are fused in a cascaded manner, enabling scale-invariant learning. The architecture comprises end-to-end trained convolutional neural networks to enhance image quality by reinforcing mutual scale dependencies. Experimental results indicate that the proposed technique outperforms existing methods in multi-scale thermal image enhancement. Performance evaluation results are provided, demonstrating consistent improvements in image quality metrics. The cascade fusion design facilitates robust generalization across scales and efficient learning of cross-scale representations.

• Journal of Korean Society for Quality Management
• /
• v.46 no.2
• /
• pp.211-224
• /
• 2018

Purpose: It can easily be understood that more rules and regulations need to be imposed on the medical device industry due to its impact on public health and hygiene. Domestic medical device manufacturers are thus required to comply with the requirements specified in the good manufacturing practice (GMP) system, and it is essential to abide by the international standards as well to sustain their global competitiveness. The main purpose of this study is to review the guidelines of the medical device GMP system in Korea and propose future directions for further enhancement of the GMP system. Methods: Specific requirements prescribed in international standards, such as ISO 9001:2015, ISO 13485:2016, ISO 14971:2012, and ISO 14155:2011, are analyzed and compared with the domestic GMP system. Results: It has been observed that the generic international standard related to quality management system, ISO 9001:2015, lays out the foundations for the development of quality management system relevant to medical device industry, ISO 13485:2003, with which the domestic GMP system is fully compatible. Further, several important aspects of risk management and clinical trials of medical devices are also recognized and included in the domestic medical device GMP system. Conclusion: Even though specific requirements of individual ISO standards are slightly different from each other, their overall structure and framework may contribute to the development and enhancement of globally competitive GMP system of the domestic medical device industry.

• Korean Institute of Interior Design Journal
• /
• v.24 no.6
• /
• pp.47-57
• /
• 2015

In this research, an attempt was made to approach social sustainability of residential environments that have been studied thus far in community-oriented research in a broader perspective, with the aim to induce evaluation indicators for social sustainability of a residential environment that is oriented for enhancement of the residents' life quality. First, evaluation system of social sustainability of residential environments is divided into 6 areas that include regionality, diversity, fairness, satisfaction of diverse needs, social exchange, and participation and decision making. A subdivision was also introduced to account for evaluation properties by area. Second, regarding measurement of life quality in a residential environment, the scope of evaluation was divided into residential environment dimension, resident dimension, and management dimension which can incorporate both objective evaluation and subjective evaluation in consideration of the fact that it involves both physical environment and socio-psychological elements. Third, evaluation indicators by area were collected based on an analysis of preceding studies. For the purpose, a total of 193 indicators were extracted, including 28 items of regionality area, 26 items of diversity area, 28 items of fairness area, 58 items of satisfaction of diverse needs, 34 items of social exchange area, and 19 items of participation and decision making area. The kind of evaluation indicators have meaning in that it can be used as an evaluation tool of social sustainability that can be applied universally from the planning stage. It can be utilized as a basic data for enhancement of life quality and promotion of social values in a residential environment.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.3
• /
• pp.211-219
• /
• 2014

Closed cracks are difficult to detect using conventional ultrasonic testing because most incident ultrasound passes completely through these cracks. Nonlinear ultrasound inspection using sub-harmonic frequencies a promising method for detecting closed cracks. To implement this method, a sub-harmonic phased array (PA) is proposed to visualize the length of closed cracks in solids. A sub-harmonic PA generally consists of a single transmitter and an array receiver, which detects sub-harmonic waves generated from closed cracks. The PA images are obtained using the total focusing method (TFM), which (with a transmitter and receiving array) employs a full matrix in the observation region to achieve fine image resolution. In particular, the receiving signals are measured using a laser Doppler vibrometer (LDV) to collect PA images for both fundamental and sub-harmonic frequencies. Oblique incidence, which is used to boost sub-harmonic generation, inevitably produces various surface waves that contaminate the signals measured in the receiving transducer. Surface wave interference often degrades PA images severely, and it becomes difficult to read the closed crack's position from the images. Various methods to prevent or eliminate this interference are possible. In particular, enhancing images with signal processing could be a highly cost-effective method. Because periodic patterns distributed in a PA image are the most frequent interference induced by surface waves, spatial frequency filtering is applicable for removing these waves. Experiments clearly demonstrate that the spatial frequency filter improves PA images.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.7
• /
• pp.36-41
• /
• 2018

An image intensifying device is equipment that makes weak objects visible in a dark environment, such as making nighttime bright enough to let objects be visually observed. It is possible to obtain a clear image by amplifying the light in the presence of a certain amount of weak light. However, in an extremely low-light environment, where even moonlight is not present, there is not enough light to amplify anything, and the sharpness of the screen deteriorates. In this paper, a method is proposed to improve image quality by using multiple filters and anisotropic diffusion for output noise of the image-intensifying device in extreme low-light environments. For the experiment, the output of the image-intensifying device was obtained under extremely low-light conditions, and signal processing for improving the image quality was performed. The configuration of the filters for signal processing uses anisotropic diffusion after applying a median filter and a Wiener filter for effective removal of salt-and-pepper noise and Gaussian noise, which constitute the main noise appearing in the image. Experimental results show that the improvement visually enhanced image quality. Both peak signal-to-noise ratio (PSNR) and SSIM, which are quantitative indicators, show improved values.

• Journal of Digital Contents Society
• /
• v.17 no.2
• /
• pp.89-96
• /
• 2016

SVC(Scalable Video Coding), which is one form among video encoding technologies, makes video streaming with the various frame rate, resolution, and video quality by combining three different scalability dimensions: temporal, spatial, and video quality scalability. As the above SVC-encoded video streaming consists of one base layer and several enhancement layers, and a wireless AP(Access Point) chooses and sends a suitable layer according to the received power from the receiving terminals in the changeable wireless network environment, the receiving terminals supporting SVC are able to receive video streaming with the appropriate resolution and quality according to their received powers. In this paper, after the performance analysis for the received power, packet loss rate, PSNR(Required Peak Signal to Noise Ratio), video quality level and amount of received video data based on the number of SVC layers was performed, an efficient method for selecting the number of SVC layer satisfying the RSNR and minimizing the amount of received video data is proposed.

• Food Science of Animal Resources
• /
• v.43 no.2
• /
• pp.245-268
• /
• 2023

The effects of phosphate alternatives on meat quality in marinated chicken were investigated with the application of chilling and freezing. Breast muscles were injected with solution of the green weight containing 1.5% NaCl and 2% sodium tripolyphosphate (STPP) or phosphate alternatives. Treatment variables consisted of no phosphate [control (-)], 0.3% sodium tripolyphosphate [control (+)], 0.3% prune juice (PJ), 0.3% oyster shell, 0.3% nano-oyster shell, and 0.3% yeast and lemon extract (YLE) powder. One-third of the meat samples were stored at 4℃ for 1 d, and the rest of the meats were kept at -18℃ for 7 d. In chilled meat, a lower drip loss was noted for control (+) and YLE, whereas higher cooking yield in YLE compared to all tested groups. Compared with control (+), the other treatments except PJ showed higher pH, water holding capacity, moisture content, lower thawing and cooking loss, and shear force. Natural phosphate alternatives except for PJ, improved the CIE L^* compared to control (-), and upregulated total protein solubility. However, phosphate alternatives showed similar or higher oxidative stability and impedance measurement compared to control (+), and an extensive effect on myofibrillar fragmentation index. A limited effect was observed for C^*, h°, and free amino acids in treated meat. Eventually, the texture profile attributes in cooked of phosphate alternatives improved except for PJ. The results indicate the high potential use of natural additives could be promising and effective methods for replacing synthetic phosphate in chilled and frozen chicken with quality enhancement.