• Journal of Korea Multimedia Society
• /
• v.4 no.4
• /
• pp.333-338
• /
• 2001

In this paper, fuzzy-ARTMAP equalizer is developed mainly for overcoming the obstacles, such as complexity and long training, in implementing the previously developed neural-basis equalizers. The proposed fuzzy-ARTMAP equalizer is fast and easy to train and includes capabilities not found in other neural network approaches a small number of parameters, no requirements for the choice of initial weights, no risk of getting trapped in local minima, and capability of adding new data without retraining previously trained data. In simulation studies, binary signals were generated at random from linear channel with Gaussian noise. The performance of the proposed equalizer is compared with other neural net basis equalizers, such as MLP and RBF equalizers. The fuzzy ARTMAP equalizer combines relatively simple structure and fast processing speed; it gives accurate results for nonlinear problems that cannot be solved with a linear equalizer.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.134-142
• /
• 2006

In this paper, we investigate a Hausdorff distance, which is used for the measurement of image similarity, to see whether it is also effective for document retrieval. The proposed method uses a local crowdedness and a Hausdorff distance to locate text images by determining whether a pair of images scanned at different time comes from the same text or not. To reduce the processing time, which is one of the disadvantages of a Hausdorff distance algorithm, we adopt a local crowdedness for feature point extraction. We apply the proposed method to 190 pairs of the same class and 190 pairs of the different class collected from postal envelop images. The results show that the modified Hausdorff distance proposed in this paper performed well in locating the tort region and calculating the degree of similarity between two images. An improvement of accuracy by 2.7% and 9.0% has been obtained, compared to a binary correlation method and the original Hausdorff distance method, respectively.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.1-10
• /
• 2018

This paper presents an autonomous detection and aiming point computation of a battle tank by using RGB images. Maximally stable extremal regions algorithm was implemented to find features of the tank, which are matched with images extracted from streaming video to figure out the region of interest where the tank is present. The median filter was applied to remove noises in the region of interest and decrease camouflage effects of the tank. For the tank segmentation, k-mean clustering was used to autonomously distinguish the tank from its background. Also, both erosion and dilation algorithms of morphology techniques were applied to extract the tank shape without noises and generate the binary image with 1 for the tank and 0 for the background. After that, Sobel's edge detection was used to measure the outline of the tank by which the aiming point at the center of the tank was calculated. For performance measurement, accuracy, precision, recall, and F-measure were analyzed by confusion matrix, resulting in 91.6%, 90.4%, 85.8%, and 88.1%, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.333-342
• /
• 2005

This paper proposes a method, which recognizes student's identification card by using image processing and recognition technology and can manage student information on the web. The presented scheme sets up an average brightness as a threshold, based on the brightest Pixel and the least bright one for the source image of the ID card. It is converting to binary image, applies a horizontal histogram, and extracts student number through its location. And, it removes the noise of the student number region by the mode smoothing with 3$\times$3 mask. After removing noise from the student number region, each number is extracted using vertical histogram and normalized. Using the enhanced ART1 algorithm recognized the extracted student number region. In this study, we propose the enhanced ART1 algorithm different from the conventional ART1 algorithm by the dynamical establishment of the vigilance parameter. which shows a tolerance limit of unbalance between voluntary and stored patterns for clustering. The Experiment results showed that the recognition rate of the proposed ART1 algorithm was improved much more than that of the conventional ART1 algorithm. So, we develop an educational matters administration system by using the proposed recognition method of the student's identification card.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.61-71
• /
• 2004

Recently, various techniques for face detection are studied, but most of them still have problems on processing in real-time. Therefore, in this paper, we propose novel techniques for real-time detection of human faces in sequential images using motion and chroma information. First, background model is used to find a moving area. In this procmoving area. edure, intensity values for reference images are averaged, then skin-color are detected in We use HCr color-space model and adaptive threshold method for detection. Second, binary image labeling is applied to acquire candidate regions for faces. Candidates for mouth and eyes on a face are obtained using differences between green(G) and blue(B), intensity(I) and chroma-red(Cr) value. We also considered distances between eye points and mouth on a face. Experimental results show effectiveness of real-time detection for human faces in sequential images.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.547-552
• /
• 2006

There have been various cohesion measurements studied considering reference relation among attributes and methods in a class. Generally, these cohesion measurement are camed out in one class. If the range of reference relation considered are extended from one class to two classes, we could find out the reference relation between two classes. Tn this paper, we proposed a neural network to determine the method location. Neural network is effective to predict output value from input data not to be included in training and generalize after training input and output pattern repeatedly. Learning vector is generated with 30-dimensional input vector and one target binary values of method location in a constraint that there are two classes which have less than or equal to 5 attributes and methods The result of the proposed neural network is about 95% in cross-validation and 88% in testing.

• Journal of The Korean Astronomical Society
• /
• v.52 no.6
• /
• pp.217-225
• /
• 2019

We apply a modified Convolutional Neural Network (CNN) model in conjunction with transfer learning to predict whether an active region (AR) would produce a ≥C-class or ≥M-class flare within the next 24 hours. We collect line-of-sight magnetogram samples of ARs provided by the SHARP from May 2010 to September 2018, which is a new data product from the HMI onboard the SDO. Based on these AR samples, we adopt the approach of shuffle-and-split cross-validation (CV) to build a database that includes 10 separate data sets. Each of the 10 data sets is segregated by NOAA AR number into a training and a testing data set. After training, validating, and testing our model, we compare the results with previous studies using predictive performance metrics, with a focus on the true skill statistic (TSS). The main results from this study are summarized as follows. First, to the best of our knowledge, this is the first time that the CNN model with transfer learning is used in solar physics to make binary class predictions for both ≥C-class and ≥M-class flares, without manually engineered features extracted from the observational data. Second, our model achieves relatively high scores of TSS = 0.640±0.075 and TSS = 0.526±0.052 for ≥M-class prediction and ≥C-class prediction, respectively, which is comparable to that of previous models. Third, our model also obtains quite good scores in five other metrics for both ≥C-class and ≥M-class flare prediction. Our results demonstrate that our modified CNN model with transfer learning is an effective method for flare forecasting with reasonable prediction performance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.73-79
• /
• 2014

In this paper, we proposed the mechanism which can measure traffic flow and vehicle speed on the highway as well as road by using the video and image processing to detect and track cars in a video sequence. The proposed mechanism uses the first few frames of the video stream to estimate the background image. The visual tracking system is a simple algorithm based on the sum of absolute frame difference. It subtracts the background from each video frame to produce foreground images. By thresholding and performing morphological closing on each foreground image, the proposed mechanism produces binary feature images, which are shown in the threshold window. By measuring the distance between the "first white line" mark and the "second white line"mark proceeding, it is possible to find the car's position. Average velocity is defined as the change in position of an object divided by the time over which the change takes place. The results of proposed mechanism agree well with the measured data, and view the results in real time.

• Journal of Korea Multimedia Society
• /
• v.9 no.11
• /
• pp.1435-1444
• /
• 2006

We present an effective and real-time face detection method based on Principal Component Analysis(PCA) and Support Vector Machines(SVMs). We extract simple Haar-like features from training images that consist of face and non-face images, reinterpret the features with PCA, and select useful ones from the large number of extracted features. With the selected features, we construct a face detector using an SVM appropriate for binary classification. The face detector is not affected by the size of a training data set in a significant way, so that it showed 90.1 % detection rates with a small quantity of training data. it can process 8 frames per second for $320{\times}240$ pixel images. This is an acceptable processing time for a real-time system.