• The Journal of the Acoustical Society of Korea
• /
• v.15 no.6
• /
• pp.16-25
• /
• 1996

In this paper, we designed the chip which can classify the Korean characters using CAM(Content Addressable Memory). A high-speed OCR has been implemented by software to recognize the characters. However, it is difficult to process in real-time. The pipelined hardware implementation is one of the solution to recognize the characters in real-time by using the parallel processing techniques. We used the CAM which has the function of high-speed parallel-match to implement easily and twenty reference patterns are used for comparison. The chip has been evaluated result using DLAB of DAZIX. The simulation results have shown that the process speed was $1.6{\mu}s$ per character. Also, we programed using C-language and compared the results.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.225-234
• /
• 2019

Deep learning has become increasingly popular in both academic and industrial areas nowadays. Various domains including pattern recognition, Computer vision have witnessed the great power of deep neural networks. However, current studies on deep learning mainly focus on quality data sets with balanced class labels, while training on bad and imbalanced data set have been providing great challenges for classification tasks. We propose in this paper a method of data analysis-based data reduction techniques for selecting good and diversity data samples from a large dataset for a deep learning model. Furthermore, data sampling techniques could be applied to decrease the large size of raw data by retrieving its useful knowledge as representatives. Therefore, instead of dealing with large size of raw data, we can use some data reduction techniques to sample data without losing important information. We group PCB characters in classes and train deep learning on the ResNet56 v2 and SENet model in order to improve the classification performance of optical character recognition (OCR) character classifier.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.4
• /
• pp.651-656
• /
• 2017

In this study, we designed the system that helps drivers check all information about parking space at the entrance and find out whether the places is available or not, because the system has 'Image recognition function' which can even recognize car number plates exactly. Besides, we place the webcam close to the car number plate, so that car number can be identified more quickly. Finally, since we set the webcam high, the system keeps us from parking wrong places by displaying on the screen.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.24-29
• /
• 2023

In this paper, we propose a real-time bus arrival notification system using deep learning to guarantee movement rights for the visually impaired. In modern society, by using location information of public transportation, users can quickly obtain information about public transportation and use public transportation easily. However, since the existing public transportation information system is a visual system, the visually impaired cannot use it. In Korea, various laws have been amended since the 'Act on the Promotion of Transportation for the Vulnerable' was enacted in June 2012 as the Act on the Movement Rights of the Blind, but the visually impaired are experiencing inconvenience in using public transportation. In particular, from the standpoint of the visually impaired, it is impossible to determine whether the bus is coming soon, is coming now, or has already arrived with the current system. In this paper, we use deep learning technology to learn bus numbers and identify upcoming bus numbers. Finally, we propose a method to notify the visually impaired by voice that the bus is coming by using TTS technology.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.11
• /
• pp.75-80
• /
• 2012

In this paper, the operational characteristics due to the introduction of the superconducting fault current limiter(SFCL) with a peak current limiting function were analyzed in the power distribution system. The parallel structure of the superconducting element can operate the peak current limiting function depending on the transient amplitude of fault current. We studied the operating characteristics of the introduction of the SFCL with a peak current limiting function in the power distribution system. Furthermore, we were analyzed between the SFCL with a peak current limiting function and the protection devices in the power distribution system, through the short circuit experiments.

• Proceedings of the KIEE Conference
• /
• 2006.05a
• /
• pp.48-50
• /
• 2006

SC(Static Condenser) in KEPCO is used in voltage control and power factor compensation. Currently KEPCO uses SC to 154kv 50MVA and 23kv SMVA. It is not important in old days because a SC bank accident has no effect on power system. But we are interested in the SC bank for power quality in these days. The SC Bank has a reactor and a condenser using series connection. It is operated in critical point for resonance circuit normally. Therefore the SC bank has a small reliability against other Power instruments. If a 4th harmonic frequency as a resonance frequency is supplied in system, the condenser is damaged because of a resonance current. And a trip and a closing for CB(Circuit Breaker) in many times will have a big influence of SC bank destruction. General OCR(Over Current Relay) observing SC bank is not useful for this protection We think that protection relay must be have the SC bank characteristics. A solution for this problem is active Power, resonance frequency and impedance.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.9-15
• /
• 2016

In this paper, we propose a method for verifying the location of the books in working order to enhance the effiency of library management. On open libraries, occasionally people relocate the book by mistake or intention after reading one. In this occasion, the book is assorted as a lost property and cannot be lended to others, even though it is still in the library. To solve this problem, the system we propose takes an image of the book selves by a mobile robot and extracts the classifying information of the book. After comparison between current location of the book and assigned location of the library database, information of the mislocated books is notified to the librarian.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.9
• /
• pp.2312-2325
• /
• 2013

In this paper, we propose a preprocessing method that it is to correct the distortion of text area in Korean signboard images as a preprocessing step to improve character recognition. Distorted perspective in recognizing of Korean signboard text may cause of the low recognition rate. The proposed method consists of four main steps and eight sub-steps: main step consists of potential vertical components detection, vertical components detection, text-boundary estimation and distortion correction. First, potential vertical line components detection consists of four steps, including edge detection for each connected component, pixel distance normalization in the edge, dominant-point detection in the edge and removal of horizontal components. Second, vertical line components detection is composed of removal of diagonal components and extraction of vertical line components. Third, the outline estimation step is composed of the left and right boundary line detection. Finally, distortion of the text image is corrected by bilinear transformation based on the estimated outline. We compared the changes in recognition rates of OCR before and after applying the proposed algorithm. The recognition rate of the distortion corrected signboard images is 29.63% and 21.9% higher at the character and the text unit than those of the original images.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.4
• /
• pp.13-20
• /
• 2016

It is possible to implement an optical character recognition system using a high-resolution camera mounted on smart phones in the modern society. Further, characters extracted from the implemented application is possible to provide the voice service for the visually impaired person by using TTS. But, it is difficult for the visually impaired person to properly shoot the objects that character information are included, because it is very hard to accurately understand the current state of the object. In this paper, we propose a method of inducing an appropriate shooting for the visually impaired persons by using a smartphone gyro sensor. As a result of simulation using the implemented program, we were able to see that it is possible to recognize the more character from the same object using the proposed method.