• Title/Summary/Keyword: Character Generation System

Search Result 104, Processing Time 0.087 seconds

CGS System based on Three-Dimensional Character Modeling I (Part1:About Non-Digital Process) (3차원 캐릭터 모델기반 CGS System 구축 I (Part1:Non-Digital Process에 관하여))

  • Cho, Dong-Min
    • Journal of Korea Multimedia Society
    • /
    • v.11 no.11
    • /
    • pp.1592-1600
    • /
    • 2008
  • This study is to help creative idea generation based on the theory of the 'reconstruction of character shape image elements', and aims to extrusion of creative and diverse shapes with combination of image elements upon computing creative image generation. In order to suggest the design generation methodology for the maximization of idea generation ability and to overcome restriction of thinking out of existing idea generation methodology, it has suggested the CGS(Character Generation System) that is a creative idea generation methodology identified and complemented the problem of the existing computerized idea generation(PDS with Proportion) method out of the preceded studies on the creative idea generation methodologies. this study is expected to have effectives as one method for idea generation or creative image generation assistance during the 3D character development process, and to serve as an assistance to overcome the restriction of the character shape image generation through diverse idea generations.

  • PDF

Development of Facial Animation Generator on CGS System (CGS 시스템의 페이셜 애니메이션 발상단계 개발)

  • Cho, Dong-Min
    • Journal of Korea Multimedia Society
    • /
    • v.14 no.6
    • /
    • pp.813-823
    • /
    • 2011
  • This study is to suggest the facial animation methodology for that 3D character animators can use CGS system effectively during on their stage which they create ideas and use repeating a process of facial animation, it has suggested the CGS(Character Generation System) that is a creative idea generation methodology identified and complemented the problem of the existing computerized idea generation, in addition, this research being extended on the article vol.13, no.7, "CGS System based on Three-Dimensional Character Modeling II (Part2: About Digital Process)," on Korea Multimedia Society in July 2010 issue, Through the preceding study on 3D character facial expression according to character's feelings as an anatomical structure and the case study on character expressions of theatrical animation, this study is expected to have effectives as one method for maximization of facial animation and idea generation ability.

CGS System based on Three-Dimensional Character Modeling II (Part 2: About Digital Process) (3차원 캐릭터 모델기반 CGS System 구축 II (Part 2 : Digital Process에 관하여))

  • Cho, Dong-Min;Cho, Kwang-Soo
    • Journal of Korea Multimedia Society
    • /
    • v.13 no.7
    • /
    • pp.1095-1104
    • /
    • 2010
  • This study is to suggest the design generation methodology for the maximization of idea generation ability and to overcome restriction of thinking out of existing idea generation methodology, it has suggested the CGS(Character Generation System) that is a creative idea generation methodology identified and complemented the problem of the existing computerized idea generation(PDS with Proportion) method out of the preceded studies on the creative idea generation methodologies. In addition, this research being extended on the article vol.11,no.11, "CGS System based on Three-Dimensional Character Modeling Ⅰ(Part1: about Non-Digital Process )," on Korea Multimedia Society in November 2008 issue and this study is expected to have effectives as one method for idea generation or creative image generation assistance during the 3D character development process with practical implementation of system, research directions and present the results.

A Study on Proportion Distort System for Idea generator (아이디어 산출을 위한 자율 비례 변형 시스템에 관한 연구 - 3Dimension Character 중심으로)

  • 조동민;최원재
    • Archives of design research
    • /
    • v.14 no.3
    • /
    • pp.155-164
    • /
    • 2001
  • Under the ambiguous situation that Id character design aim is not defined, this study would help designers with 1. overcoming the limitation of character form generation ability by establishing visual application system, 2. accepting users'opinions by generating character images dynamically, analysing and giving information on the preferred ones on the web on real time, 3. identifying tendency of preference so that they can generate preferred colors and images in future by updating image combination and dropping low-preferred ones. this system would play a role as an idea or character form generation application in the 3d character design development process

  • PDF

A Study on Input Pattern Generation of Neural-Networks for Character Recognition (문자인식 시스템을 위한 신경망 입력패턴 생성에 관한 연구)

  • Shin, Myong-Jun;Kim, Sung-Jong;Son, Young-Ik
    • Proceedings of the KIEE Conference
    • /
    • 2006.04a
    • /
    • pp.129-131
    • /
    • 2006
  • The performances of neural network systems mainly depend on the kind and the number of input patterns for its training. Hence, the kind of input patterns as well as its number is very important for the character recognition system using back-propagation network. The more input patters are used, the better the system recognizes various characters. However, training is not always successful as the number of input patters increases. Moreover, there exists a limit to consider many input patterns of the recognition system for cursive script characters. In this paper we present a new character recognition system using the back-propagation neural networks. By using an additional neural network, an input pattern generation method is provided for increasing the recognition ratio and a successful training. We firstly introduce the structure of the proposed system. Then, the character recognition system is investigated through some experiments.

  • PDF

Automatic Generation of Training Character Samples for OCR Systems

  • Le, Ha;Kim, Soo-Hyung;Na, In-Seop;Do, Yen;Park, Sang-Cheol;Jeong, Sun-Hwa
    • International Journal of Contents
    • /
    • v.8 no.3
    • /
    • pp.83-93
    • /
    • 2012
  • In this paper, we propose a novel method that automatically generates real character images to familiarize existing OCR systems with new fonts. At first, we generate synthetic character images using a simple degradation model. The synthetic data is used to train an OCR engine, and the trained OCR is used to recognize and label real character images that are segmented from ideal document images. Since the OCR engine is unable to recognize accurately all real character images, a substring matching method is employed to fix wrongly labeled characters by comparing two strings; one is the string grouped by recognized characters in an ideal document image, and the other is the ordered string of characters which we are considering to train and recognize. Based on our method, we build a system that automatically generates 2350 most common Korean and 117 alphanumeric characters from new fonts. The ideal document images used in the system are postal envelope images with characters printed in ascending order of their codes. The proposed system achieved a labeling accuracy of 99%. Therefore, we believe that our system is effective in facilitating the generation of numerous character samples to enhance the recognition rate of existing OCR systems for fonts that have never been trained.

Example Based Motion Generation and its Applications with Efficient Control for Arbitrary Morphologies (다양한 골격의 효과적인 제어가 가능한 예제 기반의 모션 생성과 응용)

  • Choung, Yu-Jean;Kang, Kyung-Kyu;Kim, Dong-Ho
    • Journal of Korea Game Society
    • /
    • v.9 no.1
    • /
    • pp.127-134
    • /
    • 2009
  • This paper presents a motion generation technique for arbitrary morphologies with the user defined correspondences between joints. Users can define the controlling part in the source character and the part to be controlled in the target character in our system. To remove the restriction in the morphology of the target character, we use the pair of example posture sets. In our system, in order to provide the correspondence regardless of the number of joints, the deformed part in the target character is simplified into the direction vector. The final postures are then generated with the weighted sum of the examples. Our experimental results demonstrate that our approach can generate motions for various target characters and can control the user defined joints in real-time.

  • PDF

A Study of Character Contents on The 6'th Generation Chinese Film - Focused on The Tragedy of Character - (중국영화 6세대에 등장하는 캐릭터 콘텐츠 연구 - 캐릭터의 비극성(悲劇性)을 중심으로 -)

  • Han, Dal Ho
    • Design Convergence Study
    • /
    • v.14 no.4
    • /
    • pp.193-208
    • /
    • 2015
  • This study is to search a meaning of treagedy to show by the 6th generation through charecter's tragedy in the 6'th Generation Chinese film. For this, it examined an inner characteristic behind of the tragedy's moment and externalized ending in directors' films of the 6'th Generation's representation. The 6'th Generation of Chinese film reorganized newly Chinese film's cultural topography in the 1990s. The 6'th Generation films, which rebelled against the primary melody and the 5'th Generation on the system, is expressed commonly a tragedy moment with the time and space by character's tragedy. Characters of the 6'th Generation in the tragedy moment attempts various efforts to escape from the tragedy moment. However, no one can overcome the wall of reality, and their concealed emotion as keeping it out of the public eye lead that play. The moment that the 6th generation film meets a tragedy, the main character's accumulated tragedy situations begin to unfold all together. A tragedy embodied through : a collapsed tragedy due to the past's wound, a tragedy due to loss of jobs, a tragedy due to a family's departure, a tragedy from a time of chaos, a tragedy of a woman who became a head of a household and other tragedies.

Evaluation of Criteria for Mapping Characters Using an Automated Hangul Font Generation System based on Deep Learning (딥러닝 학습을 이용한 한글 글꼴 자동 제작 시스템에서 글자 쌍의 매핑 기준 평가)

  • Jeon, Ja-Yeon;Ji, Young-Seo;Park, Dong-Yeon;Lim, Soon-Bum
    • Journal of Korea Multimedia Society
    • /
    • v.23 no.7
    • /
    • pp.850-861
    • /
    • 2020
  • Hangul is a language that is composed of initial, medial, and final syllables. It has 11,172 characters. For this reason, the current method of designing all the characters by hand is very expensive and time-consuming. In order to solve the problem, this paper proposes an automatic Hangul font generation system and evaluates the standards for mapping Hangul characters to produce an effective automated Hangul font generation system. The system was implemented using character generation engine based on deep learning CycleGAN. In order to evaluate the criteria when mapping characters in pairs, each criterion was designed based on Hangul structure and character shape, and the quality of the generated characters was evaluated. As a result of the evaluation, the standards designed based on the Hangul structure did not affect the quality of the automated Hangul font generation system. On the other hand, when tried with similar characters, the standards made based on the shape of Hangul characters produced better quality characters than when tried with less similar characters. As a result, it is better to generate automated Hangul font by designing a learning method based on mapping characters in pairs that have similar character shapes.

A Study on a technology of extraction of motion objects (3차원 동작객체 추출기술에 관한 연구)

  • 오용진;박노국
    • Proceedings of the Korea Society for Industrial Systems Conference
    • /
    • 1999.05a
    • /
    • pp.154-162
    • /
    • 1999
  • This paper introduces the research and development of automatic generation technology to develop the character agent. The R&D of this technology includes three major elements-body model generation, automatic motion generation and synthetic human generation. Main areas of application would be cyber space- 3D game, animation, virtual shopping, on line chatting, virtual education system, simulation and security system.

  • PDF