• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.904-911
• /
• 2003

In this paper, we propose an effective method for the distinction between machine-printed and handwritten Korean address images. It is important to know whether an input image is handwritten or machine-printed, because methods for handwritten image are quite different from those of machine-printed image in such applications as address reading, form processing, FAX routing, and so on. Our method consists of three blocks: valid connected components grouping, feature extraction, and classification. Features related to width and position of groups of valid connected components are used for the classification based on a neural network. The experiment done with live Korean address images has demonstrated the superiority of the proposed method. The correct classification rate for 3,147 testing images was about 98.85%.

• Korean Institute of Interior Design Journal
• /
• v.24 no.1
• /
• pp.104-114
• /
• 2015

The library means to children a place where they find information necessary for them among a variety of knowledge and information to address their intellectual curiosity, which makes their lives wise and mature. There are not enough research materials understanding children's cognitive systems and behaviors in studies of a children's library with this necessity. This study divided and analyzed the behaviors of children, who were users into three types of reading in terms of information processing. First, it observed the types of reading depending on the stage of their cognitive development; Second, it analyzed the patterns of their behaviors through plays; and lastly, it presented the phases of their behaviors depending on the degree of an assistant's intervention. As a result of the study, the sensory system used and the space preferred differed depending on the stage of their cognition; there were differences in the patterns of their behaviors in each age group depending on the type of play; and there were differences in the children's ability of information processing depending on the assistant's ability. It is anticipated that there will be improvements of children's reading ability at the reading room in a better environment if the three types are considered in terms of information processing.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2505-2507
• /
• 2001

The RF signal is distorted since the cross-talk noise from adjacent tracks and ISI(Inter Symbol Interference) is also incresed as recording density is increased. These cross-talk noise and ISI are main reason of reading error for the embossed pits on the disc. In this study we suggest a new coding method, spaced modulation technique and a detection technique for the spaced modulation. We report the result shows detection performance is improved when we use the suggested spaced modulation code and the detection technique instead of conventional modulation code.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.8-19
• /
• 2004

In this paper, we propose an efficient method for locating destination address block on both of machine-Printed and handwritten Korean mail piece images. The proposed method extracts connected components from the binary mail piece image, generates text lines by merging them, and then groups the text fines into nine clusters. The destination address block is determined by selecting some clusters. Considering the geometric characteristics of address information on Korean mail piece, we split a mail piece image into nine areas with an equal size. The nine clusters are initialized with the center coordinate of each area. A modified Manhattan distance function is used to compute the distance between text lines and clusters. We modified the distance function on which the aspect ratio of mail piece could be reflected. The experiment done with live Korean mail piece images has demonstrated the superiority of the Proposed method. The success rate for 1, 988 testing images was about 93.56%.

• ETRI Journal
• /
• v.43 no.5
• /
• pp.775-786
• /
• 2021

To translate in real time, a simultaneous translation system should determine when to stop reading source tokens and generate target tokens corresponding to a partial source sentence read up to that point. However, conventional attention-based neural machine translation (NMT) models cannot produce translations with adequate latency in online scenarios because they wait until a source sentence is completed to compute alignment between the source and target tokens. To address this issue, we propose a reinforced learning (RL)-based attention mechanism, the reinforced attention mechanism, which allows a neural translation model to jointly train the stopping criterion and a partial translation model. The proposed attention mechanism comprises two modules, one to ensure translation quality and the other to address latency. Different from previous RL-based simultaneous translation systems, which learn the stopping criterion from a fixed NMT model, the modules can be trained jointly with a novel reward function. In our experiments, the proposed model has better translation quality and comparable latency compared to previous models.

• Journal of Multimedia Information System
• /
• v.4 no.1
• /
• pp.39-42
• /
• 2017

Communication between human and machine is having been researched from last few decades and still it's a challenging task because human behavior is unpredictable. When it comes on handwritten digits almost each human has their own writing style. Handwritten digit recognition plays an important role, especially in the courtesy amounts on bank checks, postal code on mail address etc. In our study, we proposed an efficient feature extraction system for recognizing single digit number drawn by mouse or by a finger on a screen. Our proposed method combines basic image processing and reading the strokes of a line drawn. It is very simple and easy to implement in various platform as compare to the system which required high system configuration. This system has been designed, implemented, and tested successfully.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2563-2573
• /
• 1999

In most mail automatic processing centers, after facing and canceling, letter mails are passed through an Optical Character Recognition/Barcode Sorter(OCR/BS) to read the postal code and 3 of 5 fluorescent (luminescent) barcode is applied. Normally, 31%∼35% of this mails are rejected. The main reasons for reading failures are poor printing quality of addresses and barcodes, script printing, writing in a cursive hand, variety fonts, and failure to locate the address. Our goal is to provide mailer with top quality service and customer barcode service as we move toward 100% barcoding automation of letter mail. In this paper, we propose a method of printing 3 of 5 customer barcode, postal code management, and detection of postal code based on postal address for increase the performance of automatic processing system in mail items. Using postal code generating rules, which are automatically extracted from postal addresses and address numbers, creates postal codes. The customer barcode support system is implemented by C++ language and runs on IBM PC under Windows 95.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.225-228
• /
• 2017

In this paper, we propose a methodology to deal with the IOT system gradually as the use of effective systems such as electronic devices, healthcare, smart cars, smart home, remote meter reading and telemedicine closely related to our real life in the IOT system An IOT integrated account solution is needed as a way to address these needs as the demand grows for the need to identify and manage how users access and use the system for what period of time and at what point in time. We propose the communication algorithms for endpoint system, IOT system management rights policy, user information, and how to apply them to IOT system smart car and smart home on each object internet.

• Korean Journal of Digital Imaging in Medicine
• /
• v.6 no.1
• /
• pp.31-40
• /
• 2003

Purpose : In a PACS(Picture Archiving Communications System) environment, which is a very important component in a digital medical environment, the compression of digital medical images is a necessary and effective feature. In a current system where JPEG is applied to the compression of medical images, this study is to examine effectiveness and suitability when the JPEG2000, a more advanced compression algorithm for still images, is applied to the compression of medical images. In this thesis, we attempt to address the compressibility for effective clinical usage when compressing medical images, applying the objectivization of clinical evaluation as a function of compressibility. In the experiment al method, the compression was applied at a fixed rate using JPEG2000, and the n the result was compared with compressed images by JPEG. Method : For the performance evaluation, we choose SNR(Signal to Noise Ratio) measurement of an objective evaluation of definition and analyze a subjective evaluation by the ROC(Receiver Operating Characteristic) method. The results of the experiment showed that in the case of JPEG2000 there is hardly any distortion of images, even at high compression ratio(100:1), while regarding noise, the SNR remains around about 40dB, which is also relatively high. Before reading by reference to evaluative materials concerning objective compressed images, it is impossible to apply high compression to images : however, after reading, this can be applied to images that have already existed for some time.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.536-541
• /
• 2000

Turbo code has excellent decoding performance but had limitations for real time communications because of the system complexity and time delay in decoding procedure. To overcome this problem, a new SRI(Semi-Random Interleaver) algorithm which realize the reduction of the interleaver size is proposed for reducing the time delay during the decoding prodedure. SRI compose the interleaver 0.5 size from the input data sequence. In writing the interleaver, data is recorded by row such as block interleaver. But, in reading, data is read by randomly and the text data is located by the just address simultaneously. Therefore, the processing time of with the preexisting method such as block, helical random interleaver.