• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Journal of Families and Better Life
• /
• v.22 no.4
• /
• pp.43-61
• /
• 2004

The purpose of this study was to verify the usefulness of kinetic House- Tree- Person drawing as a diagnostic measure for the degree of self-differentiation, which is an essential part of college students' development. Participants for the study were four hundred thirty five(272 male and 163 female) university freshmen enrolled in 4-year colleges located in Pusan. The Participants completed a scale of self-differentiation and a Kinetic House- Tree-Person drawings test. The evaluation system for kinetic House-Tree-Person drawings was established based on the indexes of Buck(1948) and Bums(1972) and used exiting literatures as reference. The data were analyzed using means, standard deviations, t-test, one-way ANOVA, and Scheffe's test. The results obtained from the study are as follows: First, the mean level of college students' self-differentiation was 2.81, which is about average. Some significant gender differences were found in the areas of self-intergration, family projection, and emotional separation. Male students scored higher on self-intergration, whereas female students score higher on family projection and emotional separation. Second. self-differentiation was higher when the student drew a house with smoke coming out of the chimney, a single-story house with flat roof, or with detailed description of curtains, roof and roof tiles. Third, self-differentiation seemed to be higher when branches and fruits were included, when there was no expression of roots, when large crowns and branch openings were presented, and when no slant lines or base lines appeared. Forth, self-differentiation showed ㅁ higher level when the portrait shows eyes, mouth and neck without omission, when it included the whole body instead of face only, and when there was no person with just a profile, a back, or with a stiff posture, and when there was no weak and thin lines. Individuality also marked higher if a person was in motion and than one person was added. Finally, self-differentiation showed significant difference according to the overall harmony of the drawing, ordering of contents, hand pressure, the kind and shape of tree, and presence of other persons. The more harmonious the picture was, and the more family members are added, the higher the level of self-differentiation was.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2002.09a
• /
• pp.228-230
• /
• 2002

The relative electron density resolution was discussed by the noise power spectrum (NPS) in the heavy ion CT image. The heavy ion beam $\^$12/C accelerated up to 400MeV/u by RIMAC was used in this study. The two-dimensional (2-D) NPS in the CT image was obtained from the one-dimensional (1-D) NPS of the measured residual range distribution of water phantom for single projection, and the noise variance in the CT image was calculated from 2-D NPS. The technique used in the reconstruction was the filtered back-projection method with Shepp-Logan filter. The calculated value suggests the result of our previous works using the density resolution phantom, assuming that the relative electron density resolution is twice the standard deviation. Therefore, the estimation of the noise in CT images by 2-D NPS obtained the measured residual range distribution is the useful method.

• Journal of Preventive Medicine and Public Health
• /
• v.24 no.3 s.35
• /
• pp.305-313
• /
• 1991

In order to investigate industrial fatigue due to visual display terminal (VDT) work of banking operations the questionnaire survey for subjective symptoms of fatigue was carried out on 470 bank clerks who had been engaged in VDT work for various length of work hours. The questionnaires comprised three groups of 10 items each, representing dullness and sleepiness (level of cerebral activation), difficulty in concentration (level of motivation) and bodily projection of fatigue. The results were as follows : 1. Of the 30 items of questionnaires, the highest percentage was accounted for by 'eye strain' (51.5% ), followed by 'feel stiffness in the neck or the shoulders'(33.4%), 'feel a pain in the low back'(26.8%), 'whole body feels tired'(19.6%) and 'feel headache'(17.9%) in the order of sequence. 2. The average weighted score for the first group of questionnaire items (dullness and sleepiness) was the largest among three groups and was followed by 'the third cup (bodily projection of fatigue) and the second item group (difficulty in concentration) in the order of sequence, suggesting the heavier mental stress of VDT work in banking operations rather than physical burden. 3. In terms of the age and sex of workers, work duration and VDT work percentage, the difference in average weighted score was noted only between sex, the score of female being larger than that of male. 4. The complaint rates of subjective symptoms showed close associations with the subjective optimums of room temperature, ventilation, illumination and noise level. 5. The significant correlation was showed between age, work duration and item of 'whole body feels tired', between VDT work percentage and items of 'eye strain' and 'feel stiffness in the neck or shoulders' and between all items of subjective symptoms.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.1
• /
• pp.8-14
• /
• 2007

X-ray digital tomosynthesis is widely used in the nondestructive testing and evaluation, especially for the printed circuit boards (PCBs). In this study, we propose a simple method to reduce the blur artefact, frequently claimed in the conventional digital tomosynthesis based on SAA (shift-and-add) algorithm, and thus restore the image sharpness. The proposed method is basically based on the SAA, but has a correction procedure by finding blur artefacts from the forward-and back-projection for the firstly obtained, manipulated backprojection data. The manipulation is the replacement of the original data at the POI (plane-of-interest) by zeros. This method has been compared with the conventional SAA algorithm using the experimental measurements and Monte Carlo simulation for the designed PCB phantom. The comparison showed a much enhancement of sharpness in the images obtained from the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.35-44
• /
• 2007

Since the omnidirectional camera system with a very large field of view could take many information about environment scene from few images, various researches for calibration and 3D reconstruction using omnidirectional image have been presented actively. Most of line segments of man-made objects we projected to the contours by using the omnidirectional camera model. Therefore, the corresponding contours among images sequences would be useful for computing the camera transformations including rotation and translation. This paper presents a novel two step minimization method to estimate the extrinsic parameters of the camera from the corresponding contours. In the first step, coarse camera parameters are estimated by minimizing an angular error function between epipolar planes and back-projected vectors from each corresponding point. Then we can compute the final parameters minimizing a distance error of the projected contours and the actual contours. Simulation results on the synthetic and real images demonstrated that our algorithm can achieve precise contour matching and camera motion estimation.

• Journal of the Korean Society of Radiology
• /
• v.83 no.3
• /
• pp.669-679
• /
• 2022

Purpose To evaluate the feasibility of pediatric low-dose facial CT reconstructed with filtered back projection (FBP) using adequate kernels. Materials and Methods We retrospectively reviewed the clinical and imaging data of children aged < 10 years who underwent facial CT at our emergency department. The patients were divided into two groups: low-dose CT (LDCT; Group A, n = 73) with a fixed 80-kVp tube potential and automatic tube current modulation (ATCM) and standard-dose CT (SDCT; Group B, n = 40) with a fixed 120-kVp tube potential and ATCM. All images were reconstructed with FBP using bone and soft tissue kernels in Group A and only bone kernel in Group B. The groups were compared in terms of image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Two radiologists subjectively scored the overall image quality of bony and soft tissue structures. The CT dose index volume and dose-length product were recorded. Results Image noise was higher in Group A than in Group B in bone kernel images (p < 0.001). Group A using a soft tissue kernel showed the highest SNR and CNR for all soft tissue structures (all p < 0.001). In the qualitative analysis of bony structures, Group A scores were found to be similar to or higher than Group B scores on comparing bone kernel images. In the qualitative analysis of soft tissue structures, there was no significant difference between Group A using a soft tissue kernel and Group B using a bone kernel with a soft tissue window setting (p > 0.05). Group A showed a 76.9% reduction in radiation dose compared to Group B (3.2 ± 0.2 mGy vs. 13.9 ± 1.5 mGy; p < 0.001). Conclusion The addition of a soft tissue kernel image to conventional CT reconstructed with FBP enables the use of pediatric low-dose facial CT protocol while maintaining image quality.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.263-271
• /
• 2016

Localizing an object in image is a common task in the field of computer vision. As the existing methods provide a detection for the single object in an image, they have an utilization limit for the use of the application, due to similar objects are in the actual picture. This paper proposes an efficient method of object localization for image recognition. The new proposed method uses color correlation back-projection in the YCbCr chromaticity color space to deal with the object localization problem. Using the proposed algorithm enables users to detect and locate primary location of object within the image, as well as candidate regions can be detected accurately without any information about object counts. To evaluate performance of the proposed algorithm, we estimate success rate of locating object with common used image database. Experimental results reveal that improvement of 21% success ratio was observed. This study builds on spatially localized color features and correlation-based localization, and the main contribution of this paper is that a different way of using correlogram is applied in object localization.

• The Korean Journal of Applied Statistics
• /
• v.31 no.4
• /
• pp.427-446
• /
• 2018

Korea will have a super-aged society within only 30 years according to the United Nations' definition of an aging society and the statistics on Korea's Population projections (2016), indicates that Korea has the fastest ageing speed in the world. There is a lack of data on long-term time-series data on death as related to pension and welfare policies compared to the rapid rate of aging. This paper estimates life expectancy over 245 years (from 1955 to 2200) through past and future forecasts as well as compares the expected life expectancy of the synthetic cohort and the real cohort. In addition, an international comparisons were made to understand the level of aging in Korea. Estimates of the back-projection period were compared with previous studies and the LC model to improve accuracy and objectivity. In addition, the predictions after 2016 reflected the declined mortality rate effect of Korea using the LC-ER model. The results showed an increase in life expectancy of about 30 years over 60 years (1955-2015) with an expected life expectancy of the real cohort over the second century (1955-2155) higher than the synthetic cohort. The comparative advantage of life expectancy of real cohorts was confirmed to be a common trend among comparative countries. In addition, Japan and Korea have a higher life expectancy and starting from 85 to 90 years old, all comparative countries show that the growth rate for the life expectancy of synthetic and real cohorts is less than previous years.

• Korean Journal of Remote Sensing
• /
• v.36 no.3
• /
• pp.449-460
• /
• 2020

Super-resolution is a technique used to reconstruct an image with low-resolution into that of high-resolution. Recently, deep-learning based super resolution has become the mainstream, and applications of these methods are widely used in the remote sensing field. In this paper, we propose a super-resolution method based on the deep back-projection network model to improve the satellite image resolution by the factor of four. In the process, we customized the loss function with the edge loss to result in a more detailed feature of the boundary of each object and to improve the stability of the model training using generative adversarial network based on Wasserstein distance loss. Also, we have applied the detail preserving image down-scaling method to enhance the naturalness of the training output. Finally, by including the modified-residual learning with a panchromatic feature in the final step of the training process. Our proposed method is able to reconstruct fine features and high frequency information. Comparing the results of our method with that of the others, we propose that the super-resolution method improves the sharpness and the clarity of WorldView-3 and KOMPSAT-2 images.