• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.139-142
• /
• 2006

본 연구는 장면 이미지로부터 텍스트에 존재하는 문자-에지 특징을 이용하여 텍스트를 추출하는 방법을 제안한다. 캐니(Canny)에지 연산자를 이용하여 장면 이미지로부터 에지를 추출하고, 추출된 에지로부터 16종류의 에지-맵 생성한다. 생성된 에지 맵을 재구성하여 문자 특징을 갖는 8종류의 문자-에지 맵을 만단다. 텍스트는 배경과 잘 분리되는 특징이 있으므로 텍스트에 존재하는 '문자-에지 맵'의 특징을 이용하여 텍스트를 추출한다. 텍스트 영역에 대한 검증은 문자-에지 맵의 분포와 텍스트에 존재하는 글자간의 공백 특징으로 한다. 제안한 방법은 다양한 종류의 장면 이미지를 실험대상으로 하였고, 텍스트는 적어도 2글자 이상으로 구성된다는 제한조건과 너무 크거나 작은 텍스트는 텍스트 추출에서 제외하였다. 실험결과 텍스트 영역 추출률은 약 83%를 얻었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.2
• /
• pp.159-167
• /
• 1992

This paper describes a feature extraction process by using a multi-layer neural network and is applied to the Korean stroke pattern for on line hand written character recognition, In the first layer the features are detected during the writing process and in the second layer the stroke specific features are extracted. A modified Masking field algorithm for direction co9nstancy has been used in this neural network and the resulting action potential of stroke specific features represents statistical distribution of the features in the on-line input stroke pattern and these results can be used in the recognition of on-line hand written Korean characters successfully.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.27-33
• /
• 2011

In this paper, we propose an efficient on-line handwritten digit recognition base on Convex-Concave curves feature which is extracted by a chain code sequence using Smith-Waterman alignment algorithm. The time sequential signal from mouse movement on the writing pad is described as a sequence of consecutive points on the x-y plane. So, we can create data-set which are successive and time-sequential pixel position data by preprocessing. Data preprocessed is used for Convex-Concave curves feature extraction. This feature is scale-, translation-, and rotation-invariant. The extracted specific feature is fed to a Smith-Waterman alignment algorithm, which in turn classifies it as one of the nine digits. In comparison with backpropagation neural network, Smith-Waterman alignment has the more outstanding performance.

• Journal of the Korea Computer Graphics Society
• /
• v.17 no.4
• /
• pp.11-21
• /
• 2011

This paper proposes a method for decomposing a Hangul glyph of outline fonts into its initial, medial and final components using statistical-structural information. In a font family, the positions of components are statistically consistent and the stroke relationships of a Hangul character reflect its structure. First, we create the component histograms that accumulate the shapes and positions of the same components. Second, we make pixel clusters from character image based on pixel direction probabilities and extract the candidate strokes using position, direction, size of clusters and adjacencies between clusters. Finally, we find the best structural match between candidate strokes and predefined character model by relaxation labeling. The proposed method in this paper can be used for a study on formative characteristics of Hangul font, and for a font classification/retrieval system.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.75-84
• /
• 2018

In this study, the researchers attempted to automate the process of painting the characters on the road surface, which is currently done by manual labor, by using the information and communication technology. Here are the descriptions of how we put in our efforts to achieve such a goal. First, we familiarized ourselves with the current regulations about painting letters or characters on the road, with reference to Road Mark Installation Management Manual of the National Police Agency. Regarding the graphemes, we adopted a new one using connection components, in Gothic print characters which was within the range of acceptance according to the aforementioned manual. We also made it possible for the automated program to recognize the graphemes by means of the feature dots of the isolated dots, end dots, 2-line gathering dots, and gathering dots of 3 lines or more. Regarding the database, we built graphemes database for plotting information, classified the characters by means of the arrangement information of the graphemes and the layers that the graphemes form within the characters, and last but not least, made the character shape information database for character plotting by using such data. We measured the layers and the arrangement information of the graphemes consisting the characters by using the information of: 1) the information of the position of the center of gravity, and 2) the information of the graphemes that was acquired through vertical exploration from the center of gravity in each grapheme. We identified and compared the group to which each character of the database belonged, and recognized the characters through the use of the information gathered using this method. We analyzed the input characters using the aforementioned analysis method and database, and then converted into plotting information. It was shown that the plotting was performed after the correction.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.30-37
• /
• 2021

Recently, 3D contents used in various fields have been attracting people's attention due to the development of virtual reality and augmented reality technology. In order to produce 3D contents, it is necessary to model the objects as vertices. However, high-quality modeling is time-consuming and costly. In order to convert a 2D character into a 3D model, it is necessary to express it as line drawings through feature line extraction. The extraction of consistent line drawings from 2D cartoon cartoons is difficult because the styles and techniques differ depending on the designer who produces them. Therefore, it is necessary to extract the line drawings that show the geometrical characteristics well in 2D cartoon shapes of various styles. This study proposes a method of automatically extracting line drawings. The 2D Cartoon shading image and line drawings are learned by using adversarial network model, which is artificial intelligence technology and outputs 2D cartoon artwork of various styles. Experimental results show the proposed method in this research can be obtained as a result of the line drawings representing the geometric characteristics when a 2D cartoon painting as input.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.93-100
• /
• 2011

The necessity of research on extracting information of face and facial components in animation characters have been increasing since they can effectively express the emotion and personality of characters. In this paper, we introduce a method to extract face and facial components of animation characters by defining a mesh model adequate for characters and by using dominant colors. The suggested algorithm first generates a mesh model for animation characters, and extracts dominant colors for face and facial components by adapting the mesh model to the face of a model character. Then, using the dominant colors, we extract candidate areas of the face and facial components from input images and verify if the extracted areas are real face or facial components by means of color similarity measure. The experimental results show that our method can reliably detect face and facial components of animation characters.

• Journal of KIISE:Software and Applications
• /
• v.29 no.8
• /
• pp.573-583
• /
• 2002

Pattern recognition process is made up of the feature extraction in the pre-processing, the pattern clustering by training and the recognition process. This paper presents the F-LVQ (Fuzzy Learning Vector Quantization) pattern classification model which is optimized by the fuzzy membership function for the OCR(Optical Character Recognition) system. We trained 220 numeric patterns of 22 Hangul and English fonts and tested 4840 patterns whose forms are changed variously. As a result of this experiment, it is proved that the proposed model is more effective and robust than other typical LVQ models.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.315-322
• /
• 2006

Ant Colony System(ACS) is easily applicable to the traveling salesman problem(TSP) and it has demonstrated good performance on TSP. Recently, ACS has been emerged as the useful tool for the pattern recognition, feature extraction, and edge detection. The edge detection is wifely utilized in the area of document analysis, character recognition, and face recognition. However, the conventional operator-based edge detection approaches require additional postprocessing steps for the application. In the present study, in order to overcome this shortcoming, we have proposed the new ACS-based edge detection algorithm. The experimental results indicate that this proposed algorithm has the excellent performance in terms of robustness and flexibility.