• Spatial Information Research
• /
• v.19 no.1
• /
• pp.29-40
• /
• 2011

GOCI the world first Ocean Color Imager in Geostationary Orbit, which could obtain total 8 images of the same region a day, however, its spatial resolution(500m) is not enough to use for the accurate land application, Super Resolution(SR), reconstructing the high resolution(HR) image from multiple low resolution(LR) images introduced by computer vision field. could be applied to the time-series remotely sensed images such as GOCI data, and the higher resolution image could be reconstructed from multiple images by the SR, and also the cloud masked area of images could be recovered. As the precedent study for developing the efficient SR method for GOCI images, on this research, it reproduced the simulated data under the acquisition process of the remote sensed data, and then the simulated images arc applied to the proposed algorithm. From the proposed algorithm result of the simulated data, it turned out that low resolution(LR) images could be registered in sub-pixel accuracy, and the reconstructed HR image including RMSE, PSNR, SSIM Index value compared with original HR image were 0.5763, 52.9183 db, 0.9486, could be obtained.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.1987-1996
• /
• 2009

Recently, the color of vehicle license plate has been changed from green to white. Thus the vehicle plate recognition system used for parking management systems, speed and signal violation detection systems should be robust to the both colors. This paper presents a vehicle license plate recognition system, which works on both of green and white plate at the same time. In the proposed system, the image of license plate is taken from a captured vehicle image by using morphological information. In the next, each character region in the license plate image is extracted based on the vertical and horizontal projection of plate image and the relative position of individual characters. Finally, for the recognition process of extracted characters, PCA(Principal Component Analysis) and LDA(Linear Discriminant Analysis) are sequentially utilized. In the experiment, vehicle license plates of both green background and white background captured under irregular illumination conditions have been tested, and the relatively high extraction and recognition rates are observed.

• Journal of Internet Computing and Services
• /
• v.5 no.6
• /
• pp.79-91
• /
• 2004

Various facial pose detection and recognition has been a difficult problem. The problem is due to the fact that the distribution of various poses in a feature space is mere dispersed and more complicated than that of frontal faces, This thesis proposes a robust pose-expression-invariant face recognition method in order to overcome insufficiency of the existing face recognition system. First, we apply the TSL color model for detecting facial region and estimate the direction of face using facial features. The estimated pose vector is decomposed into X-V-Z axes, Second, the input face is mapped by deformable template using this vectors and 3D CANDIDE face model. Final. the mapped face is transformed to frontal face which appropriates for face recognition by the estimated pose vector. Through the experiments, we come to validate the application of face detection model and the method for estimating facial poses, Moreover, the tests show that recognition rate is greatly boosted through the normalization of the poses and expressions.

• Database Research
• /
• v.34 no.3
• /
• pp.124-136
• /
• 2018

There have been active research activities to use neural networks to analyze OCT images and make medical decisions. One requirement for these approaches to be promising solutions is that the trained network must be generalized to new devices without a substantial loss of performance. In this paper, we use a deep convolutional neural network to distinguish AMD from normal patients. The network was trained using a data set generated from an OCT device. We observed a significant performance degradation when it was applied to a new data set obtained from a different OCT device. To overcome this performance degradation, we propose an image normalization method which performs segmentation of OCT images to identify the retina area and aligns images so that the retina region lies horizontally in the image. We experimentally evaluated the performance of the proposed method. The experiment confirmed a significant performance improvement of our approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.1-11
• /
• 2023

Deep-learning-based image segmentation is one of the most widely employed lane detection approaches, and it requires a post-process for extracting the key points on the lanes. A general approach for key-point extraction is using a fixed threshold defined by a user. However, finding the best threshold is a manual process requiring much effort, and the best one can differ depending on the target data set (or an image). We propose a novel key-point extraction algorithm that automatically adapts to the target image without any manual threshold setting. In our adaptive key-point extraction algorithm, we propose a line-level normalization method to distinguish the lane region from the background clearly. Then, we extract a representative key point for each lane at a line (row of an image) using a kernel density estimation. To check the benefits of our approach, we applied our method to two lane-detection data sets, including TuSimple and CULane. As a result, our method achieved up to 1.80%p and 17.27% better results than using a fixed threshold in the perspectives of accuracy and distance error between the ground truth key-point and the predicted point.

• Journal of radiological science and technology
• /
• v.47 no.1
• /
• pp.29-37
• /
• 2024

This study aims to evaluate the performance of the U-Net based learning model that may vary depending on the histogram equalization algorithm. The subject of the experiment were 17 radiology students of this college, and 1,727 data sets in which the region of interest was set in the thyroid after acquiring ultrasound image data were used. The training set consisted of 1,383 images, the validation set consisted of 172 and the test data set consisted of 172. The equalization algorithm was divided into Histogram Equalization(HE) and Contrast Limited Adaptive Histogram Equalization(CLAHE), and according to the clip limit, it was divided into CLAHE8-1, CLAHE8-2. CLAHE8-3. Deep Learning was learned through size control, histogram equalization, Z-score normalization, and data augmentation. As a result of the experiment, the Attention U-Net showed the highest performance from CLAHE8-2 to 0.8355, and the U-Net and BSU-Net showed the highest performance from CLAHE8-3 to 0.8303 and 0.8277. In the case of mIoU, the Attention U-Net was 0.7175 in CLAHE8-2, the U-Net was 0.7098 and the BSU-Net was 0.7060 in CLAHE8-3. This study attempted to confirm the effects of U-Net, Attention U-Net, and BSU-Net models when histogram equalization is performed on ultrasound images. The increase in Clip Limit can be expected to increase the ROI match with the prediction mask by clarifying the boundaries, which affects the improvement of the contrast of the thyroid area in deep learning model learning, and consequently affects the performance improvement.

• Radiation Oncology Journal
• /
• v.32 no.1
• /
• pp.23-30
• /
• 2014

Purpose: The goal of this study is to determine whether the magnitude of overlap between planning target volume (PTV) and rectum ($Rectum_{overlap}$) or PTV and bladder ($Bladder_{overlap}$) in prostate cancer volumetric-modulated arc therapy (VMAT) is predictive of the dose-volume relationships achieved after optimization, and to identify predictive equations and cutoff values using these overlap volumes beyond which the Quantitative Analyses of Normal Tissue Effects in the Clinic (QUANTEC) dose-volume constraints are unlikely to be met. Materials and Methods: Fifty-seven patients with prostate cancer underwent VMAT planning using identical optimization conditions and normalization. The PTV (for the 50.4 Gy primary plan and 30.6 Gy boost plan) included 5 to 10 mm margins around the prostate and seminal vesicles. Pearson correlations, linear regression analyses, and receiver operating characteristic (ROC) curves were used to correlate the percentage overlap with dose-volume parameters. Results: The percentage $Rectum_{overlap}$ and $Bladder_{overlap}$ correlated with sparing of that organ but minimally impacted other dose-volume parameters, predicted the primary plan rectum $V_{45}$ and bladder $V_{50}$ with $R^2$ = 0.78 and $R^2$ = 0.83, respectively, and predicted the boost plan rectum $V_{30}$ and bladder $V_{30}$ with $R^2$ = 0.53 and $R^2$ = 0.81, respectively. The optimal cutoff value of boost $Rectum_{overlap}$ to predict rectum $V_{75}$ >15% was 3.5% (sensitivity 100%, specificity 94%, p < 0.01), and the optimal cutoff value of boost $Bladder_{overlap}$ to predict bladder $V_{80}$ >10% was 5.0% (sensitivity 83%, specificity 100%, p < 0.01). Conclusion: The degree of overlap between PTV and bladder or rectum can be used to accurately guide physicians on the use of interventions to limit the extent of the overlap region prior to optimization.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.79-86
• /
• 2005

In this paper, we propose a new LINF(Linear Independent Non-negative Factorization) algorithm for real-time face recognition systea This system greatly consists of the two parts: 1) face extraction part; 2) face recognition part. In the face extraction Part we applied subtraction image, the detection of eye and mouth region , and normalization method, and then in the face recognition Part we used LINF in extracted face candidate region images. The existing recognition system using only PCA(Principal Component Analysis) showed low recognition rates, and it was hard in the recognition system using only LDA(Linear Discriminants Analysis) to apply LDA directly when the training set is small. To overcome these shortcomings, we reduced dimension as the matrix that had non-negative value to be different from former eigenfaces and then applied LDA to the matrix in the proposed system We have experimented using self-organized DAIJFace database and ORL database offered by AT(')T laboratory in Cambridge, U.K. to evaluate the performance of the proposed system. The experimental results showed that the proposed method outperformed PCA, LDA, ICA(Independent Component Analysis) and PLMA(PCA-based LDA mixture algorithm) method within the framework of recognition accuracy.

• Analyses & Alternatives
• /
• v.7 no.1
• /
• pp.229-258
• /
• 2023

For the main countries of the Asia-Pacific region, the United States, China and Russia, a situation of "new normality" is emerging. Moreover, for each of the countries, this "new normality" has its own meaning. For the United States, this is an aggravation of the military confrontation with China in the Taiwan Strait. For China, this is an increase in the degree of rivalry with the United States and a slowdown in the pace of economic development with a very high probability of their decline in the future. For Russia, this is an almost complete curtailment of relations with the United States against the background of a special military operation and imposed sanctions. These nuances, in addition to the results of the 20th CPC Congress, will determine the main trends in Sino-American and Sino-Russian relations. It seems that China's attitude towards Russia will not change against the background of the Ukrainian crisis. Beijing will maintain a position of "benevolent neutrality" towards Moscow. At the same time, the balance between "goodwill" and "neutrality" may vary depending on the scope of Sino-Russian cooperation. For example, in the economic sphere, Chinese companies will be afraid to cooperate with Russian partners for fear of secondary sanctions. However, in general, Russia will retain its importance for China as the strongest anti-American pole. In relations with the United States, China will continue to firmly defend its interests, while at the same time not excluding the normalization of relations with Washington in certain areas of cooperation: strategic stability, non-traditional threats, ecology, etc. In general, the decisions of the 20th CPC Congress do not allow us to say either in favor or against the idea of China's readiness to resume dialogue with the United States in the post-congress period. Sino-American relations, as noted above, have their own logic and will probably continue to develop within its framework. However, so are Sino-Russian relations. Within the framework of these logics, Beijing seems to continue to balance between the two vectors of its foreign policy. On the one hand, this is the development of bilateral cooperation with Russia in order to strengthen its own negotiating positions in the confrontation with the United States: military cooperation with an emphasis on joint exercises, political cooperation based on anti-Americanism, economic cooperation with an eye to the risks of secondary sanctions. On the other hand, it is unacceptable for China to recognize the collapse of Ukraine, the inadmissibility of a direct military clash with the United States and the extreme undesirability of further aggravation of relations with the United States on the factor of Chinese friendship with Russia.