• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1668-1675
• /
• 2008

In this paper, we propose a post-processing technique developed for the subjective improvement of color resolution in DCT-coded color images. The high frequency components caused by complex object parts are compressed and impaired through DCT-based image processing, so color distortions such as blurs in high saturated regions are observed. It's mainly due to the severe loss of color data as Cb and Cr. Generally, the activities of chroma elements in DCT domain correlate strongly with that of luminance as spatial frequency gets higher, and based on the relations between chroma and luma AC activities, we compensate destructed Cb, Cr coefficients using modifications from Y coefficients. Simulation results show that the proposed method enhances color resolution in high saturated region, and improves the visual quality.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Journal of Biomedical Engineering Research
• /
• v.15 no.4
• /
• pp.489-497
• /
• 1994

The most serious problems related to the cardiovascular prothesis are thrombosis and hemolysis. It is known that the flow pattern of cardiovascular prostheses is highly correlated with thrombosis and hemolysis. Laser Doppler Anemometry (LDA) is a usual method to get flow pattern, which is difficult to operate and has narrow measure region. Particle Image Velocimetry (PIV) can solve these problems. Because the flow speed of valve is too high to catch particles by CCD camera, high-speed camera (Hyspeed : Holland-Photonics) was used. The estimated maximum flow speed was 5m/sec and maximum trackable length is 0.5 cm, so the shutter speed was determined as 1000 frames per sec. Several image processing techniques (blurring, segmentation, morphology, etc) were used for the preprocessing. Particle tracking algorithm and 2-D interpolation technique which were necessary in making gridrized velocity pronto, were applied to this PIV program. By using Single-Pulse Multi-Frame particle tracking algorithm, some problems of PIV can be solved. To eliminate particles which penetrate the sheeted plane and to determine the direction of particle paths are these solving methods. 1-D relaxation fomula is modified to interpolate 2-D field. Parachute artificial heart valve which was developed by Seoul National University and Bjork-Shiely valve was testified. For each valve, different flow pattern, velocity profile, wall shear stress and mean velocity were obtained.

• Imaging Science in Dentistry
• /
• v.47 no.3
• /
• pp.199-207
• /
• 2017

Purpose: Evaluation of alveolar bone is important in the diagnosis of dental diseases. The periodontal ligament space is difficult to clearly depict in cone-beam computed tomography images because the reconstruction filter conditions during image processing cause image blurring, resulting in decreased spatial resolution. We examined different reconstruction filters to assess their ability to improve spatial resolution and allow for a clearer visualization of the periodontal ligament space. Materials and Methods: Cone-beam computed tomography projections of 2 skull phantoms were reconstructed using 6 reconstruction conditions and then compared using the Thurstone paired comparison method. Physical evaluations, including the modulation transfer function and the Wiener spectrum, as well as an assessment of space visibility, were undertaken using experimental phantoms. Results: Image reconstruction using a modified Shepp-Logan filter resulted in better sensory, physical, and quantitative evaluations. The reconstruction conditions substantially improved the spatial resolution and visualization of the periodontal ligament space. The difference in sensitivity was obtained by altering the reconstruction filter. Conclusion: Modifying the characteristics of a reconstruction filter can generate significant improvement in assessments of the periodontal ligament space. A high-frequency enhancement filter improves the visualization of thin structures and will be useful when accurate assessment of the periodontal ligament space is necessary.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.898-910
• /
• 2020

Single image-based super-resolution has been studied for a long time in computer vision because of various applications. Various deep learning-based super-resolution algorithms are introduced recently to improve the performance by reducing side effects like blurring and staircase effects. Most deep learning-based approaches have focused on how to implement the network architecture, loss function, and training strategy to improve performance. Meanwhile, Several approaches using Attention Module, which emphasizes the extracted features, are introduced to enhance the performance of the network without any additional layer. Attention module emphasizes or scales the feature map for the purpose of the network from various perspectives. In this paper, we propose the various channel attention and spatial attention in single image-based super-resolution and analyze the results and performance according to the architecture of the attention module. Also, we explore that designing multi-attention module to emphasize features efficiently from various perspectives.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.351-360
• /
• 2022

Image blurring is a phenomenon that occurs due to factors such as movement of a subject and shaking of a camera. Recently, the research for image deblurring has been actively conducted based on convolution neural networks. In particular, the method of guiding the restoration process via the difference between blur and sharp images has shown the promising performance. This paper proposes a novel method for improving the deblurring performance based on the distortion information. To this end, the transformer-based neural network module is designed to guide the restoration process. The proposed method efficiently reflects the distorted region, which is predicted through the global inference during the deblurring process. We demonstrate the efficiency and robustness of the proposed module based on experimental results with various deblurring architectures and benchmark datasets.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.428-430
• /
• 2022

Image processing is playing an important part in automation and artificial intelligence systems, such as object tracking, object recognition and classification, and the importance of IoT technology and automation is emphasizing as interest in automation increases. However, in a system that requires detailed data such as an image boundary, a precise noise removal algorithm is required. Therefore, in this paper, we propose a filtering algorithm based on the pixel value distribution pattern to minimize the information loss in the filtering process. The proposed algorithm finds the distribution pattern of neighboring pixel values with respect to the pixel values of the input image. Then, a weight mask is calculated based on the distribution pattern, and the final output is calculated by applying it to the filtering mask. The proposed algorithm has superior noise removal characteristics compared to the existing method and restored the image while minimizing blurring.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Journal of radiological science and technology
• /
• v.37 no.4
• /
• pp.307-313
• /
• 2014

The purpose of this study is that in coronary artery angiography computed tomography (coronary CTA), to gain high quality of image and to use low dose radiation by administrating normal saline and converting the mode of scanning heart rate (HR) characteristics before infusing contrast media. All patients data (total specimens: 200, male: 108, female: 92) were measured by using appropriate mode of scanning the heart rate (HR) after injection of saline. in addition we measured radiation dose (CTDIvol, effective dose) in all examinations. CT number and noise, and blurring of coronary artery (proximal RCA, middle RCA, proximal LCA) were measured and compared. The result of this study after injection of saline, mean heart rate was decreased about $4.8{\pm}0.3bpm$ (beats per minute). 33 patients (13%) got converting scan mode due to reducing heart rate (HR). In prospective gating mode, radiation dose were measured less $6.0{\pm}1.0mSv$ (54.1%) than retrospective gating mode. Also showed a significant difference in heart rate decrease in image evaluation.