• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.77-83
• /
• 1999

With a surge of interest in OCR in 1990s a large number of handwriting or h handprinting databases have been built one after another around the world. One problem that researches encounter today is that all the databases differ in various ways including the script qualities. This paper proposes a method for measuring handwriting qualities that can be used for comparison of databases and objective test for character recognizers. The key idea i involved is classifying character samples into a number of groups each characterizing a set of qualities. In order to evaluate the proposed method we carried out experiments on KU-1 database. The result we achieve is meaningful and the method is helpful for the target tasks.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1641-1652
• /
• 2021

To analyze the crime scene, the role of digital evidence such as CCTV and black box is very important. Such digital evidence is often damaged due to device defects or intentional deletion. In this case, the deleted video can be restored by well-known techniques like the frame-based recovery method. Especially, the data such as the video can be generally fragmented and saved in the case of the memory used almost fully. If the fragmented video were recovered in units of images, the sequence of the recovered images may not be continuous. In this paper, we proposed a new video restoration method to match the sequence of recovered images. First, the images are recovered through a frame-based recovery technique. Then, after analyzing the time information marked on the images, the time information was extracted and recognized via optical character recognition (OCR). Finally, the recovered images are rearranged based on the time information obtained by OCR. For performance evaluation, we evaluate the recovery rate of our proposed video restoration method. As a result, it was shown that the recovery rate for the fragmented video was recovered from a minimum of about 47% to a maximum of 98%.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.441-447
• /
• 2022

In this paper, we propose a pill identification model using engraved text feature and image feature such as shape and color, and compare it with an identification model that does not use engraved text feature to verify the possibility of improving identification performance by improving recognition rate of the engraved text. The data consisted of 100 classes and used 10 images per class. The engraved text feature was acquired through Keras OCR based on deep learning and 1D CNN, and the image feature was acquired through 2D CNN. According to the identification results, the accuracy of the text recognition model was 90%. The accuracy of the comparative model and the proposed model was 91.9% and 97.6%. The accuracy, precision, recall, and F1-score of the proposed model were better than those of the comparative model in terms of statistical significance. As a result, we confirmed that the expansion of the range of feature improved the performance of the identification model.

• Journal of Broadcast Engineering
• /
• v.13 no.4
• /
• pp.463-478
• /
• 2008

A Distributed Translator Network(DTxR) is a cost-effective and frequency-effective method which can use existing transmission utilities and can be constructed in a shorter time as compared with Multiple Frequency Network(MFN) or Single Frequency Network(SFN) using On Channel Repeater(OCR). In order to verify the feasibility of DTxR, this field test was done in 30 points of north-west area in Seoul using 3rd, 5th, and 6th generation DIV receivers. Electric field strength, noise margin and ease of reception were measured and subjective evaluation of video quality was done in these points during the field test. With the test result, an improvement of receiving quality was obtained and an ease of reception was increased in case of the 5th. and 6th. receiver. From the results, we conclude that DTxR is a feasible method in DIV networks.

• International Journal of Contents
• /
• v.5 no.3
• /
• pp.50-56
• /
• 2009

Internet is being used for several activities by a great range of users. These activities include communication, e-commerce, education, and entertainment. Users are required to register regarding website in order to enroll web activities. However, registration can be done by automated hacking software. That software make false enrollments which occupy the resources of the website by reducing the performance and efficiency of servers, even stop the entire web service. It is crucial for the websites to have a system which has the capability of differing human users and computer programs in reading images of text. Completely Automated Public Turing Test to Tell Computers and Human Apart (CAPTCHA) is such a defense system against Optical Character Recognition (OCR) software. OCR can be defined as software which work for defeating CAPTCHA images and make countless number of registrations on the websites. This study proposes a new CAPTCHA context that is Korean CAPTCHA by means of the method which is splitting CAPTCHA images into several parts with random rotation values, and drawing random lines on a grid background by using Korean characters only. Lines are in the same color with the CAPTCHA text and they provide a distortion of image with grid background. Experimental results show that Korean CAPTCHA is a more secure and effective CAPTCHA type for Korean users rather than current CAPTCHA types due to the structure of Korean letters and the algorithm we are using: rotation and splitting. In this paper, the algorithm of our method is introduced in detail.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.222-227
• /
• 2022

In this paper, we implemented a Korean text generation and classification model based on a deep learning algorithm that can be applied to various industries. It consists of two implemented GAN-based Korean handwriting generation models and CNN-based Korean handwriting classification models. The GAN model consists of a generator model for generating fake Korean handwriting data and a discriminator model for discriminating fake handwritten data. In the case of the CNN model, the model was trained using the 'PHD08' dataset, and the learning result was 92.45. It was confirmed that Korean handwriting was classified with % accuracy. As a result of evaluating the performance of the classification model by integrating the Korean cursive data generated through the implemented GAN model and the training dataset of the existing CNN model, it was confirmed that the classification performance was 96.86%, which was superior to the existing classification performance.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.31-38
• /
• 2024

In this paper, we propose an ASAP(AI-driven Service for Advertisement Production) application that provides a generative AI-based automatic advertising image production service. This application utilizes GPT-3.5 Turbo Instruct to generate suitable background mood and promotional copy based on user-entered keywords. It utilizes OpenAI's DALL·E 3 model and Stability AI's SDXL model to generate background images and text images based on these inputs. Furthermore, OCR technology is employed to improve the accuracy of text images, and all generated outputs are synthesized to create the final advertisement. Additionally, using the PILLOW and OpenCV libraries, text boxes are implemented to insert details such as phone numbers and business hours at the edges of promotional materials. This application offers small business owners who face difficulties in advertising production a simple and cost-effective solution.

• Journal of KIISE:Software and Applications
• /
• v.29 no.8
• /
• pp.573-583
• /
• 2002

Pattern recognition process is made up of the feature extraction in the pre-processing, the pattern clustering by training and the recognition process. This paper presents the F-LVQ (Fuzzy Learning Vector Quantization) pattern classification model which is optimized by the fuzzy membership function for the OCR(Optical Character Recognition) system. We trained 220 numeric patterns of 22 Hangul and English fonts and tested 4840 patterns whose forms are changed variously. As a result of this experiment, it is proved that the proposed model is more effective and robust than other typical LVQ models.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.05a
• /
• pp.158.2-158.2
• /
• 2011

DME is acronym of dimethyl ether, which is spotlighted as an ideal fuel to produce hydrogen due to its high hydrogen/carbon ratio, high energy density and easiness to carry. In this research, we calculated thermodynamic hydrogen (or syngas) yield from DME autothermal reforming and compared to other fuels. The reforming efficiency was about 80% above $700^{\circ}C$. Lower OCR has higher reforming efficiency but, it requires additional heat supply since the reactions are endothermic. SCR has no significant effect on the reforming efficiency. The optimized condition is $700^{\circ}C$, SCR 1.5, OCR 0.45 without additional heat supply. Comparing to other commercial gaseous fuels (methane and propane), DME has higher selectivity of $H_2O$ and $CO_2$ than the others due to the oxygen atom in the molecule. To apply DME autothermal reforming to real system, a proper catalyst is required. Therefore, it is performed the experiment comparing various novel metal catalysts based on CGO. Experiments were performed at calculated condition. The composition of product was measured and reforming efficiency was calculated. The catalysts have similar efficiency at high temperature(${\sim}800^{\circ}C$) but, CGO-Ru has the highest efficiency at low temperature ($600^{\circ}C$).

• International journal of advanced smart convergence
• /
• v.10 no.3
• /
• pp.66-71
• /
• 2021

Recent healthcare environments have characteristics of expanding the scope of healthcare-impacting healthcare, complexity resulting from diversification of components, and accelerating the pace of change. Drugs are used for the prevention, mitigation, and treatment of diseases, so they can inevitably cause harm, while they have efficacy and effectiveness, which are key elements of health recovery. Therefore, many countries regulate permits for safe and effective medicines, and also designate essential drugs directly related to life as pay targets and guarantee health insurance. Especially Pharmacist relying on manpower for composition medicine is liable for mal-manufacture due to combination of toxic medical substances or other chemical usage. In this paper, we focus on using Kiosk and Optical Character Recognition (OCR) for automated pharmacy to level up medical service and create labor friendly environment for pharmacist themselves through maintenance of prescription data and automated manufacturing solution. Presentation of drug substances and precautions will lead to efficient drug prescription and prevent misuse of information while auto manufacturing system efficiently maintain labor force and raise patient satisfaction level by reduction of waiting time.