• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.167-175
• /
• 2002

Image Mosaicing creates a new image by composing video frames or still images that are related, and performed by arrangement, composition and redundancy analysis of images. This paper proposes a hierarchical image mosaicing system using camera and object parameters far efficient video database construction. A tree-based image mosiacing has implemented for high-speed computation time and for construction of static and dynamic image mosaic. Camera parameters are measured by using least sum of squared difference and affine model. Dynamic object detection algorithm has proposed for extracting dynamic objects. For object extraction, difference image, macro block, region splitting and 4-split detection methods are proposed and used. Also, a dynamic positioning method is used for presenting dynamic objects and a blurring method is used for creating flexible mosaic image.

• Journal of Broadcast Engineering
• /
• v.8 no.1
• /
• pp.91-100
• /
• 2003

In this paper, to improve the retrieval Performance, an efficient combination of the MPEG-7 visual descriptors, such as the edge histogram descriptor (EHD), the color layout descriptor (CLD), and the homogeneous texture descriptor (HTD), is proposed in the framework of the relevance feedback approach. The EHD represents spatial distribution of edges in local image regions and it is considered as an important feature to represent the content of the image. The CLD specifies spatial distribution of colors and is widely used in image retrieval due to its simplicity and fast operation speed. The HTD describes precise statistical distribution of the image texture. Both the feature vector for the query image and the weighting factors among the combined descriptors are adaptively determined during the relevance feedback. Experimental results show that the proposed method improves the retrieval performance significantly tot natural images.

• Cartoon and Animation Studies
• /
• s.24
• /
• pp.65-82
• /
• 2011

Since the arrival of the internet, numerous creative content industries have been active online. In particular, additional training has been necessary due to higher interest in e-Book publishing, and the opening and expansion of the online comics industry. However, as for the study of film grammar, there is a lack of research on lively and diverse expression in cartoon directing. In this study, animation and painting techniques, with examples of cartoons being expressed cartoon is intended to provide the possibility of directing. In addition, the comics industry one source multi user to the related industries is a key element with the value-added industries. So in other media expressed a wide range of research on the techniques of comic culture shall serve as key elements of the content looks.

• Journal of Broadcast Engineering
• /
• v.22 no.1
• /
• pp.42-50
• /
• 2017

A Bit-depth expansion is a method to increase the number of bit. It is getting important as the needs of HDR (High Dynamic Range) display or resolution of display have been increased because the level of luminance or expressiveness of color is proportional to the number of bit in the display. In this paper, we present effective bit-depth expansion algorithm for conventional standard 8 bit-depth content to display in high bit-depth device (10 bits). Proposed method shows better result comparing with recently developed methods in quantitative (PSNR) with low complexity. The proposed method shows 1db higher in PSNR measurement with 40 times faster in computational time.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.2
• /
• pp.234-242
• /
• 2024

We propose a passive sonar signal classification algorithm using Graph Neural Network (GNN). The proposed algorithm segments spectrograms into image patches and represents graphs through connections between adjacent image patches. Subsequently, Graph Convolutional Network (GCN) is trained using the represented graphs to classify signals. In experiments with publicly available underwater acoustic data, the proposed algorithm represents the line frequency features of spectrograms in graph form, achieving an impressive classification accuracy of 92.50 %. This result demonstrates a 8.15 % higher classification accuracy compared to conventional Convolutional Neural Network (CNN).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.1027-1030
• /
• 2011

휴머노이드 로봇 중 초상화를 그리는 로봇이 있지만 다양한 영상을 입력받아 명암 및 그림자까지 그림을 그리는 로봇은 흔하지 않다. 기존의 화가로봇들은 사용자의 얼굴을 영상으로 입력받아 윤곽선만 추출하여 그리는 방식으로, 입력된 영상으로부터 로봇 암을 제어하는 과정에서 제대로 동기화가 이뤄지지 못해 드로잉 속도가 느리고 원본 영상과 비교 시 차이가 많이 난다. 본 연구에서는 입력된 영상으로부터 명암과 그림자를 인식하여 표현해 줌으로써 입체감 있는 그림의 드로잉이 가능하다. 또한, 로봇 암의 미세한 컨트롤을 통해 드로잉 선 두께를 제어함으로써 자연스러운 그림을 그리고, 드로잉 속도가 향상되어 정확도를 높일 수 있게 하는 휴리스틱 암 제어 기술을 제안한다. 이를 구현하기 위해서는 영상으로부터 명암, 그림자의 농도에 따라 레벨을 결정하고, 레벨을 바탕으로 주변 명암 픽셀들을 평활화 하여 좌표 집합을 추출한다. 좌표 값들로 부터 유효 궤적을 분석하여 로봇 암이 이동할 경로를 추출하고, 효율적인 드로잉 기법을 통해 명암을 표현하여 드로잉하려 한다.

• Journal of Korea Multimedia Society
• /
• v.12 no.4
• /
• pp.502-511
• /
• 2009

In order to simulate a depth-of-field effect in real world, there have been several researches in computer graphics field. It can represent an out-of-focused scene by calculating focal plane. When a point in a 3D coordinate lies on further or nearer than focal plane, the point is presented as a blurred circle on image plane according to the characteristic of the aperture and the lens. We can generate a realistic image by simulating the effect because it provides an out-of-focused scene like human eye dose. In this paper, we propose a method to calculate a disparity value of a viewer using a customized stereoscopic eye-tracking system and a GPU-based depth-of-field control method. They enable us to generate more realistic images reducing side effects such as dizziness. Since stereoscopic imaging system compels the users to fix their focal position, they usually feel discomfort during watching the stereoscopic images. The proposed method can reduce the side effect of stereoscopic display system and generate more immersive images.

• Journal of Broadcast Engineering
• /
• v.10 no.4 s.29
• /
• pp.576-586
• /
• 2005

This paper presents a new estimation and representation of a disparity map for stereo-based video communication systems. Several pixel-based and block-based algorithms have been proposed to estimate the disparity map. While the pixel-based algorithms can achieve high accuracy in computing the disparity map, they require a lost of bits to represent the disparity information. The bit rate can be reduced by the block-based algorithm, sacrificing the representation accuracy. In this paper, the block enclosing a distinct edge is divided into two regions and the disparity of each region is set to that of a neighboring block. The proposed algorithm employs accumulated histograms and a neural network to classify a type of a block. In this paper, we proved that the proposed algorithm is more effective than the conventional algorithms in estimating and representing disparity maps through several experiments.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.241-249
• /
• 2009

Recently, a number of researches related to video annotation and representation have been proposed to analyze video for searching and abstraction. In this paper, we have presented a method to provide the picture elements of conversational participants in video and the enhanced representation of the characters using those elements, collectively called Character-net. Because conversational participants are decided as characters detected in a script holding time, the previous Character-net suffers serious limitation that some listeners could not be detected as the participants. The participants who complete the story in video are very important factor to understand the context of the conversation. The picture elements for detecting the conversational participants consist of six elements as follows: subtitle, scene, the order of appearance, characters' eyes, patterns, and lip motion. In this paper, we present how to use those elements for detecting conversational participants and how to improve the representation of the Character-net. We can detect the conversational participants accurately when the proposed elements combine together and satisfy the special conditions. The experimental evaluation shows that the proposed method brings significant advantages in terms of both improving the detection of the conversational participants and enhancing the representation of Character-net.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.2
• /
• pp.69-76
• /
• 2018

Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a new deep neural network model for referring expression comprehension. The proposed model finds out the region of the referred object in the given image by making use of the rich information about the referred object itself, the context object, and the relationship with the context object mentioned in the referring expression. In the proposed model, the object matching score and the relationship matching score are combined to compute the fitness score of each candidate region according to the structure of the referring expression sentence. Therefore, the proposed model consists of four different sub-networks: Language Representation Network(LRN), Object Matching Network (OMN), Relationship Matching Network(RMN), and Weighted Composition Network(WCN). We demonstrate that our model achieves state-of-the-art results for comprehension on three referring expression datasets.