• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.282-291
• /
• 2022

This research applies a pre-trained bidirectional encoder representations from transformers (BERT) handwriting recognition model to predict foreign Korean-language learners' writing scores. A corpus of 586 answers to midterm and final exams written by foreign learners at the Intermediate 1 level was acquired and used for pre-training, resulting in consistent performance, even with small datasets. The test data were pre-processed and fine-tuned, and the results were calculated in the form of a score prediction. The difference between the prediction and actual score was then calculated. An accuracy of 95.8% was demonstrated, indicating that the prediction results were strong overall; hence, the tool is suitable for the automatic scoring of Korean written test answers, including grammatical errors, written by foreigners. These results are particularly meaningful in that the data included written language text produced by foreign learners, not native speakers.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.178-185
• /
• 2009

A signal processing algorithm is proposed for end point detection which is used commonly in accelerometers-based pattern recognition problem. In the conventional method, end points are detected by manual manipulation with an additive button or algorithm based on statistical computation and highpass filtering to cause critical time delay and difficulty for parameters optimization. As an solution, we propose a focused Time Lagged Feedforward Network(TLFN) with respect to a differential signal of acceleration, which is widely applied for time series forecasting. The simple experiment is conducted with handwriting and the detection performance and response characteristic of the proposed algorithm is tested and analyzed.

• Journal of International Academy of Physical Therapy Research
• /
• v.4 no.2
• /
• pp.588-594
• /
• 2013

This study was carried out to investigate the effects of making an origami crane on the improvement of hand dexterity. Subjects composed of 20 normal adult males were randomly assigned to experimental and control groups of 10 people respectively. For the experimental group, a training of making an origami crane was conducted for 40 to 50 minutes a day during a 4-week training period. The control group was made to engage in everyday activities as usual. For pre and post assessment, Groove Pegboard test, Purdue Pegboard Test, and Jebsen Hand Function Test were used. The results on the effects of making an origami crane showed that there was a statistically significant difference in both the Grooved Pegboard test and Purdue Pegboard test(p<.05). In the Jebsen hand function Test, a significant difference was found in handwriting and building pieces of chess(p<.05), but there was no statistically significant difference in comparison with the right hand during the average performance of picking up small stuffs. The activity of making an origami crane for normal adults was confirmed to be helpful to improve the hand dexterity. Accordingly, making an origami crane is suggested to be an effective way to improve the hand dexterity.

• Journal of Computing Science and Engineering
• /
• v.10 no.2
• /
• pp.39-50
• /
• 2016

In this paper, we present a comparative study of spatial domain features for writer identification and verification with different ink width conditions. The existing methods give high error rates, when comparing two handwritten images with different pen types. To the best of our knowledge, we are the first to design the feature with different ink width conditions. To address this problem, contour based features were extracted using a chain code method. To improve accuracy at higher levels, we considered histograms of chain code and variance in bins of histogram of chain code as features to discriminate handwriting samples. The system was trained and tested for 1,000 writers with two samples using different writing instruments. The feature performance is tested on our newly created dataset of 4,000 samples. The experimental results show that the histogram of chain code feature is good compared to other methods with false acceptance rate of 11.67%, false rejection rate of 36.70%, average error rates of 24.18%, and average verification accuracy of 75.89% on our new dataset. We also studied the effect of amount of text and dataset size on verification accuracy.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1114-1135
• /
• 2018

A multiple classification system based on a new boosting technique has been approached utilizing different biometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting, palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometric traits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system is comprised of three different super-classifiers to individually perform person identification. The individual classifiers corresponding to each super-classifier in their turn identify different biometric features and their conclusions are integrated together in their respective super-classifiers. The decisions from individual super-classifiers are integrated together through a mega-super-classifier to perform the final conclusion using programming based boosting. The mega-super-classifier system using different super-classifiers in a compact form is more reliable than single classifier or even single super-classifier system. The system has been evaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrix for each of the single classifiers, super-classifiers and finally the mega-super-classifier. The different performance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.1
• /
• pp.97-107
• /
• 2002

In this paper, we propose the realization of on-line handwritten Chinese character recognition for mobile personal digital assistants (PDA). We focus on the development of an algorithm having a high recognition performance under the restriction that PDA requires small memory storage and less computational complexity in comparison with PC. Therefore, we use index matching method having computational advantage for fast recognition and we suggest a unit reconstruction method to minimize the memory size to store the character models and to accomodate the various changes in stroke order and stroke number of each person in handwriting Chinese characters. We set up standard model consisting of 1800 characters using a set of pre-defined units. Input data are measured by similarity among candidate characters selected on the basis of stroke numbers and region features after preprocessing and feature extracting. We consider 1800 Chinese characters adopted in the middle and high school in Korea. We take character sets of five person, written in printed style, irrespective of stroke ordering and stroke numbers. As experimental results, we obtained an average recognition time of 0.16 second per character and the successful recognition rate of 94.3% with MIPS R4000 CPU in PDA.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.4
• /
• pp.165-169
• /
• 2017

CNN(Convolutional Nerual Network) is one of the algorithms that show superior performance in image recognition and classification among machine learning algorithms. CNN is simple, but it has a large amount of computation and it takes a lot of time. Consequently, in this paper we performed an parallel processing unit for the convolution layer, pooling layer and the fully connected layer, which consumes a lot of handling time in the process of CNN, through the SIMT(Single Instruction Multiple Thread)'s structure of GPGPU(General-Purpose computing on Graphics Processing Units).And we also expect to improve performance by reducing the number of memory accesses and directly using the output of convolution layer not storing it in pooling layer. In this paper, we use MNIST dataset to verify this experiment and confirm that the proposed CNN structure is 12.38% better than existing structure.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.6
• /
• pp.1345-1352
• /
• 2010

The structural approach in the signature verification, representing a signature as a structural form of local primitives, shows an excellent performance since it counts in the local characteristics such as local variation, stroke complexity, and etc. However, this method has a problem of template data sizing which can not fix the number of subpatterns comprising a signature. In this paper, we proposed a new algorithm to reduce the signature data into a fixed size by selecting a fixed number of subpatterns which is considered as important parts. As a result, it shows more excellent performance when the fixed sized sub-patterns is applied with local weights extracted from variational characteristics and complexities in local part. And the number of subpatterns representing a signature reference model can be fixed under a certain number of segments determined appropriately.

• Journal of Internet Computing and Services
• /
• v.6 no.1
• /
• pp.105-114
• /
• 2005

This paper describes a new measuring technique by analysing multiple time-series patterns. This paper's goal is that extracts a really measured value having a sample pattern which is the best matched with an inputted time-series, and calculates a difference ratio with the value. Therefore, the proposed technique is not a recognition but a measurement. and not a hardware but a software. The proposed technique is consisted of three stages, initialization, learning and measurement. In the initialization stage, it decides weights of all parameters using importance given by an operator. In the learning stage, it classifies sample patterns using LBG and DTW algorithm, and then creates code sequences for all the patterns. In the measurement stage, it creates a code sequence for an inputted time-series pattern, finds samples having the same code sequence by hashing, and then selects the best matched sample. Finally it outputs the really measured value with the sample and the difference ratio. For the purpose of performance evaluation, we tested on multiple time-series patterns obtained from etching machine which is a semiconductor manufacturing.

• Journal of the Korean Applied Science and Technology
• /
• v.31 no.4
• /
• pp.688-693
• /
• 2014

This study is to increase the utilization of the ozonated water generator to make it easier to take advantage of the ozone water in the world today, there will be to develop a system that operates in one motion. Furthermore, olive oil and ozone is reacted with the wish to apply to the manufacturing technology. In the case of many existing products ozone generator driven mostly non-ozone system. In the case of ozone, but handwriting is implied general way pressure ozone gas leakage risks of suction force to the pump, it is the case of the challenge by using the injector, and limit the generation of ozone and ozone inhalation according to whether the water inlet leakage of existing products risk due to minimized. Despite the disadvantages of the injector system was found the effectiveness of the ozonated water production unit injector system used in this study to maintain the microbiological disinfection performance.