• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.4
• /
• pp.883-889
• /
• 2005

Error backpropagation algorithm of multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the ART-1 based fuzzy supervised learning algorithm which is composed of ART-1 and fuzzy single layer supervised learning algorithm. The Proposed fuzzy supervised learning algorithm using self-generation method applied not only ART-1 to creation of nodes from the input layer to the hidden layer, but also the winer-take-all method, modifying stored patterns according to specific patterns. to adjustment of weights. We have applied the proposed learning method to the problem of recognizing a resident registration number in resident cards. Our experimental result showed that the possibility of local-minima was decreased and the teaming speed and the paralysis were improved more than the conventional error backpropagation algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.31-40
• /
• 2005

we propose an enhanced self-generation supervised algorithm that by combining an ART algorithm and the delta-bar-delta method. Form the input layer to the hidden layer, ART-1 and ART-2 are used to produce nodes, respectively. A winner-take-all method is adopted to the connection weight adaption so that a stored pattern for some pattern is updated. we test the recognition of student identification, a certificate of residence, and an identifier from container that require nodes of hidden layers in neural network. In simulation results, the proposed self-generation supervised learning algorithm reduces the possibility of local minima and improves learning speed and paralysis than conventional neural networks.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.33-39
• /
• 2021

Speech recognition technology is being combined with deep learning and is developing at a rapid pace. In particular, voice recognition services are connected to various devices such as artificial intelligence speakers, vehicle voice recognition, and smartphones, and voice recognition technology is being used in various places, not in specific areas of the industry. In this situation, research to meet high expectations for the technology is also being actively conducted. Among them, in the field of natural language processing (NLP), there is a need for research in the field of removing ambient noise or unnecessary voice signals that have a great influence on the speech recognition recognition rate. Many domestic and foreign companies are already using the latest AI technology for such research. Among them, research using a convolutional neural network algorithm (CNN) is being actively conducted. The purpose of this study is to determine the non-voice section from the user's speech section through the convolutional neural network. It collects the voice files (wav) of 5 speakers to generate learning data, and utilizes the convolutional neural network to determine the speech section and the non-voice section. A classification model for discriminating speech sections was created. Afterwards, an experiment was conducted to detect the non-speech section through the generated model, and as a result, an accuracy of 94% was obtained.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.35D no.10
• /
• pp.107-115
• /
• 1998

A multiplier bit-pair recoding technique derived from Booth algorithm is used as an effective method that can carry out a fast binary multiplication regardless of a sign of both multiplicand and multiplier. In this paper, we propose an implementation of an optical high-speed multiplier which consists of a symbolic substitution adder and an optical multiplication algorithm, which transforms and enhances the multiplier bit-pair recoding algorithm to be fit for optical characteristics. Specially, a symbolic substitution addition rules are coded with a dual-rail logic, and so the complement of the logic of the symbolic substitution adder is easily obtained with a shift operation because it is always present. We also construct the symbolic substitution system which makes superposition image by superimposing two shifted images in a serial connection and recognizes a reference image by feeding this superimposed image to a mask. Thus, the optical multiplier, which is compared with a typical system, is implemented to the smaller system by reducing the number of optical passive elements and the size of this system.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.1-10
• /
• 2019

Object-based image matching algorithms have been widely used in the image processing and computer vision fields. A variety of applications based on image matching algorithms have been recently developed for object recognition, 3D modeling, video tracking, and biomedical informatics. One prominent example of image matching features is the Scale Invariant Feature Transform (SIFT) scheme. However many applications using the SIFT algorithm have implemented based on stand-alone basis, not client-server architecture. In this paper, We initially implemented based on client-server structure by using SIFT algorithms to identify and match objects in biomedical images to provide useful information to the user based on the recently released Mobile platform. The major methodological contribution of this work is leveraging the convenient user interface and ubiquitous Internet connection on Mobile device for interactive delineation, segmentation, representation, matching and retrieval of biomedical images. With these technologies, our paper showcased examples of performing reliable image matching from different views of an object in the applications of semantic image search for biomedical informatics.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.1
• /
• pp.59-67
• /
• 2008

In this paper we propose an algorithm to extract the license plate regions from Korean car images. The idea of this paper is that we first find the four digits in the input car image and then segment the plate region using the digit information. Out method has advantage of segmenting simultaneously the plate regions and four digits regions. The first step finds and groups the connected components with proper sizes as candidate digits. The second step applies an serial alignment condition to find out probable 4-digits. In the third step, we recognize the candidate digits and assign the confidence values to each of them. The final step extracts the license plate region which has the highest confidence value. We used the Perfect Metrics classification algorithm to estimate the confidence. In our experiment, we got 97.23% and 95.45% correct detection rates, 0.09% and 0.11% false detection rates for 4,600 daytime and 264 nighttime images, respectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.195-201
• /
• 2014

In this study, face recognition system was designed based on polynomial Radial Basis Function Neural Networks(pRBFNNs) pattern classifier using 2-directional 2-dimensional principal component analysis algorithm. Existing one dimensional PCA leads to the reduction of dimension of image expressed by the multiplication of rows and columns. However $(2D)^2PCA$(2-Directional 2-Dimensional Principal Components Analysis) is conducted to reduce dimension to each row and column of image. and then the proposed intelligent pattern classifier evaluates performance using reduced images. The proposed pRBFNNs consist of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with the aid of fuzzy c-means clustering. In the conclusion part of rules. the connection weight of RBFNNs is represented as the linear type of polynomial. The essential design parameters (including the number of inputs and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. Using Yale and AT&T dataset widely used in face recognition, the recognition rate is obtained and evaluated. Additionally IC&CI Lab dataset is experimented with for performance evaluation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.56-63
• /
• 2016

In this study, we introduce a design of Fuzzy RBFNNs-based digit recognition system using the incremental-PCA in order to recognize the handwritten digits. The Principal Component Analysis (PCA) is a widely-adopted dimensional reduction algorithm, but it needs high computing overhead for feature extraction in case of using high dimensional images or a large amount of training data. To alleviate such problem, the incremental-PCA is proposed for the computationally efficient processing as well as the incremental learning of high dimensional data in the feature extraction stage. The architecture of Fuzzy Radial Basis Function Neural Networks (RBFNN) consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means (FCM) algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, connection weights are used as the extended diverse types in polynomial expression such as constant, linear, quadratic and modified quadratic. Experimental results conducted on the benchmarking MNIST handwritten digit database demonstrate the effectiveness and efficiency of the proposed digit recognition system when compared with other studies.

• Journal of KIISE:Software and Applications
• /
• v.27 no.6
• /
• pp.583-594
• /
• 2000

The thinning process which is commonly used in extracting skeletons from handwritten Hangul characters has a problem of distorting the original pattern shapes. This paper proposes a method of skeleton extraction using a shape decomposition algorithm. We decompose the character pattern into a set of near convex parts using a shape decomposition algorithm. From the shape-decomposed pattern, we detect the joint parts and extract the skeletons from the parts incident to the joint parts. Then the skeletons not incident to the joint parts are extracted. Finally, the process of skeleton extension is performed to ensure the connectivity. We setup five criteria for the comparison of quality of skeletons extracted by our method and the thinning based method. The comparison shows the superiority of our method in terms of several criteria.

• Journal of the Institute of Convergence Signal Processing
• /
• v.16 no.1
• /
• pp.22-28
• /
• 2015

In this paper, a service system which shows linked video clips from the static images extracted from newspapers, magazines, photo albums and etc in an augmented reality. First, the system uses SURF algorithm to extract features from the original photos printed in the media and stores them with the linked video clips. Next, when a photo is taken by using a camera from mobile devices such as smart phones, the system extracts features in real time, search a linked video clip matching the original image, and shows it on the smart phone in an augmented reality. The proposed system is applied to Android smart phone devices and the test results verify that the proposed system operates not only on normal photos but also on partially damaged photos.