• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1464-1485
• /
• 2021

Emotional style of multimedia art works are abstract content information. This study aims to explore emotional style transfer method and find the possible way of matching music with appropriate images in respect to emotional style. DCNNs (Deep Convolutional Neural Networks) can capture style and provide emotional style transfer iterative solution for affective image generation. Here, we learn the image emotion features via DCNNs and map the affective style on the other images. We set image emotion feature as the style target in this style transfer problem, and held experiments to handle affective image generation of eight emotion categories, including dignified, dreaming, sad, vigorous, soothing, exciting, joyous, and graceful. A user study was conducted to test the synesthesia emotional image style transfer result with ground truth user perception triggered by the music-image pairs' stimuli. The transferred affective image result for music-image emotional synesthesia perception was proved effective according to user study result.

• 제어로봇시스템학회논문지
• /
• 제15권11호
• /
• pp.1076-1079
• /
• 2009

This article deals with an optical image stabilizer which moves an image sensor in the direction of cancelling the vibration caused by hand shaking to prevent a photographed image from blurring. The ball-guide way method adopted as a transfer device of the image sensor is easy to be manufactured because of its simple structure and is suitable to minimize the friction between mechanisms, but has weakness of a chance of physical defect such as groove and rising. In case that the movement of the transfer device equipped with the image sensor is blunted because a ball is stuck in defects of guide way, the performance of the image stabilizer falls down drastically. We propose a method to prevent the transfer device from blunting by applying artificial vibration. At this time, the artificial vibration should be designed under consideration of dynamic characteristics and specifications of the system to be discriminated from the vibration caused by hand shaking.

• 한국컴퓨터정보학회논문지
• /
• 제28권8호
• /
• pp.31-38
• /
• 2023

딥러닝 기반 영상 처리 기술 중 최근 활발히 연구되어 많은 성능 향상을 이룬 기술 중 하나는 스타일 전이 (Style Transfer) 기술이다. 스타일 전이 기술은 콘텐츠 영상과 스타일 영상을 입력받아 콘텐츠 영상의 스타일을 변환한 결과 영상을 생성하는 기술로 디지털 콘텐츠의 다양성을 확보하는데 활용할 수 있어 중요성이 커지고 있다. 이런 스타일 전이 기술의 사용성을 향상하기 위해서는 안정적인 성능의 확보가 중요하다. 최근 자연어 처리 분야에서 트랜스포머 (Transformer) 개념이 적극적으로 활용됨에 트랜스포머의 기반이 되는 어텐션 맵이 스타일 전이 기술 개발에도 활발하게 적용되어 연구되고 있다. 본 논문에서는 그중 대표가 되는 SANet과 AdaAttN 기술을 분석하고 향상된 스타일 전이 결과를 생성 할 수 있는 새로운 어텐션 맵 기반 구조를 제안한다. 결과 영상은 제안하는 기술이 콘텐츠 영상의 구조를 보존하면서도 스타일 영상의 특징을 효과적으로 적용하고 있음을 보여준다.

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.127-134
• /
• 2023

Existing studies on this topic have focused on the effect of online content quality on consumer attitudes and behavior, with very few illustrating the effect of influencer image on consumer attitudes and behavior. The purpose of this study intents to reveal how influencer image affect consumer behavior. We have developed an image transfer theory-based research model to reveal how influencers transfer their image to endorsed products to influence consumer behavior. The results show that influencer image positively affects satisfaction, which in turn affects the product's cognitive and affective images in the vlog. Moreover, it was found that a product's cognitive image and affective image influence consumer behavior intention. Furthermore, purchase experience exhibits significant differences in its path. Based on these results, the social media-related research theoretical implication will be offered, and managerial implications will be provided for foreign brand promotion strategies

• Design & Manufacturing
• /
• 제15권3호
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• 한국컴퓨터정보학회논문지
• /
• 제27권7호
• /
• pp.27-33
• /
• 2022

본 논문은 콘텐츠 이미지에 스타일 이미지를 입혀 스타일이 적용된 이미지를 생성하고자 기존의 이미지 대 이미지 방법이 아닌 다중 도메인 스타일 트랜스퍼(style transfer) 방법을 적용한다. 도메인별로 데이터 분포에 대한 다양한 특성을 고려하고, 콘텐츠 데이터의 특징을 잘 보존하면서 높은 품질의 이미지가 생성되도록 잠재 벡터(latent vector)와 가우시안 노이즈를 추가하는 새로운 GAN의 생성자(generator) 아키텍처를 제안한다. 콘텐츠 이미지가 도메인별 스타일을 잘 학습할 수 있도록 네트워크를 구성하고 사계절 이미지로 구성된 도메인에 적용하여 고해상도의 스타일 트랜스퍼 결과를 보여준다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(1)
• /
• pp.25-28
• /
• 2001

In this paper we implement moving picture transfer system using bluetooth Development Kit (DK). To reduce the size of the image data, we use M-JPEG compression. We use bluetooth Synchronous Connection-Oriented (SCO) link to transfer voice data. Server receive image data from camera and compress the image data in M-JPEG format, and then transmit the image data to client using bluetooth Asynchronous connection-less (ACL) link. Client receive image data from bluetooth ACL link and decode the compressed image and then display the image to screen. Sever and Client can transmit and receive voice data simultaneously using bluetooth SCO link. In this paper bluetooth HCI commands and events generated by host controller to return the results of HCI commands are explained and the flow of bluetooth connection procedure is presented.

• 한국정보통신학회논문지
• /
• 제24권5호
• /
• pp.674-677
• /
• 2020

The cultural background of users utilizing image search engines has a significant impact on the satisfaction of the search results. Therefore, it is important to analyze and understand the cultural context of images for more accurate image search. In this paper, we investigate how the cultural context of images can affect the performance of image classification. To this end, we first collected various types of images (e.g,. food, temple, etc.) with various cultural contexts (e.g., Korea, Japan, etc.) from web search engines. Afterwards, a deep transfer learning approach using VGG19 and MobileNetV2 pre-trained with ImageNet was adopted to learn the cultural features of the collected images. Through various experiments we show the performance of image classification can be differently affected according to the cultural context of images.

• ETRI Journal
• /
• 제39권1호
• /
• pp.76-86
• /
• 2017

In this study, we propose an automatic contrast enhancement method based on transfer function modification (TFM) by histogram equalization. Previous histogram-based global contrast enhancement techniques employ histogram modification, whereas we propose a direct TFM technique that considers the mean brightness of an image during contrast enhancement. The mean point shifting method using a transfer function is proposed to preserve the mean brightness of an image. In addition, the linearization of transfer function technique, which has a histogram flattening effect, is designed to reduce visual artifacts. An attenuation factor is automatically determined using the maximum value of the probability density function in an image to control its rate of contrast. A new quantitative measurement method called sparsity of a histogram is proposed to obtain a better objective comparison relative to previous global contrast enhancement methods. According to our experimental results, we demonstrated the performance of our proposed method based on generalized measures and the newly proposed measurement.

• 한국정보과학회논문지:정보통신
• /
• 제35권3호
• /
• pp.207-214
• /
• 2008

무선 센서네트워크를 이용한 많은 응용 시스템이 연구되고 있는 가운데 무선 센서네트워크 시스템의 신뢰성 확보에 대한 문제점이 대두되고 있다. 이러한 문제점은 센서네트워크의 활용범위를 확장하는데 장애 요인으로 작용하고 있다. 본 연구에서는 초소형 카메라 모듈과 무선 센서네트워크 노드를 이용하여 무선 센서네트워크의 신뢰성 확보를 위한 시스템과 저속의 무선 센서네트워크 상에서 효율적으로 영상정보를 전송하는 방법을 제안하였다. 또한 이러한 기술을 이용하여 무선 이미지 센서네트워크 기반 화재 감시 모니터링 시스템을 구현하였다.