• Journal of the Korea Computer Graphics Society
• /
• v.24 no.5
• /
• pp.1-10
• /
• 2018

In this paper, we present a non-photorealistic rendering technique that automatically delivers a stylized abstraction of a photograph with DoF(Depth of field). Our approach is a new filtering method that efficiently classifies DoF regions using RGB channels and automatically adjusts the color abstraction and extracted line quality based on this classification. This DoF-based filtering is simple, fast, and easy to implement and significantly improves the abstraction performance in terms of feature enhancement and stylization.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1113-1119
• /
• 2006

본 논문에서는 광고나 포스터제작에 사용될 수 있는 이미지 모자이크 기법을 소개한다. 모자이크는 임의의 개수의 셀로 하나의 전체 이미지를 표현하는 기법이다. 이중 포토 모자이크는 사진의 조합으로 새로운 사진을 생성한다. 이는 만들고자 하는 영상을 격자를 이용해 나누고 해당 격자에 최적의 이미지를 영상 DB 로부터 찾아 격자를 채움으로써 하나의 이미지 모자이크를 생성한다. 본 논문에서는 하나의 단위 이미지(색이 할당되지 않고 형태만 갖는 영상)를 사용하여 경계로 구분된 특정 영역을 채워나감으로써 하나의 추상화된 예술적 모자이크 영상을 생성하는 알고리즘을 소개한다. 하나의 단위 이미지는 회전, 이동을 통해 다양하게 변할 수 있으며 입력영상의 그래디언트의 방향과 에지정보를 이용해 해당영역을 채우게 된다. 이를 위해서 에지를 넘어서지 않도록 단위 이미지를 변환시키며 최적의 위치를 찾게된다. 또한 입력영상의 색상이나 임의의 색상이나 특정 색상테이블을 이용해 단위 이미지에 색상을 할당함으로써 만들고자 하는 입력영상과 비슷한 모양을 갖거나 형태만을 유지한 추상화된 모자이크 영상 생성이 가능하다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.59-70
• /
• 2021

With the recent advancements in the Internet of Things, context-aware system that provides customized services become important to consider. The existing context-aware systems analyze data generated around the user and abstract the context information that expresses the state of situations. However, these datasets is mostly unstructured and have difficulty in processing with simple approaches. Therefore, providing context-aware services using the datasets should be managed in simplified method. One of examples that should be considered as the unstructured datasets is a deep learning application. Processes in deep learning applications have a strong coupling in a way of abstracting dataset from the acquisition to analysis phases, it has less flexible when the target analysis model or applications are modified in functional scalability. Therefore, an abstraction model that separates the phases and process the unstructured dataset for analysis is proposed. The proposed abstraction utilizes a description name Analysis Model Description Language(AMDL) to deploy the analysis phases by each fat client is a specifically designed instance for resource-oriented tasks in edge computing environments how to handle different analysis applications and its factors using the AMDL and Fat client profiles. The experiment shows functional scalability through examples of AMDL and Fat client profiles targeting a vehicle image recognition model for vehicle access control notification service, and conducts process-by-process monitoring for collection-preprocessing-analysis of unstructured data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.830-833
• /
• 2021

인공지능 기술이 사회 전반에 적용되면서 인공지능에 대한 인간의 이해도 역시 중요해지고 있다. 이러한 필요성을 기반으로 설명 가능한 인공지능(XAI) 분야 연구가 현재 활발히 진행되고 있다. 이 중 입력의 변화를 통하여 반사실적 대안을 제시하는 반사실적 예제 기반의 설명은 피쳐수가 많아지는 이미지 데이터에서 연산량이 크게 증가하는 단점이 있다. 본 연구에서는 이러한 단점을 해결하고자 이미지의 추상화된 피쳐 영역에서 프로토타입 피쳐를 이용한 반사실적 예제를 생성하는 기법을 제안한다. 나아가 이러한 이미지 형식의 반사실적 예제를 활용할 분야를 제시하고자 한다.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.209-220
• /
• 2024

A sketch is an intuitive means to express information, but compared to actual images, it has the problem of being highly abstract, diverse, and sparse. Recent advances in deep learning models have made it possible to discover features that are common to images and sketches. In this paper, we summarize recent trends in sketch-based image retrieval (SBIR) but it is not limited to SBIR. Besides SBIR, we also introduce sketch-based image recognition and generation studies. Zero-shot learning enables models to recognize categories not encountered during training. Zero-shot SBIR methods are also discussed. Commonly used free-hand sketch datasets are summarized and retrieval performance based on these datasets is reported.

• Journal of the Korea Computer Graphics Society
• /
• v.17 no.1
• /
• pp.33-38
• /
• 2011

This paper proposes the method of image cartooning, that makes cartoon-like images of a target, using reference images. We deform a target image using pre-defined reference images. For this deformation, we extract feature points from the target image by Active Appearance Model(AAM) and apply the warping method to the target using feature points of target and feature points of reference image as a basis of warping function. We create simplified cartoon-like images by abstraction of the deformed target image and drawing of edges and quantization of luminance of the abstracted image. Two main concept of cartoon(exaggeration and simplification) is inhered in this method when we use a exaggerated cartoon image as a reference image. It is possible for this method to create various results by control of warping and change of reference image.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.76-82
• /
• 2017

Malware, including ransomware to quickly detect, in this study, to provide an analysis method of malicious code through the image analysis that has been learned in the deep learning of artificial intelligence. First, to analyze the 2,400 malware data, and learning in artificial neural network Convolutional neural network and to image data. Extracts subgraphs to convert the graph of abstracted image, summarizes the set represent malware. The experimentally analyzed the malware is not how similar. Using deep learning of artificial intelligence by classifying malware and It shows the possibility of accurate malware detection.

• Korean Journal of Cognitive Science
• /
• v.25 no.3
• /
• pp.259-276
• /
• 2014

Artists such as Duchamp and Balla tried to portray moving objects on static canvases by superimposing snapshots of moving objects. Previously, our group showed the influence of prior experience on brain responses within a motion-sensitive area MT+ to abstr act paintings with or without implied motion. In the present study, we went further to investigate whether the differential MT+activation between observers is originated from differential eye movement patterns. Prior experience was defined operationally with major in art. In addition, we examined whether perceiver's awareness of artist's intention concerning the implied motion, as well as expertise in art, affects the way he/she views the artwork. Results showed that the number and the duration of fixation on the abstract paintings tended to differ between participants based on art major. The awareness of artist's intention was not related to such differences. In contrast, observers' awareness of artist's intention of implying motion affected eye movement patterns in specific regions of the abstract paintings where the motion was portrayed. In other words, observers with awareness focused more on the parts of paintings portraying motion and moved their eyes in the direction corresponding to the direction of moving objects than observers without awareness. Expertise was not related to such specific eye movement patterns. The present study implies that art expertise and awareness of artist's intention play differential roles in observers' perception of paintings with implied motion. Namely, it suggests that expertise is related to the overall perception of paintings, while awareness of implied motion is related to perception of the specific spatial information in those paintings.

• Journal of KIISE:Databases
• /
• v.32 no.4
• /
• pp.383-393
• /
• 2005

Retrieval of images from image databases by spatial relationship can be effectively performed through visual interface systems. In these systems, the representation of image with 2D strings, which are derived from symbolic projections, provides an efficient and natural way to construct image index and is also an ideal representation for the visual query. With this approach, retrieval is reduced to matching two symbolic strings. However, using 2D-string representations, spatial relationships between the objects in the image might not be exactly specified. Ambiguities arise for the retrieval of images of 3D scenes. In order to remove ambiguous description of object spatial relationships, in this paper, images are referred by considering spatial relationships using the spatial location algebra for the 3D image scene. Also, we remove the repetitive spatial relationships using the several reduction rules. A reduction mechanism using these rules can be used in query processing systems that retrieve images by content. This could give better precision and flexibility in image retrieval.

• Science of Emotion and Sensibility
• /
• v.14 no.3
• /
• pp.403-414
• /
• 2011

The current study examined brain regions associated with aesthetic experience to fractal images using functional MRI. The aesthetic estimations of the images showed that there is a general consensus regarding the perception of beautiful images. Out of 270 fractal images, fifty images rated highest(beautiful images) and fifty images rated lowest(non-beautiful images) were selected and presented to the participants. The two conditions were presented using the block design. Frontal lobes, cingulate gyri, and insula, the areas related to the cognitive and emotional processing in aesthetic experience, were activated when beautiful images were presented. In contrast, the middle occipital gyri and precuneus, the areas associated with experience of negative emotions, were activated when non-beautiful images were presented. The conjunction analysis showed activations in temporal areas in response to beautiful images and activations in parietal areas in response to non-beautiful images. These results indicate that beautiful images elicit semantic interpretations whereas non-beautiful images facilitate abstract processes.