• Convergence Security Journal
• /
• v.17 no.3
• /
• pp.21-29
• /
• 2017

Accurate encoding of local patterns is a very important factor in texture classification. However, LBP based methods w idely studied have fundamental problems that are vulnerable to noise. Recently, LDP method using edge response and dire ction information was proposed in facial expression recognition. LDP is more robust to noise than LBP and can accommod ate more information in it's pattern code, but it has drawbacks that it is sensitive to rotation transforms that are critical to texture classification. In this paper, we propose a new local pattern coding method called Rotation Invariant Local Direc tional Pattern, which combines rotation-invariant transform to LDP. To prove the texture classification performance of the proposed method in this paper, texture classification was performed on the widely used UIUC and CUReT datasets. As a result, the proposed RILDP method showed better performance than the existing methods.

• The Journal of the Korea Contents Association
• /
• v.5 no.5
• /
• pp.33-42
• /
• 2005

In this paper, we propose a new training algorithm for improving pattern classification performance of ART neural network. The proposed train algorithm restricts unnecessary cluster generation and transition, applies the location extraction algorithm, and operates the reset system based on the agreement between the present learning pattern and the initial pattern. As a result, repetitive input of a pattern does not generate a new cluster and mis-recognition rate decreases.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2000.06a
• /
• pp.54-61
• /
• 2000

A method and results of classification of 4 types metallic wear debris were presented by using their color features. The color image of wear debris was used (or the initial data, and the color properties of the debris were specified by HSI color model. Particle was characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used for the definition of classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• Journal of Sensor Science and Technology
• /
• v.31 no.1
• /
• pp.16-23
• /
• 2022

Cardiac disease is the most common cause of death worldwide. Therefore, detection and classification of electrocardiogram (ECG) signals are crucial to extend life expectancy. In this study, we aimed to implement an artificial intelligence signal recognition system in field programmable gate array (FPGA), which can recognize patterns of bio-signals such as ECG in edge devices that require batteries. Despite the increment in classification accuracy, deep learning models require exorbitant computational resources and power, which makes the mapping of deep neural networks slow and implementation on wearable devices challenging. To overcome these limitations, spiking neural networks (SNNs) have been applied. SNNs are biologically inspired, event-driven neural networks that compute and transfer information using discrete spikes, which require fewer operations and less complex hardware resources. Thus, they are more energy-efficient compared to other artificial neural networks algorithms.

• Proceedings of the IEEK Conference
• /
• 2003.07b
• /
• pp.703-706
• /
• 2003

Yield enhancement in semiconductor fabrication is important. It is ideal to prevent all the failures. However, when a failure occurs, it is important to quickly specify the cause stage and take countermeasure. The automatic method of failure pattern extraction from fail bit map provides reduced time to analysis and facilitates yield enhancement. This paper describes the techniques to automatically classifies a failure pattern using a fail bit map, a new simple schema which facilitates the failure analysis.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.9
• /
• pp.3243-3257
• /
• 2021

Deep neural networks provide excellent performance in pattern recognition, audio classification, and image recognition. It is important that they accurately recognize input data, particularly when they are used in autonomous vehicles or for medical services. In this study, we propose a data correction method for increasing the accuracy of an unknown classifier by modifying the input data without changing the classifier. This method modifies the input data slightly so that the unknown classifier will correctly recognize the input data. It is an ensemble method that has the characteristic of transferability to an unknown classifier by generating corrected data that are correctly recognized by several classifiers that are known in advance. We tested our method using MNIST and CIFAR-10 as experimental data. The experimental results exhibit that the accuracy of the unknown classifier is a 100% correct recognition rate owing to the data correction generated by the proposed method, which minimizes data distortion to maintain the data's recognizability by humans.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.9
• /
• pp.1682-1688
• /
• 2008

The Counterpropagation algorithm(CP) is a combination of Kohonen competition network as a hidden layer and the outstar structure of Grossberg as an output layer. CP has been used in many real applications for pattern matching, classification, data compression and statistical analysis since its learning speed is faster than other network models. However, due to the Kohonen layer's winner-takes-all strategy, it often causes instable learning and/or incorrect pattern classification when patterns are relatively diverse. Also, it is often criticized by the sensitivity of performance on the learning rate. In this paper, we propose an enhanced CP that has multiple Kohonen layers and dynamic controlling facility of learning rate using the frequency of winner neurons and the difference between input vector and the representative of winner neurons for stable learning and momentum learning for controlling weights of output links. A real world application experiment - pattern recognition from passport information - is designed for the performance evaluation of this enhanced CP and it shows that our proposed algorithm improves the conventional CP in learning and recognition performance.

• Current Optics and Photonics
• /
• v.7 no.5
• /
• pp.511-517
• /
• 2023

Pipelines play an important role in urban water supply and drainage, oil and gas transmission, etc. This paper presents a technique for pattern recognition of fiber optic vibration signals collected by a distributed vibration sensing (DVS) system using a deep learning residual network (ResNet). The optical fiber is laid on the pipeline, and the signal is collected by the DVS system and converted into a 64 × 64 single-channel grayscale image. The grayscale image is input into the ResNet to extract features, and finally the K-nearest-neighbors (KNN) algorithm is used to achieve the classification and recognition of pipeline damage.

• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• pp.571-582
• /
• 2018

Recently, development of deep learning has shown better image classification result than human. According to recent research, a hidden layer of deep learning is deeper, and a preservation of extracted features shows good results. However, in the case of general images, the extracted features are clear and easy to sort. This study aims to classify plant leaf images. This plant leaf image has high similarity in each image. Since plant leaf images have high similarity not only between images of different species but also within the same species, classification accuracy is not increased by simply extending the hidden layer or connecting the layers. Therefore, in this paper, we tried to improve the hidden layer of the algorithm called DenseNet which shows the recent excellent classification results, and compare the results of several different modified layers. The proposed method makes it possible to classify plant leaf images collected in a natural environment more easily and accurately than conventional methods. This results in good classification of plant leaf image data including unnecessary noise obtained in a natural environment.

• 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.