• 한국지능시스템학회논문지
• /
• 제17권3호
• /
• pp.328-335
• /
• 2007

온톨로지는 공유된 개념과 그 개념들 사이의 관계로 표현된다. 이러한 온톨로지를 사용하여 인간과 시스템에 대한 지식의 공유에 관한 연구가 활발히 이루어져 왔다. 예를 들면, 온톨로지의 설계 및 구축에 의한 영상이해를 들 수 있다. 그러나 온톨로지에 기반한 영상이해 방식 중 대부분의 기존 방식은 개념적인 연구에 그칠 뿐 구체적인 방법을 제시하지는 못하였다. 본 논문에서는 온톨로지로 표현된 지식에 근거하여 영상을 이해하는 다음과 같은 영상이해 프로세스 및 시스템을 제안한다. i)특정 분야의 지식을 온톨로지로 표현하고, ii)영상 처리 및 분석 과정을 통해 영상을 구성하는 객체들의 특징을 추출하며, iii)객체의 특징으로부터 객체의 개념을 해석하고, iv)온톨로지 추론을 통해 영상 해석 과정에서의 애매성을 줄인다. 제안된 영상 이해 프로세스에 기반하여 영상이해 시스템을 구축하고, 특정 분야에서의 실험을 통하여 제안된 프로세스와 시스템의 효용성을 확인한다.

• ETRI Journal
• /
• 제42권3호
• /
• pp.399-410
• /
• 2020

Detecting visual relationships in an image is important in an image understanding task. It enables higher image understanding tasks, that is, predicting the next scene and understanding what occurs in an image. A visual relationship comprises of a subject, a predicate, and an object, and is related to visual, language, and spatial cues. The predicate explains the relationship between the subject and object and can be categorized into different categories such as prepositions and verbs. A large visual gap exists although the visual relationship is included in the same predicate. This study improves upon a previous study (that uses language cues using two losses) and a spatial cue (that only includes individual information) by adding relative information on the subject and object of the extant study. The architectural limitation is demonstrated and is overcome to detect all zero-shot visual relationships. A new problem is discovered, and an explanation of how it decreases performance is provided. The experiment is conducted on the VRD and VG datasets and a significant improvement over previous results is obtained.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.235-240
• /
• 2004

In this paper, we propose a framework for ontological knowledge-based image understanding systems. Ontology composed of concepts can be used as a guide for describing objects from a specific domain of interest and describing relations between objects from different domains The proposed framework consists of four main subparts ⅰ) ontological knowledge bases, ⅱ) primitive feature detectors, ⅲ) concept inference engine, and ⅳ) semantic inference engine. Using ontological knowledge bases on various domains and features extracted from the detectors, concept inference engine infers concepts on regions of interest in an image and semantic inference engine reasons semantic situations between concepts from different domains. We present a outline for ontological knowledge-based image understanding systems and application examples within specific domains such as text recognition and human recognition in order to show the validity of the proposed system.

• 한국실내디자인학회논문집
• /
• 제15권6호
• /
• pp.238-246
• /
• 2006

Recent trends of interior design have a focus on creation of more various meanings rather than past ideology which sought after the compatibility to the function of modem design. These trends requires integral understanding of social and cultural ideologies with a sens of values for a certain periods. In addition, they also require creativity which able to read, find and solve consumer's diverse demand and desire. Considering the effort of trend forecasting in Korea is still heavily rely on the foreign trend shows, it is natural to attempt to study the analytical forecasting methodology based upon more systematic principles which lead to more objective outcome, when the understanding, forcasting and analysis of interior decoration trend are required. In this thesis, the analysis and forecasting of interior decoration trend are studied by means of verbal image code process which involves the induction of design concept through data extraction, classification and analysis, in order to understanding and satisfying the diversified consumer's demand and trend. The coding process of verbal image is understanding as general concept. by extracting common elements from abstract and individual image, and/or specific concept. Therefore, it is proposed that the database building and data mining process of verbal Image, and subsequent development of programming skill can be applied as more efficient tool for various verbal image process.

• 대한전자공학회논문지
• /
• 제24권6호
• /
• pp.961-968
• /
• 1987

This paper describes an intelligent image compression system called AIIC which is capable of adjusting image compression ratios ranging from 1:1 to 12,000:1 depending on available bandwidth. This system utilizes not only conventional image compression algorithms but also intelligent techniques through understanding image contents to achieve ultra-high compression ratios. This system was simulated on a micro-computer network.

• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 1997년도 International Conference MULTIMEDIA DATABASES on INTERNET
• /
• pp.24-48
• /
• 1997

. Supported byㆍDARPA′s image Understanding (IU) program under "Video Retrieval Based on Language and image Analysis" project.DARPA′s Computer Assisted Education and Training Initiative program (CAETI)ㆍObjective: Develop practical systems for automatic understanding and indexing of video sequences using both audio and video tracks(omitted)

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1171-1178
• /
• 2019

This study proposes a deep neural network model based on an encoder-decoder structure for visual dialogs. Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual features extracted from the entire input image at the encoding stage using a convolutional neural network, we emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark dataset, confirmed that the proposed model performed well.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.333-335
• /
• 2015

A computer vision-based scene recognition algorithm is proposed for monitoring construction sites. The system analyzes images acquired from a surveillance camera to separate regions and classify them as building, ground, and hole. Mean shift image segmentation algorithm is tested for separating meaningful regions of construction site images. The system would benefit current monitoring practices in that information extracted from images could embrace an environmental context.

• 게임&엔터테인먼트 논문지
• /
• 제1권1호
• /
• pp.31-38
• /
• 2005

게임개발에 사용되어지는 여러 가지 공정 중 게임제작의 정확한 흐름. 그리고 제작에 대한 이해가 보다 정확한 게임을 제작하리라 여긴다. 게임의 원인제공이 되는 영상제작에 있어 정확한 공정이해와 3D게임영상제작이해에 중심을 둔다. 실제 게임제품에 있어서는 게임을 기동했을 때에 표시되는 오프닝 무비, 이벤트 때에 삽입되는 Cut Scene등의 영상이 이 방법으로 생성되고 있다. 게임과는 다르지만 극장 영화에 있어서 특수효과 영상에서 3D게임영상이 이용되는 것이 게임 제작 시 고려되어야 할 그래픽이다. 게임플레이어가 보다 정확한 원인제공으로 그 게임에 몰입 할 수 있는 원인을 제공하리라 여겨진다.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.926-930
• /
• 2006

Current image retrieval techniques have shortcomings that make it difficult to search for images based on a semantic understanding of what the image is about. Since an image is normally associated with multiple contexts (e.g. when and where a picture was taken,) the knowledge of these contexts can enhance the quantity of semantic understanding of an image. In this paper, we present a context-aware image retrieval system, which uses the context information to infer a kind of metadata for the captured images as well as images in different collections and databases. Experimental results show that using these kinds of information can not only significantly increase the retrieval accuracy in conventional content-based image retrieval systems but decrease the problems arise by manual annotation in text-based image retrieval systems as well.