• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1256-1259
• /
• 2002

In this paper, we have proposed license plate recognition system for multi-national vehicle license plate using geometric features along with hybrid and seven segment pattern vectors. In the proposed system, we suggested to find horizontal and vertical relation after going through preparation process with inputted real-time license plate image of Korea and Japan, and then to classify license plate with using characteristic and geometric information of license plates. It classifies the extracted license plate images into letters and numbers, such as local name, local number, classification character and license consecutive numbers, and recognize license plate of Korea and Japan by applying hybrid and seven segments pattern vectors to classified letter and number region. License plate extraction step of the proposed system uses width and length information along with relative rate of Korean and Japanese license plate. Moreover, it exactly segmentation by letters with using each letter and number position information within license plate region, and recognizes Korean and Japanese license plates by applying hybrid and seven segment pattern vectors, containing characteristics related to letter size and movement within segmented letter area. As the result of testing the proposed system in real experiment, it recognized regardless of external lighting conditions as well as classifying license plates by nations, Korea and Japan. We have developed a system, recognizing regardless of inputted structural character of vehicle licenses and external environment.

• Korean journal of applied entomology
• /
• v.42 no.1
• /
• pp.57-63
• /
• 2003

Accurate forecasting of occurrence time and abundance of insect pests is essential for developing technology of integrated pest management system. Digital image processing algorithms were utilized to automatically recognize rice planthoppers which are major insect pests in the rice cultivation field and were subsequently used to estimate densities in the field for efficient forecasting of insect pests. To the images taken in the rice field, image decomposition, top-hat transformation, threshold, and minimum and maximum filter were implemented for patterning individually the brown planthopper specimens attached at the bottom area of rice stems. In average 95.8cio of images were correctly recognized for estimating densities by the developed system, and the recognition rate was higher than that obtained from direct observations by experienced observers. Furthermore, the size of the recognized specimens was measured and was used for estimating the age structure in the observed brown planthopper populations.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.383-389
• /
• 2004

In this paper. we propose the bias compensation methods and the eigenvoice method using the mean of dimensional eigenvoice to improve the performance of rapid speaker adaptation based on eigenvoice under mismatch between training and test environment. Experimental results for vocabulary-independent word recognition task (using PBW 452 DB) show that the proposed methods yield improvements for small adaptation data. We obtained about 22∼30% relative improvement by the bias compensation methods as amount of adaptation data varied from 1 to 50, and obtained 41% relative improvement in error rate by the eigenvoice method using the mean of dimensional eigenvoice with only single adaptation word.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.410-419
• /
• 2004

In this paper. we propose a method of confidence measure fusion under Bayesian framework for speech recognition. Centralized and distributed schemes are considered for confidence measure fusion. Centralized fusion is feature level fusion which combines the values of individual confidence scores and makes a final decision. In contrast. distributed fusion is decision level fusion which combines the individual decision makings made by each individual confidence measuring method. Optimal Bayesian fusion rules for centralized and distributed cases are presented. In isolated word Out-of-Vocabulary (OOV) rejection experiments. centralized Bayesian fusion shows over 13% relative equal error rate (EER) reduction compared with the individual confidence measure methods. In contrast. the distributed Bayesian fusion shows no significant performance increase.

• Journal of Integrative Natural Science
• /
• v.11 no.3
• /
• pp.131-138
• /
• 2018

In this paper, we have implemented speeches that utilized the emotion information of the user's speech and image matching and recommendation system. To classify the user's emotional information of speech, the emotional information of speech about the user's speech is extracted and classified using the PLP algorithm. After classification, an emotional DB of speech is constructed. Moreover, emotional color and emotional vocabulary through factor analysis are matched to one space in order to classify emotional information of image. And a standardized image recommendation system based on the matching of each keyword with the BM-GA algorithm for the data of the emotional information of speech and emotional information of image according to the more appropriate emotional information of speech of the user. As a result of the performance evaluation, recognition rate of standardized vocabulary in four stages according to speech was 80.48% on average and system user satisfaction was 82.4%. Therefore, it is expected that the classification of images according to the user's speech information will be helpful for the study of emotional exchange between the user and the computer.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.27 no.1
• /
• pp.61-69
• /
• 2014

In this paper, we have researched semiconductor optical filters to solve the problem of the high failure rate that are recognize bad of financial account, jam of financial account and the ATM service interruption due to failure of accurate location information among the operation of the ATM (automatic teller machine) systems. A semiconductor optical filters that have high resolution and less diffuse, high transmittance are able to detect the information of financial account surface accurately. Therefore, it is a stable filter that is able to minimize the incidence of disability. In this paper, we drew the determinants by element for implement an excellent semiconductor optical filters. Based on this, we had to be able to implement the semiconductor optical filter that is able to be mounted on the actual ATM system through future studies.

• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.1000-1007
• /
• 2003

In this paper, we propose an efficient method for locating lip. The lip shape is represented as a set of points based on Point Distribution Model. We use the Isodata clustering algorithm to find clusters for all training data. For each cluster, a lip shape model is calculated using principle component analysis. For all training data, a lip boundary model is calculated based on the pixel values around the lip boundary. To decide whether a recognition result is correct, we use a cost function based on the lip boundary model. Because of using different models according to the lip shapes, our method can localize correctly the flu far from the mean shape. The experiments have been performed for many images, and show correct recognition rate of 92%.

• Journal of Sensor Science and Technology
• /
• v.24 no.1
• /
• pp.69-77
• /
• 2015

The Microsoft Kinect is a motion sensing input device which is widely used for many motion recognition applications such as fitness, sports, and rehabilitation. Until now, most of remote rehabilitation systems with the Microsoft Kinect have allowed the user or patient to do rehabilitation or fitness by following the motion of a video screen. However in this paper we propose a smart remote rehabilitation system with the Microsoft Kinect motion sensor and a wearable ECG sensor which can allow patients to offer monitoring of the individual's performance and personalized feedback on rehabilitation exercises. The proposed noble smart remote rehabilitation is able to monitor and measure the state of the patient's condition during rehabilitation exercise, and transmits it to the prescriber. This system can give feedback to a prescriber, a doctor and a patient for improving and recovering motor performance. Thus, the efficient rehabilitation training service can be provided to patient in response to changes of patient's condition during exercise.

• Natural Product Sciences
• /
• v.19 no.1
• /
• pp.28-35
• /
• 2013

In this study, quantitative and pattern recognition analysis for the quality evaluation of Cinnamomi Ramulus and Cinnamomi Cortex using HPLC/UV was developed. For quantitative analysis, three major bioactive compounds were determined. The separation conditions employed for HPLC/UV were optimized using an ODS $C_{18}$ column ($250{\times}4.6$ mm, 5 ${\mu}m$) with gradient conditions of acetonitrile and water as the mobile phase, at a flow rate of 1.0 mL/min and a detection wavelength of 265 nm. This method was fully validated with respect to linearity, accuracy, precision, recovery, and robustness. The HPLC/UV method was applied successfully to the quantification of three major compounds in the extract of Cinnamomi Ramulus and Cinnamomi Cortex. The HPLC analytical method for pattern recognition analysis was validated by repeated analysis of thirty eight Cinnamomi Ramulus and thirty five Cinnamomi Cortex samples. The results indicate that the established HPLC/UV method is suitable for quantitative analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.288-301
• /
• 2017

In this paper, we propose an optimized algorithm for texture classification by computing a completed modeling of the local binary pattern (CLBP) instead of the traditional LBP of a scalable block size in an image. First, we show that the CLBP descriptor is a better representative than LBP by extracting more information from an image. Second, the CLBP features of scalable block size of an image has an adaptive capability in representing both gross and detailed features of an image and thus it is suitable for image texture classification. This paper successfully implements a machine learning scheme by applying the CLBP features of a scalable size to the Support Vector Machine (SVM) classifier. The proposed scheme has been evaluated on Outex and CUReT databases, and the evaluation result shows that the proposed approach achieves an improved recognition rate compared to the previous research results.