• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.6
• /
• pp.62-70
• /
• 2007

In this study, the natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.8-18
• /
• 1993

A multi-font, multi-size and high speed character recognition system is designed. The design principles are simpilcity of algorithm, adaptibility, learnability, hierachical data processing and attention by feed back. For the multi-size character recognition, the extracted character images are normalized. A hierachical classifier classifies the feature vectors. Feature is extracted by applying the directional receptive field after the directional dege filter processing. The hierachical classifier is consist of two pre-classifiers and one decision making classifier. The effect of two pre-classifiers is prediction to the final decision making classifier. With the pre-classifiers, the time to compute the distance of the final classifier is reduced. Recognition rate is 95% for the three documents printed in three kinds of fonts, total 1,700 characters. For high speed implemention, a multiprocessor system with the ring structure of four transputers is implemented, and the recognition speed of 30 characters per second is aquired.

• Korean Journal of Computational Design and Engineering
• /
• v.19 no.1
• /
• pp.50-60
• /
• 2014

In this paper, we propose a non-overlapping volume decomposition method that decomposes a solid model into non-overlapped volumes. The non-overlapping volume decomposition finds non-overlapped volumes from maximum volumes. After introducing the concept of the non-overlapping volume decomposition, we discuss technical issues and solutions for them. The non-overlapping volume decomposition is verified by the experiments with a prototype system. From the experiments, it was found that the non-overlapping volume decomposition shows better result than maximum volume decomposition from the view point of design feature recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.159-167
• /
• 2006

Lipreading has been suggested as one of the methods to improve the performance of speech recognition in noisy environment. However, existing methods are developed and implemented only in software. This paper suggests a hardware design for real-time lipreading. For real-time processing and feasible implementation, we decompose the lipreading system into three parts; image acquisition module, feature vector extraction module, and recognition module. Image acquisition module capture input image by using CMOS image sensor. The feature vector extraction module extracts feature vector from the input image by using parallel block matching algorithm. The parallel block matching algorithm is coded and simulated for FPGA circuit. Recognition module uses HMM based recognition algorithm. The recognition algorithm is coded and simulated by using DSP chip. The simulation results show that a real-time lipreading system can be implemented in hardware.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.1
• /
• pp.13-20
• /
• 2016

In this paper, we propose an object recognition system that can effectively find out its category, its instance name, and several attributes from the color and depth images of an object with hierarchical feature learning. In the preprocessing stage, our system transforms the depth images of the object into the surface normal vectors, which can represent the shape information of the object more precisely. In the feature learning stage, it extracts a set of patch features and image features from a pair of the color image and the surface normal vector through two-layered learning. And then the system trains a set of independent classification models with a set of labeled feature vectors and the SVM learning algorithm. Through experiments with UW RGB-D Object Dataset, we verify the performance of the proposed object recognition system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.82-89
• /
• 2015

The researches of image recognition have been processed traditionally. Especially, face recognition technology has been received attractions with advance and applied to various areas according as camera sensor embedded into many devices such as smart phone. In this study, we design and develop a feature vector generation technique of face for making animation caricatures using methods for face detection which are previous stage of face recognition. At first, we detect both face region and detailed eye region of component element by Viola&Johns's realtime detection method which are called as ROI(Region Of Interest). And then, we generate feature vectors of eye region by utilizing factors as opposed to the periphery and by using appearance information of eye. At this point, we focus on the embedded information in many color spaces to overcome the problems which can be occurred by using one color space. We propose a feature vector generation method using information from many color spaces. Finally, we experiment the test of feature vector generation by the proposed method with enough quantity of sample picture data and evaluate the proposed method for factors of estimating performance such as error rate, accuracy and generation time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.77-80
• /
• 2013

SURF algorithm is an algorithm to extract feature points and to generate descriptors from input images. It is robust to change of environment such as scale, rotation, illumination and view points. Because of these features, it is used for many image processing applications such as object recognition, constructing panorama pictures and 3D image restoration. But there is disadvantage for real time operation because many recognition algorithms such as SURF algorithm requires a lot of calculations. In this paper, we propose a design of feature extractor and descriptor generator based on SURF for high memory efficiency. The proposed design reduced a memory access and memory usage to operate in real time.

• Convergence Security Journal
• /
• v.14 no.7
• /
• pp.23-28
• /
• 2014

This study proposes the design and implementation of the system for a facial expression recognition system. LDP(Local Directional Pattern) feature computes the edge response in a different direction from a pixel with the relationship of neighbor pixels. It is necessary to be estimated that LDP code can represent facial features correctly under various conditions. In this respect, we build the system of facial expression recognition to test LDP performance quickly and the proposed evaluation system consists of six components. we experiment the recognition rate with local micro patterns (LDP, Gabor, LBP) in the proposed evaluation system.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.67-75
• /
• 1997

A design for a system to perform rapid recognition of three dimensional objects is presented, focusing on efficient indexing. In order to retrieve the best matched models without exploring all possible object matches, we have employed a bayesian framework. A decision-theoretic measure of the discriminatory power of a feature for a model object is defined in terms of posterior probability. Detectability of a featrue defined as a function of the feature itselt, viewpoint, sensor charcteristics, nd the feature detection algorithm(s) is also considered in the computation of discribminatory power. In order to speed up the indexing or selection of correct objects, we generate and verify the object hypotheses for rfeatures detected in a scene in the order of the discriminatory power of these features for model objects.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.319-327
• /
• 2012

In this paper, we present a sign language recognition model which does not use any wearable devices for object tracking. The system design issues and implementation issues such as data representation, feature extraction and pattern classification methods are discussed. The proposed data representation method for sign language patterns is robust for spatio-temporal variances of feature points. We present a feature extraction technique which can improve the computation speed by reducing the amount of feature data. A neural network model which is capable of incremental learning is described and the behaviors and learning algorithm of the model are introduced. We have defined a measure which reflects the relevance between the feature values and the pattern classes. The measure makes it possible to select more effective features without any degradation of performance. Through the experiments using six types of sign language patterns, the proposed model is evaluated empirically.