• 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.

• 한국의류학회지
• /
• 제33권4호
• /
• pp.644-654
• /
• 2009

The purpose of this study is to analyze the characteristics of current fashion illustrations within the framework of Multi-space method. Multi-space means being piled up one moment & space on others, and being amassed in a scene. This method is related with Dadaism, Surrealism and Postmodernism, and also influences on the current fashion illustration. In this study, the types of Multi-space method could be classified into 4 types; Repetitive Time Mixture in Multi-space, Juxtaposed Time Mixture in Multi-space, Reiterated Space Mixture in Multi-space, Projected Space Mixture in Multi-space. The characteristics of Multi-space were analyzed and the results are as followed. The distinctive methods for Time Mixture in Multi-space are repetition and juxtaposition in a scene. Time Mixture in Multi-space can make the nonlinear narration and unreal illusory space in fashion illustrations more effectively. Reiterated Space Mixture in Multi-space can be related with the heterogeneous, surrealistic illusions in current fashion illustrations. Projected Space Mixture in Multi-space can be characterized into inter-penetration. It can derive spectators to mix the projected & transparent images in a scene for their own imaginary stories. The final imagination can be made differently according to the personal experiences of spectators.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.148-153
• /
• 2009

Few methods have dealt with segmenting multiple images with analogous content. Concurrent images of a scene and gathered images of a similar foreground are examples of these images, which we term consistent scene images. In this paper, we present a method to segment these images based on manual segmentation of one image, by iteratively propagating information via multi-level cues with adaptive confidence. The cues are classified as low-, mid-, and high- levels based on whether they pertain to pixels, patches, and shapes. Propagated cues are used to compute potentials in an MRF framework, and segmentation is done by energy minimization. Through this process, the proposed method attempts to maximize the amount of extracted information and maximize the consistency of segmentation. We demonstrate the effectiveness of the proposed method on several sets of consistent scene images and provide a comparison with results based only on mid-level cues [1].

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권5호
• /
• pp.2576-2589
• /
• 2017

Co-saliency detection is a task of detecting same or similar objects in multi-scene, and has been an important preprocessing step for multi-scene image processing. However existing methods lack efficiency to match similar areas from different images. In addition, they are confined to single image detection without a unified framework to calculate co-saliency. In this paper, we propose a novel model called Superpixel Matching-Cellular Automata (SMCA). We use Hausdorff distance adjacent superpixel sets instead of single superpixel since the feature matching accuracy of single superpixel is poor. We further introduce Cellular Automata to exploit the intrinsic relevance of similar regions through interactions with neighbors in multi-scene. Extensive evaluations show that the SMCA model achieves leading performance compared to state-of-the-art methods on both efficiency and accuracy.

• 방송공학회논문지
• /
• 제18권6호
• /
• pp.895-910
• /
• 2013

멀티스크린 서비스(Multi-screen service)는 하나 이상의 미디어를 복수개의 단말에서 동시에 또는 차별적으로 소비하는 서비스로서, 이러한 멀티스크린 서비스는 기존 TV의 스마트화 및 스마트 단말의 보편화에 따라 그 활용성이 더욱 높아지고 있다. 또한 방송통신 융합 환경인 하이브리드 방송(Hybrid Broadcasting) 환경에 적용할 경우, 여러 개의 화면을 통해 여러 소스의 콘텐츠를 소비하여 다양한 사용자 경험(User experience)을 제공할 수 있다. 하이브리드 방송 환경에서 멀티스크린 서비스를 제공하기 위한 요소기술로서 장면구성기술을 활용할 수 있다. 장면구성 기술은 미디어가 소비되는 시간과 화면상의 공간을 특정함으로써 다수의 미디어를 복합적으로 소비하는 방법으로서, 해당 기술을 통해 제공되는 멀티스크린 서비스는 단말 간의 연계를 통한 복수 미디어의 시공간적 제어 및 소비를 제공할 수 있다. 하지만 기존의 장면구성 기술은 적용 가능한 환경의 제약과 다양한 단말에 대한 적용이 어렵다는 점, 활용의 복잡성 등으로 인해 하이브리드 방송 환경에 쉽게 적용하기 어려운 점이 존재한다. 이러한 문제점을 해결할 수 있는 새로운 환경으로 HTML5를 고려할 수 있다. HTML5는 개방형 네트워크를 활용하는 다양한 스마트 단말에 공통적으로 적용될 것으로 기대되며, 기존 HTML에 비해 다양한 종류의 미디어의 소비를 지원한다. 이에 본 논문에서는 하이브리드 방송환경이 적용될 다양한 스마트기기에서 사용될 것으로 예상되는 HTML5을 기반으로 한 장면구성 및 멀티스크린 서비스 기술을 제안한다. 이를 위해, 본 논문에서는 HTML5 및 멀티스크린 서비스와 관련된 기술을 소개하고, HTML5의 요소 및 속성의 확장을 통한 장면구성 및 멀티스크린 서비스 정보 제공 방법과 멀티스크린 서비스를 위한 단말 간 미디어 시그널링 및 동기화 방법을 제안하였다. 또한, 제안된 HTML5 기반 장면구성 및 멀티스크린 서비스 적용 방안을 구현 및 실험을 통해 검증하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.551-552
• /
• 2021

본 논문에서는 변환 학습에 기반을 둔 다중 클래스 영상 장면 분류 방법을 제시한다. ImageNet 대형 이미지 데이터 세트에서 사전 훈련된 네트워크 모델에 의존하여 다중 클래스의 자연 장면 이미지를 분류한다. 실험에서는 최적화된 ResNet 모델을 Kaggle의 Intel Image Classification 데이터 셋에 분류하여 우수한 결과를 얻었다.

• 대한원격탐사학회지
• /
• 제17권3호
• /
• pp.189-197
• /
• 2001

원격탐사의 장점 중 하나는 넓은 지역의 정보를 신속하게 추출할 수 있다는 것이다. 이러한 장점은 광역지대의 토지피복을 분류하여 자원 및 환경을 신속하게 파악하고자 하는 수요에 부응할 수 있는 효과적인 수단이다. 이 연구에서는 다량의 위성영상을 이용하여 넓은 지역의 토지피복분류를 효율적으로 수행하는 방법을 제안하였다. 이를 위해 한반도를 대상으로 Landsat TM 및 ETM+ 위성영상 23 scene을 이용하여 공간해상도 100m인 토지피복분류를 수행하였다. 기존의 정형화된 위성영상처리 및 분류기법을 적용하여 다량의 위성영상을 처리하고 광역 토지피복분류를 효율적으로 수행하였다. 이러한 방법은 국토계획이나 광역 지역계획 등에서 필요한 전반적인 자원현황을 신속하고 효과적으로 제공할 수 있는 수단이 될 것으로 판단된다.

• 한국실내디자인학회논문집
• /
• 제16권3호
• /
• pp.21-29
• /
• 2007

The communication in a play has a dual structure, which is composed of the communications within a play and in a theatre space. This research focuses on the scene design that creates the background or the theme of a play and communicates theme of a play to the audience. A scene design of a theatre has meta-linguistic aspects, which is the image or mood as the theme of a play. The scene design is composed of various design elements of space and objects as the properties of a play. Design elements and the objects are the design languages in various form; plane, three-dimensional, multi-dimensional form. These design languages have the significant meanings as signs like human language. The play works chooses the rhetorical expression to arouse the audience's sympathy. The scene design is completed with rhetorical expression for communication in theatre too. This research defines the category of meanings that design elements of scene design can create and the rhetorical expression of the scene design language. King Lear directed by Robert G. Anderson was analyzed with the category of design elements as a sign and the pattern of the rhetorical expression. The scene design for a play is completed effectively by the rhetorical expression of design elements as the design language for the communication with the audience in theatre.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권3호
• /
• pp.175-182
• /
• 2017

In this paper, we present a multi-depth generation method using a time-of-flight (ToF) fusion camera system. Multi-view color cameras in the parallel type and ToF depth sensors are used for 3D scene capturing. Although each ToF depth sensor can measure the depth information of the scene in real-time, it has several problems to overcome. Therefore, after we capture low-resolution depth images by ToF depth sensors, we perform a post-processing to solve the problems. Then, the depth information of the depth sensor is warped to color image positions and used as initial disparity values. In addition, the warped depth data is used to generate a depth-discontinuity map for efficient stereo matching. By applying the stereo matching using belief propagation with the depth-discontinuity map and the initial disparity information, we have obtained more accurate and stable multi-view disparity maps in reduced time.

• 한국실내디자인학회:학술대회논문집
• /
• 한국실내디자인학회 2007년도 춘계학술대회 논문집
• /
• pp.176-180
• /
• 2007

The stage space in theatre for the performance of a play requires two aspects of the physical space for a play and the image as the background or the theme of a play. This research focuses on the scene design that creates the background or the theme of a play and communicates it to the audience. The scene design is composed of various design elements of space and objects as the properties of a play. Design elements and the objects are the design languages in various form; plane, three-dimensional, multi-dimensional form. These design language have the significant meaning as a sign like human language. The scene design is completed with rhetorical expression for communication in theatre. This research defines the category of meaning that design elements of scene design can create and the rhetorical expression of the scene design language. King Lear directed by Robert G. Anderson was analyzed with the category of design elements as a sign and the pattern of the rhetorical expression. The scene design for a play is completed effectively by the rhetorical expression of design elements as the design language for communication with the audience in theatre.