• Title/Summary/Keyword: Image-development

Search Result 6,191, Processing Time 0.03 seconds

Deep Multi-task Network for Simultaneous Hazy Image Semantic Segmentation and Dehazing (안개영상의 의미론적 분할 및 안개제거를 위한 심층 멀티태스크 네트워크)

  • Song, Taeyong;Jang, Hyunsung;Ha, Namkoo;Yeon, Yoonmo;Kwon, Kuyong;Sohn, Kwanghoon
    • Journal of Korea Multimedia Society
    • /
    • v.22 no.9
    • /
    • 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.

Image Deduplication Based on Hashing and Clustering in Cloud Storage

  • Chen, Lu;Xiang, Feng;Sun, Zhixin
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.15 no.4
    • /
    • pp.1448-1463
    • /
    • 2021
  • With the continuous development of cloud storage, plenty of redundant data exists in cloud storage, especially multimedia data such as images and videos. Data deduplication is a data reduction technology that significantly reduces storage requirements and increases bandwidth efficiency. To ensure data security, users typically encrypt data before uploading it. However, there is a contradiction between data encryption and deduplication. Existing deduplication methods for regular files cannot be applied to image deduplication because images need to be detected based on visual content. In this paper, we propose a secure image deduplication scheme based on hashing and clustering, which combines a novel perceptual hash algorithm based on Local Binary Pattern. In this scheme, the hash value of the image is used as the fingerprint to perform deduplication, and the image is transmitted in an encrypted form. Images are clustered to reduce the time complexity of deduplication. The proposed scheme can ensure the security of images and improve deduplication accuracy. The comparison with other image deduplication schemes demonstrates that our scheme has somewhat better performance.

A Study on the Design Characteristics of Athleisure Look in Image-based SNS (이미지 기반 SNS에 나타난 애슬레저 룩의 디자인 특성 연구)

  • Kwon, Suehee;Park, Minjung
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.45 no.1
    • /
    • pp.17-27
    • /
    • 2021
  • The pursuit of a healthier life has created life style changes through exercise; in addition, an athleisure look as well as a combination of everyday clothes and sportswear has rapidly spread through sharing based on image-based SNS. Fashion related images shown in an image-based SNS are considered important resources for grasping micro-needs with regard to the sensibility of consumers. Therefore, this study analyzes the design characteristics of an athleisure look shown in image-based SNS. In order to analyze the athleisure look, images of the entire garment were collected and classified to enable content analysis methods that analyzed the design characteristics of each type. As a result, types were classified as sporty-athleisure, modern-athleisure, high-end athleisure, retro-athleisure, and romantic-athleisure. Looking at the characteristics of the athleisure look, it was shown that the design characteristics of each type were well expressed through differences in the direction, material, and details by matching between the items used. This study can be used in design development processes by deriving the characteristics of athleisure looks through an analysis of fashion images that appear in image-based SNS.

CNN-Based Fake Image Identification with Improved Generalization (일반화 능력이 향상된 CNN 기반 위조 영상 식별)

  • Lee, Jeonghan;Park, Hanhoon
    • Journal of Korea Multimedia Society
    • /
    • v.24 no.12
    • /
    • pp.1624-1631
    • /
    • 2021
  • With the continued development of image processing technology, we live in a time when it is difficult to visually discriminate processed (or tampered) images from real images. However, as the risk of fake images being misused for crime increases, the importance of image forensic science for identifying fake images is emerging. Currently, various deep learning-based identifiers have been studied, but there are still many problems to be used in real situations. Due to the inherent characteristics of deep learning that strongly relies on given training data, it is very vulnerable to evaluating data that has never been viewed. Therefore, we try to find a way to improve generalization ability of deep learning-based fake image identifiers. First, images with various contents were added to the training dataset to resolve the over-fitting problem that the identifier can only classify real and fake images with specific contents but fails for those with other contents. Next, color spaces other than RGB were exploited. That is, fake image identification was attempted on color spaces not considered when creating fake images, such as HSV and YCbCr. Finally, dropout, which is commonly used for generalization of neural networks, was used. Through experimental results, it has been confirmed that the color space conversion to HSV is the best solution and its combination with the approach of increasing the training dataset significantly can greatly improve the accuracy and generalization ability of deep learning-based identifiers in identifying fake images that have never been seen before.

Analysis on the Importance of Beautiful Place Images Recognition Using AHP (AHP를 활용한 아름다운 장소 이미지의 중요도 인식 분석)

  • Lee, Lim-Jung;Cho, Chi-Woung;Noh, Kyung-Ran
    • Journal of the Korean Institute of Rural Architecture
    • /
    • v.24 no.2
    • /
    • pp.1-11
    • /
    • 2022
  • Purpose: The purpose of this study is to analyze image factors of places located in natural and humanistically superior geographical locations. It aims to analyze image recognition and spatiality of scenically historical Sahmyook University, located northeast of Gangneung, through standardization. Method: The analysis method of landscape is composed of data investigation and research, and elements of how students, faculty, and visitors recognize a place's beautiful image will be examined. Result: A phenomenological approach was applied to how the images of beautiful place were set by FGI group meeting, and how such factors affect beautiful place's perception from the user's point of view. When looking at comprehensive ranking of image factors in recognition of beautiful landscapes, factors corresponding to forest landscapes appear at the top rank. In determining factors for its recognition, shared space with natural elements such as water, trees, flowers, etc. has been analyzed to have the biggest influence. Among factors corresponding to urban landscape, 'streets and pedestrian paths' is of medium importance and are recognized for it is artificial structure coexisting with natural elements shared with humans. The image corresponding to 'city area' and 'architecture' was analyzed to have insignificant influence on beautiful places' image recognition for artificial element was prioritized.

A Research on Aesthetic Aspects of Checkpoint Models in [Stable Diffusion]

  • Ke Ma;Jeanhun Chung
    • International journal of advanced smart convergence
    • /
    • v.13 no.2
    • /
    • pp.130-135
    • /
    • 2024
  • The Stable diffsuion AI tool is popular among designers because of its flexible and powerful image generation capabilities. However, due to the diversity of its AI models, it needs to spend a lot of time testing different AI models in the face of different design plans, so choosing a suitable general AI model has become a big problem at present. In this paper, by comparing the AI images generated by two different Stable diffsuion models, the advantages and disadvantages of each model are analyzed from the aspects of the matching degree of the AI image and the prompt, the color composition and light composition of the image, and the general AI model that the generated AI image has an aesthetic sense is analyzed, and the designer does not need to take cumbersome steps. A satisfactory AI image can be obtained. The results show that Playground V2.5 model can be used as a general AI model, which has both aesthetic and design sense in various style design requirements. As a result, content designers can focus more on creative content development, and expect more groundbreaking technologies to merge generative AI with content design.

Examining City Image from the Application of Country Image: The Case of Daegu City (국가이미지를 응용한 도시이미지 연구: 대구시를 중심으로)

  • Park, Kyung-Ae
    • Journal of the Korean association of regional geographers
    • /
    • v.10 no.1
    • /
    • pp.96-109
    • /
    • 2004
  • Applying the construct of country image this study examined city image for Daegu in Korea. Study 1 measured the city image for Daegu and Seoul, identified the city image dimensions, and compared the images of the two cities. Study 2 confirmed the city image dimensions and examined the Daegu image by residency and demographic characteristics of respondents in Daegu and Seoul regions. The study extracted 4 dimensions of city image including economy, people, conservatism, and development capability. High conservatism and low economic prosper represented the image of Daegu while the opposite did of Seoul. Regardless of residency, single and Young respondents with high income and education had negative images for Daegu, and residents in Daegu rather than in Seoul had more negative images.

  • PDF

The Analysis of the Image of Kongju City Based on Citizen - Image Positioning by Adjectives of City and Landmarks - (시민의식에 기초한 공주시 도시 이미지 분석 - 도시와 랜드마크의 형용사 이미지 포지셔닝 -)

  • Cheong Yong-Moon;Byeon Jae-Sang
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.33 no.3 s.110
    • /
    • pp.18-30
    • /
    • 2005
  • Since the 1990s, with the beginning of local autonomy, most Korean cities have tried to establish and reinforce their own identity. The Law on the Planning and the Use of National Land, which took effect in January 2003, requires major and minor cities to manage and develop a city image and a marketing strategy to reflect their current condition. However, many cities continue to experience confusion in implementing urban landscape planning because no efficient and systematic method has been provided for the analysis of a city's image. The absence of systematic analysis methods makes it difficult not only to assess the current condition of a city accurately but also to choose an appropriate policy for the given city. Consequently, many cities suffer excessive trials and errors in implementing the correct policies for their city. The purpose of this study was to analyze the image: of Kongju, which has many historical properties. For this purpose, adjective questionnaires and multi-dimensional scaling (MDS) were made use of in order to assess the city image. The results of this study can be summarized as follows: 1. There are five properties that serve as landmarts lie symbolize Kongju: Muryeong royal tomb, Castle Kong, Mt. Gyeoiryong, Forest Museum, and Kongju National Museum. 2. Based on the citizen survey regarding the city type, Kongju is seen as a historical and an educational city. 3. Based on the image positioning (image spatial plot), Kongju is described as an old and familiar city. There we, however, no landmarks which are in accord with the image of Kongju. It is difficult to establish and reinforce the image of a city with a single element like a landmark However, with steady follow-up research, this study may serve as a systematic and logical model to improve the urban landscape and image.

Development of compound eye image quality improvement based on ESRGAN (ESRGAN 기반의 복안영상 품질 향상 알고리즘 개발)

  • Taeyoon Lim;Yongjin Jo;Seokhaeng Heo;Jaekwan Ryu
    • Journal of the Korea Computer Graphics Society
    • /
    • v.30 no.2
    • /
    • pp.11-19
    • /
    • 2024
  • Demand for small biomimetic robots that can carry out reconnaissance missions without being exposed to the enemy in underground spaces and narrow passages is increasing in order to increase the fighting power and survivability of soldiers in wartime situations. A small compound eye image sensor for environmental recognition has advantages such as small size, low aberration, wide angle of view, depth estimation, and HDR that can be used in various ways in the field of vision. However, due to the small lens size, the resolution is low, and the problem of resolution in the fused image obtained from the actual compound eye image occurs. This paper proposes a compound eye image quality enhancement algorithm based on Image Enhancement and ESRGAN to overcome the problem of low resolution. If the proposed algorithm is applied to compound eye image fusion images, image resolution and image quality can be improved, so it is expected that performance improvement results can be obtained in various studies using compound eye cameras.

Study on the Development and Application of Image Viewer System (Image Viewer System의 개발 및 적용에 관한 고찰)

  • Yang, Oh-Nam;Seo, In-Ki;Hong, Dong-Ki;Kwon, Kyeong-Tae
    • The Journal of Korean Society for Radiation Therapy
    • /
    • v.18 no.2
    • /
    • pp.67-73
    • /
    • 2006
  • Purpose: The number of patients receiving radiotherapy has increased every year and will keep increasing in the future. Therefore, the technique of radiotherapy is developing from day to day, as a result of it, the quantities of image and data used for radiotherapy are also considerably increasing. Therefore, there have been many difficulties in storing, keeping and managing them. Then, we developed and applied this system for improving complicated work process as well as solving these problems with the collaboration Medical Information Team. Materials and Methods: We exported its image at R & V (Record and Verify: Varis vision, Varian, USA) system and planning system after giving some code to be able to access from management system(RO) for department of radiation oncology to PACS. And, we programmed their information by using necessary information among many information included in DICOM head. Results: All images and data generated by our working environment (Simulation CT, L-gram image and internal body structure, DRR, does distribution )were realized at PACS and it became to be possible for clear image to be printed from any computer in department of radiation oncology. Conclusion: It was inevitable to use film during radiotherapy for patients in the past, however, due to the development of this system, film-less system became to be possible. Therefore, the darkroom space and its management cost in relation to the development process disappeared and it became to be unnecessary for spending tangible and intangible financial expense including human resources, time needed for finding film storing space and film and purchasing separate storing equipment for storing images. Finally, we think this system would be very helpful to handle ail complicated processes for radiotherapy and increasing efficiency of overall working conditions.

  • PDF