• 대한전자공학회논문지SP
• /
• 제45권5호
• /
• pp.18-24
• /
• 2008

본 논문은 적웅적 움직임 추정영역 선택을 사용한 디지털 영상안정화의 성능개선에 대한 새로운 방법을 제시한다. 움직임 추정을 위한 후보영역을 선정하고 그 중에서 제안하는 두 가지 방법인 다중 영상 참조와 윤곽에너지 판별을 통해 최종 움직임 추정영역을 선택한다. 정해진 영역에서 움직임을 추정하고 보상한다. 실험을 통해 제안하는 방법이 영상안정화의 성능을 향상 시킴을 보인다.

• Journal of information and communication convergence engineering
• /
• 제4권3호
• /
• pp.97-100
• /
• 2006

In this paper, the transmission service for medical image is proposed via IEEE 802.15.4a on WPAN environment. Also, transmission and receiving performance of medical image using TH UWB-IR system is evaluated on indoor multi-path fading environment. On the results, the proposed scheme can solve the problem of interference from the medical equipment in same frequency band, and minimize the loss due to the indoor multi-path fading environment. Therefore, the transmission with low power usage is possible.

• 한국의학물리학회지:의학물리
• /
• 제9권3호
• /
• pp.143-154
• /
• 1998

상강화기는 형광 영상장치에서 영상의 특성을 결정하는 주된 요소이다. 본 연구는 두가지의 상강화기를 임상에서 평가하기 위하여 간단하고 비파괴적이며 적당한 시간내에 행할 수 있는 계의 활동 프로그램을 제시하였다. 이 프로그램은 크게 세 부분 즉, X-선 발생장치, 영상의 질, 조준으로 되어있다. X-선의 발생장치에 대하여 관전압의 정확도와 자동노출 조절기능을 비교하였다. 영상의 질을 위해서는 저대비 및 고대비 분해능 측정, 체격자 실험 등을 수행하였으며 이 실험에서는 비디오 모니터 및 순간영상을 필름화한 정량적인 분석을 분석하였다. 조준에 대해서는 상강화기의 유용한 영역의 직경과 상의 찌그러짐을 측정하고 정량적인 분석을 하였다. 이 실험들의 과정 및 결과들이 상강화기의 인수검사 및 계의 활동지수를 평가하는데 이용되기를 바란다.

• ETRI Journal
• /
• 제42권1호
• /
• pp.67-77
• /
• 2020

Image captioning has received significant interest in recent years, and notable results have been achieved. Most previous approaches have focused on generating visual descriptions from images, whereas a few approaches have exploited visual descriptions for image classification. This study demonstrates that a good performance can be achieved for both description generation and image classification through an end-to-end joint learning approach with a loss function, which encourages each task to reach a consensus. When given images and visual descriptions, the proposed model learns a multimodal intermediate embedding, which can represent both the textual and visual characteristics of an object. The performance can be improved for both tasks by sharing the multimodal embedding. Through a novel loss function based on class activation mapping, which localizes the discriminative image region of a model, we achieve a higher score when the captioning and classification model reaches a consensus on the key parts of the object. Using the proposed model, we established a substantially improved performance for each task on the UCSD Birds and Oxford Flowers datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• 한국간호교육학회지
• /
• 제9권1호
• /
• pp.64-72
• /
• 2003

Purpose: The purpose of this study was to identify changes in nurses' image of student nurses before and after their first clinical practice. Method: Study samples were composed of 78 student nurses who were from nursing dept. of one college in G city. All participants had their first clinical practice for 4 weeks at two general hospitals in Gwangju. The internal consistency of the total scale was Cronbach's $\alpha$= .883. Results: After the first clinical practice, the mean score of nurses' image in general was lower than that of nurses' image before the clinical practice. In five subcategories, before the first clinical practice, professionalism and expertness were the highest followed by role performance, vision of a career, and temperature as a nurse in order but after the first clinical practice, professionalism was the highest score followed by expertness, temperature as a nurse, role performance, vision of a career in the mean scores of nurses' image. Conclusion: Based upon these findings, clinical practice will play an important role in improving role performance and vision of a nursing career for student nurses, so nursing administrators should make efforts to improve image of nurses in a variety of practice.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1417-1424
• /
• 2018

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

• 한국멀티미디어학회논문지
• /
• 제22권9호
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4665-4683
• /
• 2019

Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.

• 우주기술과 응용
• /
• 제1권1호
• /
• pp.41-48
• /
• 2021

본 논문에서는 영상의 대각선 정보를 이용하여 원영상의 왜곡이나 성능저하 없이 해상도를 1.4배 증가시킬 수 있는 기술 및 기법에 대해 논하고자 한다. 적용된 방법은 영상을 45도 돌리지 않고도 인접한 4점의 영상정보를 이용하여 카메라의 특성에 맞게 확대 및 재배열을 함으로써, 영상을 실제로 45도 돌리는 것과 동일한 물리적 개념을 적용할 수 있고, 원 영상의 왜곡이나 성능 저하 없이 해상도를 1.4배 증가시킬 수 있는 구체적 실현 방법 및 이에 대한 실증이다.