• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• 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.

• International Journal of Contents
• /
• 제8권3호
• /
• 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.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.409-414
• /
• 2023

In recent years, the emergence of a number of AI image generation software represented by [Midjourney] has brought great impetus to the development of the field of AI-assisted art creation. Compared with the traditional hand-painted digital painting with the aid of electronic equipment, broke the traditional sense of animation character creation logic.This paper analyzes the application of AI technology in the field of animation character design through the practice of two-dimensional animation character . This is having a significant impact on the productivity and innovation of animation design and character modeling. The key results of the analysis indicate that AI technology, particularly through the utilization of "Midjourney,"enables the automation of certain design tasks, provides innovative approaches, and generates visually appealing and realistic characters. In conclusion, the integration of AI technology, specifically the application of "Midjourney," brings a new dimension to animation character design. The utilization of AI image generation software facilitates streamlined workflows, sparks creativity, and improves the overall quality of animated characters. As the animation industry continues to evolve, AI-assisted tools like "Midjourney" hold great potential for further advancement and innovation.

• 한국잠사곤충학회지
• /
• 제7권
• /
• pp.43-47
• /
• 1967

가잠 다교배와 차대잠의 형질을 연구하여 다음과 같은 결과를 얻었다. 1. 삼원이교배에 있어서는 이원이중교배와 같이 잠품종적인 수정선택성과 교배순서가 작용하여서 그 수정력이 차대잠 형질에 나타난다. 2. 사원삼교배에 있어서는 보통반문백색견, 용각백색견, 이호백색견 적색잠등을 공시하여 중복교배를 시켰던 바 차대에 모품종과 부품종 이외의 형질잠이나 형질잠은 전혀 나타나지 않았다. 3. 교미시간을 달리한 삼원이교배에서는 교미시간이 차대잠에 영향을 미치며 교미시간의 장단은 교배형식과 밀접한 관계가 있다.

• 한국잠사곤충학회지
• /
• 제6권
• /
• pp.9-17
• /
• 1966

The ratio of form and character in the text generation of silkworms which were double copulated between home race copulation and hetero race copulation in crossing with two males of different races for female(double crossing) are different according to the copulating time, copulating order and sperm activities. But the general tendencies are as follows; 1. During two hour's double copulation, sufficiently ejaculating time, the fertilization percentage of hetero lace copulation are higher than that of homo race, but in case of double copulation with plain and normal marked silkworms showed opposite results. The fertilization percentage of homo race copulation are equal or higher compare with that of hetero race copulation. 2. The form and character of the next generation were largely effected by copulating order, so the primary copulating moths are more effected in the next generation than the secondary moths. 3. The active sperms were more fertilized than non-active sperms in the double copulation.

• 한국멀티미디어학회논문지
• /
• 제23권7호
• /
• 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.

• 한국정보통신학회논문지
• /
• 제12권9호
• /
• pp.1547-1553
• /
• 2008

본 논문은 간소화된 주성분 벡터를 이용한 벡터 그래픽 캐릭터의 다양한 얼굴 표정 생성 방법을 제안한다. 먼저 Russell의 내적 정서 상태에 기반하여 재정의된 벡터 그래픽 캐릭터들의 9가지 표정에 대해 주성분 분석을 수행한다. 이를 통해 캐릭터의 얼굴 특성과 표정에 주된 영향을 미치는 주성분 벡터를 찾아내고, 간소화된 주성분 벡터로부터 얼굴 표정을 생성한다. 또한 캐릭터의 특성과 표정의 가중치 값을 보간함으로써 자연스러운 중간 캐릭터 및 표정을 생성한다. 이는 얼굴 애니메이션에서 종래의 키프레임 저장 공간을 상당히 줄일 수 있으며, 적은 계산량으로 중간 표정을 생성할 수 있다. 이에 실시간 제어를 요구하는 웹/모바일 서비스, 게임 등에서 캐릭터 생성 시스템의 성능을 상당히 개선할 수 있다.

• International journal of advanced smart convergence
• /
• 제7권2호
• /
• pp.7-21
• /
• 2018

The author studied the process of unifying Hanja variant groups of Korea and China for LGR (Label Generation Rule) of Internet Top-Level Hangeul Hanja Domain and possible confusion between Hangeul syllable and Hanja character. Among 3518 Chinese variant groups, Korea and China need not review variant groups which include no or just one Korean Hanja character. Korea and China reviewed 304 Chinese variant groups (9% of the 3518 Chinese variant groups) which include two or more Korean Hanja characters. By doing so, Korea and China succeeded in efficiently unifying variant groups. Unification process of variant groups which is the main core of Korea-China coordination and almost final unification result is summarized in this paper. In addition, the author analyzed systematically whether some Hanja character could be confused with a Hangeul syllable and obtained a good result which was not expected at the beginning. Probably this kind of systematic analysis has not been performed in the past and seems the first attempt, which is one of the contributions of this paper. The author also reviewed how to express K-LGR in XML for submission to ICANN.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1794-1806
• /
• 2023

This study presents a method for capturing photographs of users as input and converting them into 2D character animation sprites using a generative adversarial network-based artificial intelligence network. Traditionally, 2D character animations have been created by manually creating an entire sequence of sprite images, which incurs high development costs. To address this issue, this study proposes a technique that combines motion videos and sample 2D images. In the 2D sprite generation process that uses the proposed technique, a sequence of images is extracted from real-life images captured by the user, and these are combined with character images from within the game. Our research aims to leverage cutting-edge deep learning-based image manipulation techniques, such as the GAN-based motion transfer network (impersonator) and background noise removal (U² -Net), to generate a sequence of animation sprites from a single image. The proposed technique enables the creation of diverse animations and motions just one image. By utilizing these advancements, we focus on enhancing productivity in the game and animation industry through improved efficiency and streamlined production processes. By employing state-of-the-art techniques, our research enables the generation of 2D sprite images with various motions, offering significant potential for boosting productivity and creativity in the industry.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.698-701
• /
• 2003

In recent years, various digital characters, which are automatic and intelligent, are attempted with the introduction of artificial intelligence or artificial life. Since the style of a character's behavior is usually designed by a developer, the style is very static and simple. So such a simple pattern of the character cannot satisfy various users and easily makes them feel tedious. A game should maintain various and complex styles of a character's behavior, but it is very difficult for a developer to design various and complex behaviors of it. In this paper, we adopt the genetic algorithm to produce various and excellent behavior-styles of a character especially focusing on Robocode which is one of promising simulators for artificial intelligence.