• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.114-117
• /
• 2002

본 논문에서는 미세한 차이를 식별할 수 있는 Chaos 이론을 숫자 패턴 인식 분야에 응용한다. 먼저, 숫자 영상의 특징 정보들을 시계열 데이터로 변환한 후, 제안된 수정된 에농 시스템으로부터 숫자 어트랙터를 재구성하고, 어트랙터의 특성 분석을 위해 프랙탈 차원 특징을 나타내는 정보 차원값을 이용하여 숫자를 인식하는 새로운 알고리즘을 제안함으로써, 특수한 용도로 숫자를 전문적으로 빠르고 정확하게 인식하는 고정도 숫자 인식 시스템을 구현하였다.

• Proceedings of the KOSOMBE Conference
• /
• v.1993 no.05
• /
• pp.90-93
• /
• 1993

In this study, Korean speech was recognized by using spatio-temporal recognition neural network. The subjects of speech are numeric speech from zero to nine and basic command which might be used for motorized wheelchair developed it own Lab. Rabiner and Sambur's method of speech detection was used in determining end-point of speech, speech parameter was extracted by using LPC 16 order. The recognition rate was over 90%.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.383-386
• /
• 2002

In this paper, we investigated the pattern recognition performance of the numeric patterns (from 0 to 9) using DNA coding method. The pattern recognition performance of the DNA coding method is compared to the that of the GA(Genetic Algorithm). GA searches effectively an optimal solution via the artificial evolution of individual group of binary string using binary coding, while DNA coding method uses four-type bases denoted by A(Adenine), C(Cytosine), G(Guanine) and T(Thymine), The pattern recognition performance of GA and DNA coding method is evaluated by using the same genetic operators(crossover and mutation) and the crossover probability and mutation probability are set the same value to the both methods. The DNA coding method has better characteristics over genetic algorithms (GA). The reasons for this outstanding performance is multiple possible solution presentation in one string and variable solution string length.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.105-113
• /
• 1996

In this paper, a new korean digita speech recognition technique was proposed using muktolayer perceptron (MLP). In spite of its weakness in dynamic signal recognition, MLP was adapted for this model, cecause korean syllable could give static features. It is so simle in its structure and fast in its computing that MLP was used to the suggested system. MLP's input vectors was transformed using karhunen-loeve transformation (KLT), which compress signal successfully without losin gits separateness, but its physical properties is changed. Because the suggested technique could extract static features while it is not affected from the changes of syllable lengths, it is effectively useful for korean numeric recognition system. Without decreasing classification rates, we can save the time and memory size for computation using KLT. The proposed feature extraction technique extracts same size of features form the tow same parts, front and end of a syllable. This technique makes frames, where features are extracted, using unique size of windows. It could be applied for continuous speech recognition that was not easy for the normal neural network recognition system.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.55-60
• /
• 2017

The pulmonary function test (PFT) is an essential data source for evaluating the effect of drugs on the lungs or the status of lung function. However, the numeric values of PFT cannot be easily used for clinical studies without labor-intensive manual efforts, because PFTs are usually recorded as image files. This study was aimed at constructing a de-identified, open-access PFT database with various clinical information. For constructing the PFT database, optical character recognition (OCR), regular expression, and the parsing technique were used to extract alphanumeric data from the PFT images in a Korean tertiary teaching hospital. This longitudinal observational database contains 413,000 measurements of PFT from 183,000 patients.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.5
• /
• pp.701-710
• /
• 1995

A thinning algorithm is a very important procedure in order to increase recognition rate in the character recognition. This paper is the study of a parallel thinning algorithm available for the recognition of various characters, and it proposes the parallel thinning algorithm using the 8-neighbors connectivity value. Characteristics of the proposed algorithm are easiness of implementation of parallelism, the result of thinning is perfectly-8 connectivity and represented by numeric information. The proposed algorithm is very suitable for characters having many curve segments such as English, Japanese etc. Performance evaluation was performed by the measure of similarity to reference skeleton.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1125-1128
• /
• 1993

We propose the new method about the neural-based pattern recognition by using Hadamard transform for the improvement of learning speed, stability and flexibility of network. We can obtain the spatial feature of pattern by Hadamard transformed pattern. We carried out an experiment to estimate the effect of Hadamard transform. We tried the learning of numeric patterns, and tried the pattern recognition with noisy pattern. As a result, the learning times of the network for the 'Hadamard' case is smaller than that of usual case. And the recognition rate of the network for the 'Hadamard' case is higher than that of usual case, too.

• Journal of Korea Game Society
• /
• v.12 no.6
• /
• pp.121-130
• /
• 2012

Due to recent developments in smart media, the desire for interaction between humans and computers has increased. In order to satisfy these needs, gesture recognition fields have been actively studied using image processing. In this paper, we propose a method to recognize Chinese hand numeric representation using image processing. The method binarizes an input image based on skin color to extract region of interest and check the number using the angular information of stretched fingers. Our proposed method has 95.83% of recognition rate.

• Nuclear Engineering and Technology
• /
• v.25 no.3
• /
• pp.424-429
• /
• 1993

Numeric characters are printed at the end part of nuclear fuel rod containing nuclear pellets. Fuel rods are discriminated and managed systematically by these characters in the process of producing fuel assembly. The characters are also used to examine manufacturing process of fuel rods in the survey of burnup efficiency as well as in inspection of irradiated fuel rod. Therefore automatic character recognition is one of the most important technologies in automatic manufacture of fuel assembly. In this study, character recognition system is developed. In the developed system, mesh feature extracted from each character written in the fuel rod has been compared with reference feature value stored in database, and the character is thus identified. In the result of experiment, 95.83 percent recognition rate is achievable.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.94-97
• /
• 2003

In this Paper, propose for MLP(multilayer perception) neural network that uses optimization recognition training scheme for the wavelet transform and the numeral image add to noise, and apply this system in Numeral Recognition. As important part of original image information preserves maximum using the wavelet transform, node number of neural network and the loaming convergence time did size of input vector so that decrease. Apply in training vector, examine about change of the recognition rate as optimization recognition training scheme raises noise of data gradually. We used original image and original image added 0, 10, 20, 30, 40, 50㏈ noise (or the increase of numeral recognition rate. In case of test image added 30∼50㏈, numeral recognition rate between the original image and image added noise for training Is a little But, in case of test image added 0∼20㏈ noise, the image added 0, 10, 20, 30, 40 , 50㏈ noise is used training. Then numeral recognition rate improved 9 percent.