• Journal of the Korean Society of Industry Convergence
• /
• v.8 no.4
• /
• pp.221-226
• /
• 2005

This paper presents a hybrid method for recognizing the faces by using zero mean and principal component analysis. Zero mean is applied to reduce the 1st order statistics to data nonlinearities. PCA is also used to derive an orthonormal basis which directly leads to dimensionality reduction, and possibly to feature extraction of face image. The proposed method has been applied to the problems for recognizing the 20 face images(10 persons * 2 scenes) of 324*243 pixels from Yale face database. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed method has a superior recognition performances(speed, rate). The negative angle has been relatively achieved more an accurate similarity than city-block or Euclidean.

• Journal of the Korea Computer Industry Society
• /
• v.8 no.3
• /
• pp.155-166
• /
• 2007

In this paper, captured face-image was pre-processing, segmentation, and extracting features from thinning by differential operator and minute-delineation. A straight line in slope-intercept form was transformed at the $r-\theta$ domain using Hough Transform, instead of Housdorff distance are extract feature as length, rotation, displacement of lines from thinning line components by differentiation. This research proposed a new approach compare with Hough Transformation and Housdorff Distance for face recognition so that Hough transform is simple and fast processing of face recognition than processing by Housdorff Distance. Rcognition accuracy rate is that Housdorff method is higher than Hough transformation's method.

• MALSORI
• /
• no.46
• /
• pp.65-76
• /
• 2003

In this paper, we employ the adaptive comb filtering for effective noise reduction in mobile communication environment. Adaptive comb filtering is a well-known method for noise reduction, but requires correct pitch period and must be applied just in voiced speech frames. To satisfy these requirements we use two kinds of information extracted from speech packets, one of which is the pitch period information measured precisely by a speech coder and the other is the frame rate information related to a decision on speech or silence frame. Experiments on speech recognition system confirm the efficiency of this method. Feature parameters employing this method give superior performance in noise environment to those extracted directly from output speech.

• MALSORI
• /
• no.65
• /
• pp.105-124
• /
• 2008

This paper presents the effects of different phone-like-unit (PLU) sets in order to propose an optimal PLU set for the performance improvement of Korean automatic speech recognition (ASR) systems. The examination of 9 currently used PLU sets indicates that most of them include a selection of allophones without any sufficient phonetic base. In this paper, a total of 34 PLU sets are designed based on Korean phonetic characteristics arid the effects of each PLU set are evaluated through experiments. The results show that the accuracy rate of each phone is influenced by different phonetic constraint(s) which determine(s) the PLU sets, and that an optimal PLU set can be anticipated through the phonetic analysis of the given speech data.

• Journal of Biosystems Engineering
• /
• v.26 no.3
• /
• pp.253-262
• /
• 2001

This study was conducted to develop the vision system of a robotic transplanter for plug-seedling. A color image processing algorithm was developed to identify and locate empty cells and bad plants in the seedling tray. The image of pepper and tomato seedling tray was segmented into regions of plants, frame and soil using threshold technique which utilized Q of YIQ for finding leaves and H of HSI for finding frame of tray in the color coordinate system. The recognition system was able to successfully identify empty cells and bad seeding and locate their two-dimensional locations. The overall success rate of the recognition system was about 99%.

• MALSORI
• /
• no.56
• /
• pp.173-183
• /
• 2005

We propose a speech emotion recognition method for affective human-robot interface. In the Proposed method, emotion is classified into 6 classes: Angry, bored, happy, neutral, sad and surprised. Features for an input utterance are extracted from statistics of phonetic and prosodic information. Phonetic information includes log energy, shimmer, formant frequencies, and Teager energy; Prosodic information includes Pitch, jitter, duration, and rate of speech. Finally a pattern classifier based on Gaussian support vector machines decides the emotion class of the utterance. We record speech commands and dialogs uttered at 2m away from microphones in 5 different directions. Experimental results show that the proposed method yields $48\%$ classification accuracy while human classifiers give $71\%$ accuracy.

• MALSORI
• /
• no.44
• /
• pp.83-92
• /
• 2002

Speech recognition performance is severly degraded under noisy envrionments. One approach to cope with this problem is audio-visual speech recognition. In this paper, we discuss the experiment results of bimodal speech recongition based on enhanced speech feature vectors using lip information. We try various kinds of speech features as like linear predicion coefficient, cepstrum, log area ratio and etc for transforming lip information into speech parameters. The experimental results show that the cepstrum parameter is the best feature in the point of reconition rate. Also, we present the desirable weighting values of audio and visual informations depending on signal-to-noiso ratio.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.1
• /
• pp.81-87
• /
• 1989

This paper discribes the method associated with modeling of Korean phonemes. Hidden Markov models(HMM's) may be viewed as an effective technique for modeling the inherent nonstationarity of speech signal. We propose a 3-state phoneme model to represent the sequentially changing characteristics of phonemes, i.e., transition-to-stationary-to-transition. Also we clarify that the duration of a phoneme is an important factor to have an effect in recognition accuracy and show that improvement in recognition rate can be obtained by using duration-dependent 3-state hidden Markov models.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.8
• /
• pp.3971-3975
• /
• 2013

This paper introduces an Augmented Reality system recognizing hand gestures and shows results of the evaluation. The system's user can interact with artificial objects and manipulate their position and motions simply by his hand gestures. Hand gesture recognition is based on Histograms of Oriented Gradients (HOG). Salient features of human hand appearance are detected by HOG blocks. Blocks of different sizes are tested to define the most suitable configuration. To select the most informative blocks for classification multiclass AdaBoostSVM algorithm is applied. Evaluated recognition rate of the algorithm is 94.0%.

• The Journal of the Korea Contents Association
• /
• v.4 no.1
• /
• pp.24-31
• /
• 2004

This paper embodies the rating recognition system of broadcast program which can automatically acknowledge the broadcast pictures indicating the harmfulness rating, so prevent children from watching TV. This experiment was progressed as the course of extracting featured patterns (standard number patterns) and the proper patterns owned only by the concerned numbers from the numbers of standard font used by broadcasters, and comparing these patterns with input pictures and arranging them. The recognition rate of x-rating was remarkably high as a result of this experiment.