• 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.

• International Journal of Costume and Fashion
• /
• 제5권2호
• /
• pp.1-10
• /
• 2005

In the 21th century, the age of image, people express and are evaluated with their images. Image making, as behavior of creating image, is rapidly spreading in the society. Thus, the purpose of this study is to investigate the precise concepts of image making, and the meaning of personal image and fashion styling in image making. Based on previous studies in clothing for a theoretical examination of the concepts of image making, and the meaning of personal image and fashion styling in image making, we have analyzed and studied the concepts of image making generally accepted in the society. The results of this study are as follows. First, personal image making aims at the establishment of one's own identity through the ideal image construction. Second, the establishment of one's own identity through building up his ideal image is completed through fashion styling. Third. image making increases one's personal values and competitive power to implement its ultimate goals. In this study, we have proved that image making makes people establish their own identity by building up their ideal images through fashion styling.

• 복식
• /
• 제64권5호
• /
• pp.18-29
• /
• 2014

Modern male has displayed an increased desire to express their social influence and image, and the male fashion market has had to provide various styles and images to fill these needs. The current domestic menswear market, however, is unable to satisfy the needs of male consumers who have a need for diversity in a rapidly changing society; more segmented fashion images and styles are needed. The purposes of this study are to classify fashion images and to establish character of the types. This study was done by performing a literature review and a survey. This study proposed 10 categories of fashion style images. Men's fashion style is classified into the classic image, sophisticated image, urban casual image, chic modern image, mods modern image, basic casual image, ethnic image, avant-garde image, active & outdoor image, and street-kitsch image. In the case of the classic images, common in formal setting, men's formal wear is the main focus with the classic suit. The sophisticated image is that of a colorful formal wear seasoned with elegance. Urban casual image is contemporary image, and therefore is meant for city life wear. Chic and modern image conveys an urban image by seeking a simple and chic feel. Mods modern image is retro yet dandy, giving off a sense of youthfulness compared to the other classic images. Ethnic image expresses the exotic quality of folklore as the main representatives of the character casual wear. Avant garde image portrays strong character casual wear with oversized silhouettes or exaggerated details. Active & Outdoor image is leisure life wear conveying active, functional images. Street Kitsch image is men's street casual wear with graphic patterns such as pop art and graffiti. This study's significance lies in its presentation of fashion style data, which can be utilized in the design and marketing of fashion targeted to males.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• pp.3620-3637
• /
• 2019

Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field and so on. However, the existence of speckle noise makes a good deal inconvenience for the subsequent image processing. The continuous development of sparse representation (SR) opens a new field for the speckle suppressing of SAR image. Although the SR de-noising may be effective, the over-smooth phenomenon still has bad influence on the integrity of the image information. In this paper, one novel SAR image de-noising method based on residual image fusion and sparse representation is proposed. Firstly we can get the similar block groups by the non-local similar block matching method (NLS-BM). Then SR de-noising based on the adaptive K-means singular value decomposition (K-SVD) is adopted to obtain the initial de-noised image and residual image. The residual image is processed by Shearlet transform (ST), and the corresponding de-noising methods are applied on it. Finally, in ST domain the low-frequency and high-frequency components of the initial de-noised and residual image are fused respectively by relevant fusion rules. The final de-noised image can be recovered by inverse ST. Experimental results show the proposed method can not only suppress the speckle effectively, but also save more details and other useful information of the original SAR image, which could provide more authentic and credible records for the follow-up image processing.

• 한국멀티미디어학회논문지
• /
• 제21권9호
• /
• pp.1044-1051
• /
• 2018

In this paper, we propose a new method to improve low light image. In order to improve the image quality of a night image with a moving object as much as the quality of a daytime image, the following tasks were performed. Firstly, we reduce the noisy of the input night image and improve the night image by the tone mapping method. Secondly, we segment the input night image into a foreground with motion and a background without motion. The motion is detected using both the difference between the current frame and the previous frame and the difference between the current frame and the night background image. The background region of the night image takes pixels from corresponding positions in the daytime image. The foreground regions of the night image take the pixels from the corresponding positions of the image which is improved by the tone mapping method. Experimental results show that the proposed method can improve the visual quality more clearly than the existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권7호
• /
• pp.3245-3271
• /
• 2016

To obtain well-dehazed images at the receiver while sustaining low bit rates in the transmission pipeline, this paper investigates the effects of image dehazing methods using dehazing contrast-enhancement filters on image compression for surveillance systems. At first, this paper proposes a novel image dehazing method by using a new method of calculating the transmission function—namely, the direct denoising method. Next, we deduce the dehazing effects of the direct denoising method and image dehazing method based on dark channel prior (DCP) on image compression in terms of ringing artifacts and blocking artifacts. It can be concluded that the direct denoising method performs better than the DCP method for decompressed (reconstructed) images. We also improve the direct denoising method to obtain more desirable dehazed images with higher contrast, using the saliency map as the guidance image to modify the transmission function. Finally, we adjust the parameters of dehazing contrast-enhancement filters to obtain a corresponding composite peak signal-to-noise ratio (CPSNR) and blind image quality assessment (BIQA) of the decompressed images. Experimental results show that different filters have different effects on image compression. Moreover, our proposed dehazing method can strike a balance between image dehazing and image compression.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3092-3107
• /
• 2019

Visible-infrared image fusion is a process of synthesizing an infrared image and a visible image into a fused image. This process synthesizes the complementary advantages of both images. The infrared image is able to capture a target object in dark or foggy environments. However, the utility of the infrared image is hindered by the blurry appearance of objects. On the other hand, the visible image clearly shows an object under normal lighting conditions, but it is not ideal in dark or foggy environments. In this paper, we propose a multi-guided filter and a real-time image fusion method. The proposed multi-guided filter is a modification of the guided filter for multiple guidance images. Using this filter, we propose a real-time image fusion method. The speed of the proposed fusion method is much faster than that of conventional image fusion methods. In an experiment, we compare the proposed method and the conventional methods in terms of quantity, quality, fusing speed, and flickering artifacts. The proposed method synthesizes 57.93 frames per second for an image size of $320{\times}270$. Based on our experiments, we confirmed that the proposed method is able to perform real-time processing. In addition, the proposed method synthesizes flicker-free video.

• 한국광학회지
• /
• 제34권2호
• /
• pp.61-65
• /
• 2023

본 논문은 고보 조명 광학계의 image mask에 사전 왜곡을 적용하여, image를 선명하게 조사 및 보정하는 방법을 연구하였다. 고보 조명 광학계의 경우, 일반적으로 기울여 조사되는 경우가 많기 때문에 image에서 상·하 방향의 왜곡이 심하게 발생한다. 이러한 문제점을 해결하기 위해 비례식을 이용해 image의 보정 좌표를 도출하고, 이를 image mask에 적용하여 왜곡을 보정하였다. 그 결과, 기존 image mask를 사용하였을 경우에 비해 왜곡이 64.5% 감소되는 것을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2385-2388
• /
• 2005

In this paper, we propose the estimation method for the image affine information for computer vision. The first estimation method is given based on the XYS image normalization and the second estimation method is based on the image normalization by Pei and Lin. The XYS normalization method turns out to have better performance than the method by Pei and Lin. In addition, we show that rotation and aspect ratio information can be obtained using the central moments of both the original image and the sensed image. Finally, we propose the modified version of the normalization method so that we may control the size of the image.