• Korean Journal of Construction Engineering and Management
• /
• v.15 no.4
• /
• pp.20-29
• /
• 2014

As construction projects increase their complexity, variety, and scale, various recognition applications (such as RFID, bar-code etc.) have been tried for managing material effectively in construction projects. However, existing recognition applications for construction material management have some limitations that cause additional works (such as attaching RFID tag), additional cost (labor cost, recognition device cost, etc.), and cognitive impairment of workers. Therefore, this study proposed a character recognition technology as an alternative of previous recognition technologies such as RFID, bar-code, etc. The technical feasibility of proposed technology was validated by three recognition tests. Additionally, this study proposed code the structure to manage materials using the character recognition technology. The effects of character recognition technology are presented by comparing with existing RFID-based logistics processes.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.2
• /
• pp.168-177
• /
• 1996

In this paper, we propose an on-line recognition system of chinese characters using an adaptive resonance theory-1(ART-1) neural network. Strokes, primitive components of chinese characters are usually warped into a cursive form and classifying them is very difficult. To deal with such cursive strokes, we use an ART-1 neural network that has the following advantages: (1) it automatically assembles similar patterns together to form classes in a self-organized manner: (2) it directly accesses the recognition codes corresponding to binary input patterns after self-stabilizing; (3) it doesn't tends to get trapped in local minima, or globally incorrect solutions. A database for character recognition also dynamically constructed with generalized character lists, and a new character can be included simply by adding a new sequence to the list. Character recognition is achieved by traversing the chinese datbase with a sequence of recognized strokes and positional relations between the strokes. To verify the performance of the system. We tested it for 1800 daily-used basic chinese second per character. This results suggest that the proposed system is pertinent to be put into practical use.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2276-2290
• /
• 1994

In this paper, we propose an algorithm for character recognition using the subdivided type and the stable structure information. The subdivided type of character is acquired from the stable structure information of character which is extracted from an input character. Firstly, the character is obtained from a scanner and classified into on of 6 types by using directional density vector. And then, the stable structure information is extracted from each character and the character is subdivided into on of 26 types. Finally, the classified character is recognized by using neural network which is inputted the directional density vector equivalent to JASO area or recognized direct. Aa a result of experiment with KS C 5601 2350 printed Hangeul characters, we obtain the recognition rate of 94%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.267-270
• /
• 2016

Currently, tire has a variety of information to know the information of the tire are displayed on the tire side. the market are marked with raised letters showing a variety of information relating to the tires. Such information enables people and tire related companies to distinguish between tires upon the information marked on the tires. Generally, people see the information including max press, manufacturing date, etc. Accordingly, studies on automated recognition of raised letters on tire by using image processing technology have been presented consistently. However, they lack a method for recognition of letters and improvement of the recognition. Moreover, the raised letters have been previously recognized through image processing. Further, to obtain the character recognition of a conventional side in video, it is suitably utilized the effects of lighting time of acquisition, so as part of the background and the character has a gray level values between approximately the same, is the part that is not relatively clear are many scattered. In this paper, we see the characters of the tire side using the laser sensor, recognition, was designed for character recognition of the tire side.

• Smart Media Journal
• /
• v.2 no.4
• /
• pp.20-26
• /
• 2013

This paper presents an approach to Mongolian car plate recognition using artificial neural network. Our proposed method consists of two steps: detection and recognition. In detection step, we implement Flood fill algorithm. In recognition step we proceed to segment the plate for each Cyrillic character, and use an Artificial Neural Network (ANN) machine - learning algorithm to recognize the character. We have learned the theory of ANN and implemented it without using any library. A total of 150 vehicles images obtained from community entrance gates have been tested. The recognition algorithm shows an accuracy rate of 89.75%.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.9
• /
• pp.27-36
• /
• 2016

Recognition of grapheme is a very important process in the recognition within 'Hangul(Korean written language)' letters using phoneme recognition. It is because the success or failure in the recognition of phoneme greatly affects the recognition of letters. For this reason, it is reported that separation of phonemes is the biggest difficulty in the phoneme recognition study. The current study separates and suggests the new phonemes that used the connective elements that are helpful for dividing phonemes, recommends the features for recognition of such suggested phonemes, databases this, and carried out a set of experiments of recognizing phonemes using the suggested features. The current study used 350 letters in the experiment of phoneme separation and recognition. In this particular kind of letters, there were 1,125 phonemes suggested. In the phoneme separation experiment, the phonemes were divided in the rate of 100%, and the phoneme recognition experiment showed the recognition rate of 98% in recognizing only 14 phonemes into different ones.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.1-8
• /
• 2017

Recently, with the development of ICT technology such as cloud and mobile, image utilization through social networks is increasing rapidly. These images contain personal information, and personal information leakage accidents may occur. As a result, studies are underway to recognize and mask personal information in images. However, optical character recognition, which recognizes personal information in images, varies greatly depending on brightness, contrast, and distortion, and Korean recognition is insufficient. Therefore, in this paper, we design and implement a personal information identification and masking system based on image recognition through deep learning application using CNN algorithm based on optical character recognition method. Also, the proposed system and optical character recognition compares and evaluates the recognition rate of personal information on the same image and measures the face recognition rate of the proposed system. Test results show that the recognition rate of personal information in the proposed system is 32.7% higher than that of optical character recognition and the face recognition rate is 86.6%.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.92-98
• /
• 2020

This paper proposes a vehicle license plate recognition system using light weight deep learning models without high-end server. The proposed license plate recognition system consists of 3 steps: [license plate detection]-[character area segmentation]-[character recognition]. SSD-Mobilenet was used for license plate detection, ResNet with localization was used for character area segmentation, ResNet was used for character recognition. Experiemnts using Samsung Galaxy S7 and LG Q9, accuracy showed 85.3% accuracy and around 1.1 second running time.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.12 no.2
• /
• pp.11-17
• /
• 1975

The paper examined the character structure as a basic study for the recognition of Korean characters. In view of concave structure, line structure and node relationship of character graph, the algebraic structure of the basic Korean characters is are analized. Also, the degree of complexities in their character structure is discussed and classififed. Futhermore, by describing the fact that some equivalence relations are existed between the 10 vowels of rotational transformation group by Affine transformation of one element into another, it could be pointed out that the geometrical properting in addition to the topological properties are very important for the recognition of Korean characters.

• KIISE Transactions on Computing Practices
• /
• v.20 no.10
• /
• pp.549-554
• /
• 2014

Handwritten character recognition data is usually imbalanced because it is collected from the natural language sentences written by different writers. The imbalanced data can cause seriously negative effect on the performance of most of machine learning algorithms. But this problem is typically ignored in handwritten character recognition, because it is considered that most of difficulties in handwritten character recognition is caused by the high variance in data set and similar shapes between characters. We propose the oversampling-based ensemble learning methods to solve imbalanced data problem in handwritten character recognition and to improve the recognition accuracy. Also we show that proposed method achieved improvements in recognition accuracy of minor classes as well as overall recognition accuracy empirically.