• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1181-1185
• /
• 1991

Unlike printed character, the recognition of Hand written one has various kinds of difficulties due to the existence of the huge pattern associated with the person who writes. Therefore, in general, recognition of Hand written characters requires an algorithm which takes into consideration of the individual differences. Hangul characters are basically made of straight lines and circles. They can be represented in terms of feature parameters such as the end point of the straight line, the length and the angle. Then all Hangul characters can be represented by the number of basic segments(-, /, vertical bar, O) multiplied by the feature parameters respectively. In this study we propose a method for recognizing Hand written Hangul characters in terms of fuzzy inference.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.545-549
• /
• 1992

In general, recognition of Hand written characters requires to apply an algorithm which takes into consideration of the individual differences. Considering the differences, the authors propose a new method for recognizing Hand written Hangul by parallel procedure analyzing both the segments and the structure of the character. In the previous recognition method proposed by the authors two severe restrictions were placed. The element representing consonant/O/ was closed, and the character elements were separated each other. In order to remove these two restrictions, the authors propose an improved algorithm. It is shown that Hangul in its simplified form is well recognized by using this improved algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.2
• /
• pp.95-100
• /
• 2010

This paper proposes a new spatial regularization of Fisher linear discriminant analysis (LDA) to reduce the overfitting due to small size sample (SSS) problem in face recognition. Many regularized LDAs have been proposed to alleviate the overfitting by regularizing an estimate of the within-class scatter matrix. Spatial regularization methods have been suggested that make the discriminant vectors spatially smooth, leading to mitigation of the overfitting. As a generalized version of the spatially regularized LDA, the proposed regularized LDA utilizes the non-uniformity of spatial correlation structures in face images in adding a spatial smoothness constraint into an LDA framework. The region-dependent spatial regularization is advantageous for capturing the non-flat spatial correlation structure within face image as well as obtaining a spatially smooth projection of LDA. Experimental results on public face databases such as ORL and CMU PIE show that the proposed regularized LDA performs well especially when the number of training images per individual is quite small, compared with other regularized LDAs.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.2
• /
• pp.35-41
• /
• 2018

The analysis of plankton species distribution in sea or fresh water is very important in preserving marine ecosystem health. Since manual analysis is infeasible, many automatic approaches were proposed. They usually use images from in situ towed underwater imaging sensor or specially designed, lab mounted microscopic imaging system. Normally they assume that only single plankton is present in an image so that, if there is a clumping among multiple plankton of same species (homogeneous clumping) or if there are multiple plankton of different species scattered in an image (heterogeneous interspersion), they have a difficulty in recognition. In this work, we propose a deep learning based method that can detect and recognize individual plankton in images with homogeneous clumping, heterogeneous interspersion, or combination of both.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.12
• /
• pp.2138-2144
• /
• 2016

People with visual disabilities suffer environmentally, socially, and technologically. Navigating through places and recognizing objects are already a big challenge for them who require assistance. This study aimed to develop an android-based assistive application for the visually impaired. Specifically, the study aimed to create a system that could aid visually impaired individuals performs significant tasks through object recognition and identifying locations through GPS and Google Maps. In this study, the researchers used an android phone allowing a visually impaired individual to go from one place to another with the aid of the application. Google Maps is integrated to utilize GPS in identifying locations and giving distance directions and the system has a cloud server used for storing pinned locations. Furthermore, Haar-like features were used in object recognition.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.1
• /
• pp.28-32
• /
• 2006

Because of the recent development of radio frequency identification (RFID) technologies, various systems for RFID have been proposed. and it expected to become pervasive and ubiquitous. offers tantalizing benefits for supply chain management, inventory control, and many other applications. recently, however, has the convergence of lower cost and increased capabilities made businesses take a hard look at what RFID can do fer them. In this paper, We propose the real-time RFID face recognition system using Hippocampus neuron modeling algorithm(HNMA) and PCA-LDA mixture algorithm. this system store an extracted face-feature in tag and uses for individual authentication.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.455-457
• /
• 2019

In this paper we study the effect of decomposed spatiotemporal convolutions for action recognition in videos. Our motivation emerges from the empirical observation that spatial convolution applied on solo frames of the video provide good performance in action recognition. In this research we empirically show the accuracy of factorized convolution on individual frames of video for action classification. We take 3D ResNet-18 as base line model for our experiment, factorize its 3D convolution to 2D (Spatial) and 1D (Temporal) convolution. We train the model from scratch using Kinetics video dataset. We then fine-tune the model on UCF-101 dataset and evaluate the performance. Our results show good accuracy similar to that of the state of the art algorithms on Kinetics and UCF-101 datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1639-1658
• /
• 2019

Named entity recognition (NER) is an important technique for improving the performance of data mining and big data analytics. In previous studies, NER systems have been employed to identify named-entities using statistical methods based on prior information or linguistic features; however, such methods are limited in that they are unable to recognize unregistered or unlearned objects. In this paper, a method is proposed to extract objects, such as technologies, theories, or person names, by analyzing the collocation relationship between certain words that simultaneously appear around specific words in the abstracts of academic journals. The method is executed as follows. First, the data is preprocessed using data cleaning and sentence detection to separate the text into single sentences. Then, part-of-speech (POS) tagging is applied to the individual sentences. After this, the appearance and collocation information of the other POS tags is analyzed, excluding the entity candidates, such as nouns. Finally, an entity recognition model is created based on analyzing and classifying the information in the sentences.

• The Journal of the Korea Contents Association
• /
• v.4 no.4
• /
• pp.65-70
• /
• 2004

In this paper, I propose a new extraction method of Individual Pitch Pulse in order to accommodate the changes in each pitch interval and reduce pitch errors in Speech Coding. The extraction rate of individual pitch pulses was $96\%$ for male voice and $85\%$ for female voice respectively. This method has the capability of being applied to many fields, such as speech coding, speech analysis, speech synthesis and speech recognition.

• Journal of Korea Multimedia Society
• /
• v.18 no.1
• /
• pp.1-8
• /
• 2015

In recent years, ear has emerged as a new biometric trait, because it has advantage of higher user acceptance than fingerprint and can be captured at remote distance in an indoor or outdoor environment. This paper proposes an individual identification method using ear region based on SIFT(shift invariant feature transform). Unlike most of the previous studies using rectangle shape for extracting a region of interest(ROI), this study sets an ROI as a flexible expanded region including ear. It also presents an effective extraction and matching method for SIFT keypoints. Experiments for evaluating the performance of the proposed method were performed on IITD public database. It showed correct identification rate of 98.89%, and it showed 98.44% with a deformed dataset of 20% occlusion. These results show that the proposed method is effective in ear recognition and robust to occlusion.