• The Journal of the Korea Contents Association
• /
• v.16 no.9
• /
• pp.694-701
• /
• 2016

The smart phone application to provide auto identification and answer explanation of multiple choice answer for each OMR answer item in the test paper different from ordinary OMR test by using smart phone is very useful in terms of a self learning and a smart learning. In this paper, smart phone application of OMR mark identification for each question item in test paper is proposed. QR code for each OMR answer is provided for the encrypted correct answer and the reference location of multiple choice answer rectangle location. The OMR answer region is extracted and the marked answer is identified in each question of test paper, in order to compare between the marking answer and the correct answer. Experimental result of smart phone application of the proposed algorithm for the OMR answer images with various size and direction shows excellent recognition performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.2
• /
• pp.231-236
• /
• 2011

The binarization algorithm frequently applies to one part of the preprocessing phase for a variety of image processing techniques such as image recognition and image analysis, etc. So it is important that binarization algorithm is determined by the selection of threshold value for binarization in image processing. The previous algorithms could get the proper threshold value in the case that shows all the difference of brightness between background and object, but if not, they could not get the proper threshold value. In this paper, we propose the efficient fuzzy binarization method which first, segments the brightness range of gray_scale images to 2 intervals to perform car license plate binarization and applies fuzzy member function to each intervals. The experiment for performance evaluation of the proposed binarization algorithm showed that the proposed algorithm generates the more effective threshold value than the previous algorithms in car license plate.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.201-207
• /
• 2012

A RAM-based neural network is a weightless neural network based on binary neural network(BNN) which is efficient neural network with a one-shot learning. RAM-based neural network has multiful information bits and store counts of training in BNN. Supervised learning based on the RAM-based neural network has the excellent performance in pattern recognition but in pattern categorization with unsupervised learning as unsuitable. In this paper, we propose a unsupervised learning algorithm in the RAM-based neural network to perform pattern categorization. By the proposed unsupervised learning algorithm, RAM-based neural network create categories depending on the input pattern by itself. Therefore, RAM-based neural network for supervised learning and unsupervised learning should proof of all possible complex models. The training data for experiments provided by the MNIST offline handwritten digits which is consist of 0 to 9 multi-pattern.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.65-71
• /
• 2004

We improved the MLLR speaker adaptation algorithm with reduction of the order of HMM parameters using PCA(Principle Component Analysis) or ICA(Independent Component Analysis). To find a smaller set of variables with less redundancy, we adapt PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible, minimize the correlations between data elements, and remove the axis with less covariance or higher-order statistical independencies. Ordinary MLLR algorithm needs more than 30 seconds adaptation data to represent higher word recognition rate of SD(Speaker Dependent) models than of SI(Speaker Independent) models, whereas proposed algorithm needs just more than 10 seconds adaptation data. 10 components for ICA and PCA represent similar performance with 36 components for ordinary MLLR framework. So, compared with ordinary MLLR algorithm, the amount of total computation requested in speaker adaptation is reduced by about 1/167 in proposed MLLR algorithm.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.2
• /
• pp.260-267
• /
• 2011

This paper proposes a method for segmenting objects from the background in IR(Infrared) images based on GrabCut algorithm. The GrabCut algorithm needs the window encompassing the interesting known object. This procedure is processed by user. However, to apply it for object recognition problems in image sequences. the location of window should be determined automatically. For this, we adopted the Otsu' algorithm for segmenting the interesting but unknown objects in an image coarsely. After applying the Otsu' algorithm, the window is located automatically by blob analysis. The GrabCut algorithm needs the probability distributions of both the candidate object region and the background region surrounding closely the object for estimating the Gaussian mixture models(GMMs) of the object and the background. The probability distribution of the background is computed from the background window, which has the same number of pixels within the candidate object region. Experiments for various IR images show that the proposed method is proper to segment out the interesting object in IR image sequences. To evaluate performance of proposed segmentation method, we compare other segmentation methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.5
• /
• pp.22-28
• /
• 2008

This paper aims to offer a solution based on semantic document classification to improve e-Government utilization and efficiency for people using their own information retrieval system and linguistic expression. Generally, semantic document classification method is an approach that classifies documents based on the diverse relationships between keywords in a document without fully describing hierarchial concepts between keywords. Our approach considers the deep meanings within the context of the document and radically enhances the information retrieval performance. Concept Weight Document Classification(CoWDC) method, which goes beyond using existing keyword and simple thesaurus/ontology methods by fully considering the concept hierarchy of various concepts is proposed, experimented, and evaluated. With the recognition that in order to verify the superiority of the semantic retrieval technology through test results of the CoWDC and efficiently integrate it into the e-Government, creation of a thesaurus, management of the operating system, expansion of the knowledge base and improvements in search service and accuracy at the national level were needed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10C
• /
• pp.992-1000
• /
• 2009

Available electric wave resources have been limited than frequency demands that increase with the development of radio communication. According to FCC's (Federal Communication Commission) report, 70% of allocated spectrum was unused. This means that the lack phenomenon of electronic wave resources is ineffectively managed compare with the finiteness of frequency resources. According to the recognition of unused frequency within allocated band, this progress has been investigating to identify the unused TV channel and provide radio communication services. This paper proposed the sensing algorithm that efficiently recognizes the frequency resources which does not use and shares with the licensed user through using the multi-band CIC (Cascaded Integrator Comb) filter based on polyphase filter bank. The simulation results verifies that the proposed scheme can obtain the similar performance of variance and relatively low complexity to the existing scheme.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.199-207
• /
• 2013

Spin images representing efficiently surface features of 3D mesh models have been used to detect facial landmark points. However, at a certain point, different normal direction can lead to quite different spin images. Moreover, since 3D points are projected to the 2D (${\alpha}-{\beta}$) space during spin image generation, surface features cannot be described clearly. In this paper, we present a method to detect 3D facial landmark using improved spin images by partitioning the search area with respect to angle. By generating sub-spin images for angular partitioned 3D spaces, more unique features describing corresponding surfaces can be obtained, and improve the performance of landmark detection. In order to generate spin images robust to inaccurate surface normal direction, we utilize on averaging surface normal with its neighboring normal vectors. The experimental results show that the proposed method increases the accuracy in landmark detection by about 34% over a conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.9
• /
• pp.1718-1724
• /
• 2017

Recently, Smart plugs for real time monitoring of household appliances based on IoT(Internet of Things) have been activated. Through this, consumers are able to save energy by monitoring real-time energy consumption at all times, and reduce power consumption through alarm function based on consumer setting. In this paper, we measure the alternating current from a wall power outlet for real-time monitoring. At this time, the current pattern for each household appliance was classified and it was experimented with deep learning to determine which product works. As a result, we used a cross validation method and a bootstrap verification method in order to the classification performance according to the type of appliances. Also, it is confirmed that the cost function and the learning success rate are the same as the train data and test data.