• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.656-658
• /
• 2022

The purpose of infrared and visible image fusion is to integrate images of different modes with different details into a result image with rich information, which is convenient for high-level computer vision task. Considering many deep networks only work in a single scale, this paper proposes a novel image fusion based on three-scale dense network to preserve the content and key target features from the input images in the fused image. It comprises an encoder, a three-scale block, a fused strategy and a decoder, which can capture incredibly rich background details and prominent target details. The encoder is used to extract three-scale dense features from the source images for the initial image fusion. Then, a fusion strategy called l₁-norm to fuse features of different scales. Finally, the fused image is reconstructed by decoding network. Compared with the existing methods, the proposed method can achieve state-of-the-art fusion performance in subjective observation.

• 대한족부족관절학회지
• /
• 제15권1호
• /
• pp.1-6
• /
• 2011

Purpose: The purpose of this study was to compare the clinical and radiological results of single and double fusions in the transverse tarsal joint. Materials and Methods: Between December 2000 and April 2009, 16 patients (16 feet) who had been treated by fusion of transverse tarsal joint were included in this study. In 8 patients, only talonavicular joint was fused and in the other 8 patients, both talonavicular and calcaneocuboid joints were fused simultaneously. We have measured talo-first metatarsal angle, calcaneal pitch angle, talonavicular coverage angle and presence of adjacent joint arthritis for radiological assessment at both preoperative and last visit. Furthermore, we have evaluated Visual Analogue Scale (VAS), American Orthopaedic Foot and Ankle Society (AOFAS) score and patient's satisfaction. Results: In a single fusion group, VAS was improved from $6.4{\pm}1.4$ to $0.8{\pm}1.0$ (p=0.0011) and AOFAS score was improved from $63.8{\pm}6.2$ to $89.4{\pm}9.8$ (p=0.0012). In a double fusion group, VAS was improved from $8.0{\pm}0.75$ to $2.0{\pm}1.8$ (p=0.0011) and AOFAS score was improved from $60.5{\pm}11.2$ to $89.5{\pm}6.0$ (p=0.0012). In the difference of talo-first metatarsal angle between two groups, a single fused group was more improved than a double fused group (p=0.04). Conclusion: Both single and double fusions are useful and attractive treatment for the transverse tarsal joint arthritis. Furthermore, a single fusion has advantages of less invasiveness and preserving some degree of hindfoot motion and could be an effective alternative to a double fusion if patient meets appropriate criteria through careful preoperative evaluation.

• 한국멀티미디어학회논문지
• /
• 제22권10호
• /
• pp.1160-1167
• /
• 2019

Because of the dynamic range limitation of digital equipment, it is impossible to obtain dark and bright areas at the same time with one shot. In order to solve this problem, an exposure fusion technique for fusing a plurality of images photographed at different exposure amounts into one is being studied. Among them, Laplacian pyramid decomposition based fusion method can generate natural HDR image by fusing images of various scales. But this requires a lot of computation time. Therefore, in this paper, we propose an approximation technique that achieves similar performance and greatly shortens computation time. The concept of vanishing point image for approximation is introduced, and the validity of the proposed approach is verified by comparing the computation time with the resultant image.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.427-438
• /
• 2023

Plenty of works have indicated that single image super-resolution (SISR) models relying on synthetic datasets are difficult to be applied to real scene text image super-resolution (STISR) for its more complex degradation. The up-to-date dataset for realistic STISR is called TextZoom, while the current methods trained on this dataset have not considered the effect of multi-scale features of text images. In this paper, a multi-scale and attention fusion model for realistic STISR is proposed. The multi-scale learning mechanism is introduced to acquire sophisticated feature representations of text images; The spatial and channel attentions are introduced to capture the local information and inter-channel interaction information of text images; At last, this paper designs a multi-scale residual attention module by skillfully fusing multi-scale learning and attention mechanisms. The experiments on TextZoom demonstrate that the model proposed increases scene text recognition's (ASTER) average recognition accuracy by 1.2% compared to text super-resolution network.

• Journal of Korean Neurosurgical Society
• /
• 제58권2호
• /
• pp.119-124
• /
• 2015

Objective : We compared the clinical and radiographic outcomes of stand-alone polyetheretherketone (PEEK) cage and Zero-Profile anchored spacer (Zero-P) for single level anterior cervical discectomy and fusion (ACDF). Methods : We retrospectively reviewed 121 patients who underwent single level ACDF within 2 years (Jan 2011-Jan 2013) in a single institute. Total 50 patients were included for the analysis who were evaluated more than 2-year follow-up. Twenty-nine patients were allocated to the cage group (m : f=19 : 10) and 21 for Zero-P group (m : f=12 : 9). Clinical (neck disability index, visual analogue scale arm and neck) and radiographic (Cobb angle-segmental and global cervical, disc height, vertebral height) assessments were followed at pre-operative, immediate post-operative, post-3, 6, 12, and 24 month periods. Results : Demographic features and the clinical outcome showed no difference between two groups. The change between final follow-up (24 months) and immediate post-op of Cobb-segmental angle (p=0.027), disc height (p=0.002), vertebral body height (p=0.033) showed statistically better outcome for the Zero-P group than the cage group, respectively. Conclusion : The Zero-Profile anchored spacer has some advantage after cage for maintaining segmental lordosis and lowering subsidence rate after single level anterior cervical discectomy and fusion.

• 대한수학교육학회지:학교수학
• /
• 제10권2호
• /
• pp.259-277
• /
• 2008

본 연구는 인지 진단 이론을 활용하여 수학 평가 결과를 분석하고 교수 학습에 활용하는 방안을 모색하고자 하였다. $2003{\sim}2006$년에 실시된 국가수준 학업성취도 평가의 중학교 3학년 수학 검사에서 30개의 선다형 문항을 선정하여 검사지를 재구성하고 검사를 실시하였고 인지 진단 이론의 한 모형인 Fusion Model을 적용하여 평가 결과를 분석하였다. 검사 문항을 통해 학생들이 숙달한 수학적 속성을 판별하고, 학생 전체와 성취수준별로 숙달한 속성과 그 속성의 개수를 분석하였다. 그리고 학생 개개인의 수학적 강점과 약점을 분석하여 교사들에게 학생 개개인의 수학적 능력에 대한 정보를 구체적으로 알려줄 수 있었다. 이 결과는 학생들의 수학 학습에 대한 진단과 처방, 추후 학습 지도에 유용한 정보로 활용될 수 있을 것이다.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.75-94
• /
• 2021

The 4th industrial revolution needs a fusion of artificial intelligence, robotics, the Internet of Things (IoT), edge computing, and other technologies. For the fusion of technologies, cloud computing technology can provide flexible and high-performance computing resources so that cloud computing can be the foundation technology of new emerging services. The emerging services become a global-scale, and require much higher performance, availability, and reliability. Public cloud providers already provide global-scale services. However, their services, costs, performance, and policies are different. Enterprises/ developers to come out with a new inter-operable service are experiencing vendor lock-in problems. Therefore, multi-cloud technology that federatively resolves the limitations of single cloud providers is required. We propose a software platform, denoted as Cloud-Barista. Cloud-Barista is a multi-cloud service common platform for federating multiple clouds. It makes multiple cloud services as a single service. We explain the functional architecture of the proposed platform that consists of several frameworks, and then discuss the main design and implementation issues of each framework. To verify the feasibility of our proposal, we show a demonstration which is to create 18 virtual machines on several cloud providers, combine them as a single resource, and manage it.

• The Journal of the Acoustical Society of Korea
• /
• 제27권3E호
• /
• pp.77-83
• /
• 2008

In the process of the sonar image textures produced, the orientation and scale factors are very significant. However, most of the related methods ignore the directional information and scale invariance or just pay attention to one of them. To overcome this problem, we apply Gabor wavelet to extract the features of sonar images, which combine the advantages of both the Gabor filter and traditional wavelet function. The mother wavelet is designed with constrained parameters and the optimal parameters will be selected at each orientation, with the help of bandwidth parameters based on the Fisher criterion. The Gabor wavelet can have the properties of both multi-scale and multi-orientation. Based on our experiment, this method is more appropriate than traditional wavelet or single Gabor filter as it provides the better discrimination of the textures and improves the recognition rate effectively. Meanwhile, comparing with other fusion methods, it can reduce the complexity and improve the calculation efficiency.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• 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 Korean Neurosurgical Society
• /
• 제40권3호
• /
• pp.175-179
• /
• 2006

Objective : The surgical outcome of anterior lumbar interbody fusion[ALlF] with pedicle screw fixation for elderly isthmic spondylolisthesis was analyzed. Methods : Consecutive nineteen elderly patients [aged 65 years or more] with isthmic spondylolisthesis [Grade I or II] who underwent single level ALIF with pedicle screw fixation in 2002 were analyzed. Using clinical chart and mailed questionnaires, preoperative and postoperative Visual Analogue Scale[VAS] of back and leg pain and postopertive Macnab criteria were evaluated. Results : The mean age at the time of operation was 68.4 years [range 65 to 78 years]. Twelve patients underwent ALIF with percutaneous pedicle screw fixation. Seven patients underwent ALIF followed by posterior decompression and pedicle screw fixation. The postoperative complication rate was 10.5% [wound dehiscence in 1 patient and incisional hernia in 1 patient]. There was no postoperative major morbidity or mortality. At a mean follow-up duration of 30.7 months [range 25 to 35 months], 93.3% [14/15] of the patients showed excellent or good outcomes in terms of Macnab criteria. The mean VAS scores of back pain and leg pain significantly decreased after surgery. Conclusion : ALIF with pedicle screw fixation yielded favorable results for elderly isthmic spondylolisthesis in selected cases.