• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.385-396
• /
• 2005

In this paper, a new structural approach to on-line signature verification is presented. A primitive pattern is defined as a part segmented by a local minimal position of speed. And a structural description of signature is composed of subpatterns which are defined as such forms as rotation shape, cusp shape and bell shape, acquired by composition of the primitives regarding the directional changes. As the matching method to find identical parts between two signatures, a modified DP(dynamic programming) matching algorithm is presented. And also, variation and complexity of local parts are computed from the training samples, and reference model and decision boundary are derived from these. Error rate, execution time and memory usage are compared among the functional approach, the parametric approach and the proposed structural approach. It is found that the average error rate can be reduced from 14.2% to 4.05% when the local parts of a signature are weighted and the complexity is used as a factor of decision threshold. Though the error rate is similar to that of functional approaches. time consumption and memory usage of the proposed structural approach are shown to be very effective.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.185-196
• /
• 1999

In this dissertation, a new off-line recognition system is proposed using a subgraph pattern, neural network. After thinning is applied to input characters, balance having a noise elimination function on location is performed. Then as the first step for recognition procedure, circular elements are extracted and recognized. From the subblock HT, space feature points such as endpoint, flex point, bridge point are extracted and a subgraph pattern is formed observing the relations among them. A region where vowel can exist is allocated and a candidate point of the vowel is extracted. Then, using the subgraph pattern dictionary, a vowel is recognized. A same method is applied to extract horizontal vowels and the vowel is recognized through a simple structural analysis. For verification of recognition subgraph in this paper, experiments are done with the most frequently used Myngjo font, Gothic font for printed characters and handwritten characters. In case of Gothic font, character recognition rate was 98.9%. For Myngjo font characters, the recognition rate was 98.2%. For handwritten characters, the recognition rate was 92.5%. The total recognition rate was 94.8% with mixed handwriting and printing characters for multi-font recognition.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.10
• /
• pp.329-336
• /
• 2014

Pipe spool is the most important element of plant equipment in plant construction site. Currently, the plant construction site manage the pipe spool location and usage history by handwriting. Frequently, the pipe spool is moved to unpredictable places by field workers in many construction sites and in cases like this, the pipe stool is replaced with another similar pipe spool. Since it's hard to determine the exact location of some of the pipe spools, it takes unnecessary time and labour to find the missing pipe spools, which proves that stock management is not under control. The purpose of our system is to make the identification of real-time location of the field pipes possible by attaching UHF RFID tags to the pipe spool, which will be used to connect with UHF RFID reader and antenna on vehicles. A field test conducted by the proposed system resulted in the success rate of 98% and the missing 2% was recuperated by hands-on correction, which proved that stock management through the proposed method can be 100% effective. The proposed system is expected to reduce labour costs and make stock control of assets possible, as well as applicable to similar stock management environments.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.6
• /
• pp.49-56
• /
• 2020

The virtual Korean keyboard system is a method of inputting characters by touching a fixed position. This system is very inconvenient for people who have difficulty moving their fingers. To alleviate this problem, this paper proposes an efficient framework that enables keyboard input and handwriting through video and user motion obtained through the RGB camera of the mobile device. To develop this system, we use face recognition to calculate control coordinates from the input video, and develop an interface that can input and combine Hangul using this coordinate value. The control position calculated based on face recognition acts as a pointer to select and transfer the letters on the keyboard, and finally combines the transmitted letters to integrate them to perform the Hangul keyboard function. The result of this paper is an efficient writing system that utilizes face recognition technology, and using this system is expected to improve the communication and special education environment for people with physical disabilities as well as the general public.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.946-954
• /
• 2021

Since COVID19 virus has been occured, variety steps of the quarantine guidelines were enacted. In step 2.5, eating in a cafe was prohibited and only takeout was permitted, but the government has changed several rules. So now people can have a dissert or coffee in the cafe. Though the government adviced available staying time as 1 hour, it is not obeyed often except superstore, and even the management depends on handwriting. In this paper, we implemented a blockchain system to use for this case. This system is implemented with using hyperledger fabric, the blockchain framework which is made by IBM. For a test, 1 organization is in the system and chaincode is installed to the organization to run the system. We expect the certain effect to the quarantine via this system. Moreover, we will develop an application by using this system as a backend.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.790-791
• /
• 2016

The system used in the laboratory of chemistry and medical is management only by measuring the temperature inside the reagent management within and recording in handwriting. When you hold the reagent, it can not recognize in real time the problems that occur in the interior, an accident occurs. you can not find a use record reagent storage, a problem with the management of an efficient reagent can be generated. In this paper, we propose a reagent management system that leverages the embedded boards and sensors in the laboratory reagents effectively manage to resolve it. As a result, Converting the information of the reagent to the data using the NFC, the administrator can identify the reagent user to register and manage hazardous reagents. Converted by using the NFC information of the reagent to the data, the administrator can identify the reagent user to register and manage hazardous reagents, temperature, humidity, so that it can be controlled by utilizing the VOC sensor to. Also it is passes the message to the administrator in the event of a particular risk situation. This is believed to enable the effective administration in a laboratory reagent.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1271-1279
• /
• 2020

Text region detection is a technology that detects text area in handwriting or printed documents. The detected text areas are digitized through a recognition step, which is used in various fields depending on the purpose of use. However, the detection result of the small text unit is not suitable for the industrial field. In addition, the border of tables in the document that it causes miss-detected results, which has an adverse effect on the recognition step. To solve the issues, we propose a method for detecting text region using the border information of the table. In order to utilize the border information of the table, the proposed method adjusts the flow of two decoders. Experimentally, we show improved performance using the table border pseudo label based on weak supervised learning.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.1
• /
• pp.1-10
• /
• 2022

This study is a marketing tool for securing loyal customers and increasing sales by developing a customizing manual according to the change of segmented nail art consumption pattern due to the development of the nail industry and performing art to meet the needs of various customers and increase satisfaction. This was done to demonstrate the possibility of use. In order to develop a manual for the study, we conducted a survey that combined an online survey and in-person survey for ordinary citizens in their 20s and 50s living in Busan and Gyeongnam. Taste (50.0%) was the highest, and personal preference (62.9%) was also the highest for items related to nail art color selection, suggesting that the consumption pattern is changing to require a variety of personal art preferences rather than recommendations or recommendations from practitioners. Could know. As a result of performing nail art by applying the customizing manual developed based on customer selection, opinions were shown in the order of reliability (39.1%), attachment (39.1%), and rarity (26.1%). Utilization (73.9%) was also high in the question of 'If customizing manual was developed as an app', and overall satisfaction with the art selected by the customer was high, indicating that the customer had a high degree of attachment to the nail art design decided by the customer. As for the improvement points of the manual, it was possible to confirm the necessity of developing the app with the majority opinion that handwriting was inconvenient. Based on the nail art customizing manual of this study, the follow-up research proceeds with the app production and utilization process, and it is hoped that it will be used as a basic data for sales promotion by increasing customer satisfaction according to the rapidly changing consumption patterns of nail customers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.24-31
• /
• 2023

Meta-learning is metacognition that instantly distinguishes between knowing and unknown. It is a learning method that adapts and solves new problems by self-learning with a small amount of data.A few-shot learning method is a type of meta-learning method that accurately predicts query data even with a very small support set. In this study, we propose a method to solve the limitations of the prototype created with the mean-point vector of each class. For this purpose, we use the few-shot learning method that created the prototype used in the few-shot learning method as the median prototype. For quantitative evaluation, a handwriting recognition dataset and mini-Imagenet dataset were used and compared with the existing method. Through the experimental results, it was confirmed that the performance was improved compared to the existing method.