• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.6B
• /
• pp.1041-1049
• /
• 2000

A face recognition algorithm for the user identification procedure of automatic teller machine(ATM), as an application of the still image processing techniques is proposed in this paper. In the proposed algorithm, face recognition techniques, especially, face region detection, eye and mouth detection schemes, which can distinguish abnormal faces from normal faces, are proposed. We define normal face, which is acceptable, as a face without sunglasses or a mask, and abnormal face, which is non-acceptable, as that wearing both, or either one of them. The proposed face recognition algorithm is composed of three stages: the face region detection stage, the preprocessing stage for facial feature detection and the eye and mouth detection stage. Experimental results show that the proposed algorithm can distinguish abnormal faces from normal faces accurately from restrictive sample images.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.6
• /
• pp.369-378
• /
• 2018

This study proposes a new approach to real time implimemtation of shape recognition technology of die casting and forging parts based on robot vision for smart factory. The proposed shape recognition and inspection technology for forging and die casting parts is very useful for manufacturing process automatiom and smart factory including external form's automatic inspection of machanical or electronic panrs for the precision verification. The reliabiblity of proposed technology Ihas been illustrated through experiments.

• Journal of Sensor Science and Technology
• /
• v.30 no.1
• /
• pp.15-19
• /
• 2021

Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.

• Phonetics and Speech Sciences
• /
• v.15 no.4
• /
• pp.101-107
• /
• 2023

This study aims to propose an automatic method of detecting vowel variation in the Korean dialects of Gyeong-sang and Jeol-la. The method is based on error patterns extracted using phone recognition. Canonical and recognized phone sequences are compared, and statistical analyses distinguish the vowels appearing in both dialects, the dialect-common vowels, and the vowels with high mismatch rates for each dialect. The dialect-common vowels show monophthongization of diphthongs. The vowels unique to the dialects are /we/ to [e] and /ʌ/ to [ɰ] for Gyeong-sang dialect, and /ɰi/ to [ɯ] in Jeol-la dialect. These results corroborate previous dialectology reports regarding phonetic realization of the Korean dialects. The current method provides a possibility of automatic explanation of the dialect patterns.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1688-1692
• /
• 2003

The automatic Landing system is used for the automatic functions of automatic transfer crane in the automated container terminal. It confirms and adjusts the alignment and pose between spreader and container and accomplishes the automatic loading/unloading job of containers in yard. Specially, it is required in the automated container terminal and is well adapted under the coarse external environments. This system used the laser sensors to recognize the alignment between spreader and container. In this paper the algorithm of recognition of the alignment and pose is presented and the result of its simulation is shown.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.37 no.1 s.109
• /
• pp.73-81
• /
• 2005

Stockigt sizing test, which is readily affected by individual tester's bias as well as testing conditions in recognizing red coloration, had to be modified to improve its reliability and reproducibility. The novel testing system with the automatic recognizing program of red coloration was developed with the auxiliary equipments including an automatic liquid dispenser and a specimen shifter. The analysis program used a hue value of a droplet image in recognizing a point of time on red coloration instead of RGB values that are not similar to human perception of color. Hue was more sensitive in recognizing the red coloration of a droplet than the other two factors, Saturation and Value. During the test, the program records the time consumed up to a specific hue value of a droplet on a specimen. Differently from the conventional test, the automatic test could obtain a reliable and reproducible sizing degree with a minor error. Furthermore, the Stockigt sizing degree measured by the automatic system showed great correlations with contact angle and Hercules sizing degree. It means that such great correlations will contribute to the development of an integrated measuring system capable of predicting contact angle, surface tension, surface energy and Hercules sizing degree of paper and paperboards through the Stbckigt sizing test. It was meaningful to note that the automatic system for Stbckigt sizing test might be able to used to predict contact angle, Hercules and Cobb sizing degree, based upon the high correlation coefficients.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.417-417
• /
• 2000

This paper proposes a face detection and recognition method that combines the template matching method and the eigenface method with the neural network. In the face extraction step, the skin color information is used. Therefore, the search region is reduced. The global property of the face is achieved by the eigenface method. Face recognition is performed by a neural network that can learn the face property.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.297-297
• /
• 2000

This paper proposed character recognition method by using DB Matching and Artificial Neural Network at the Gerber files. Gerber files are file for make PCB. But we also use the file to a program of extraction PCB position data. If the Gerber file recognized a character, the extraction PCB position data will be faster and also when the recognition rate is high, it can be possible to automatic extraction. We apply to the construction PCB Gerber file program and Simulation results are presented to verify the usefulness of the method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.35-40
• /
• 1998

This paper describes an automatic recognition method of contents in moving images. The recognition process is carried out by the following two steps. At first, camera works in moving images are analyzed and moving objects are extracted from the moving images. Next, the motion of the object is recognized by pre-procured knowledge. These techniques will be applied to a construction of an efficient image database.

• 한국ITS학회:학술대회논문집
• /
• 2008.11a
• /
• pp.284-288
• /
• 2008