• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.25-35
• /
• 1997

Most of speech analysis methods developed up to date are based on second order statistics, and one of the biggest drawback of these methods is that they show dramatical performance degradation in noisy environments. On the contrary, the methods using higher order statistics(HOS), which has the property of suppressing Gaussian noise, enable robust feature extraction in noisy environments. In this paper we propose a text-independent speaker identification system using higher order statistics and compare its performance with that using the conventional second-order-statistics-based method in both white and colored noise environments. The proposed speaker identification system is based on the vector quantization approach, and employs HOS-based voiced/unvoiced detector in order to extract feature parameters for voiced speech only, which has non-Gaussian distribution and is known to contain most of speaker-specific characteristics. Experimental results using 50 speaker's database show that higher-order-statistics-based method gives a better identificaiton performance than the conventional second-order-statistics-based method in noisy environments.

• Journal of Advanced Navigation Technology
• /
• v.15 no.2
• /
• pp.319-325
• /
• 2011

In this paper, we propose the matching model between virtual reality and the real-world for peoples with limited mobility. The proposed matching model is consist of four parts: wearable input device-based PC control, hand-motion pattern recognition, application software, and matching between virtual reality and the real-world. To recognition mouse functions and hand-motion patterns from six-axis coordinate of wearable input device, RF communication is used. In addition, to easily control the real-world, virtual reality has been implemented with realism of the real-world. Some experiments are conducted so as to verify the proposed model, and as a result, hand-motion recognition as well as virtual reality control are well performed.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.155-164
• /
• 2011

APP based on the smart phone is being utilized to various scopes such as medical services in hospitals, financing services at banks and credit card companies, and ubiquitous technologies in companies and homes etc. In this service environment, exposures of smart phones cause loss of assets including leaks of official/private information by outsiders. Though secret keys, pattern recognition technologies, and single image authentication techniques are being applied as protective methods, but they have problems in that accesses are possible by utilizing static key values or images like pictures. Therefore, this study proposes a face authentication technology for protecting smart phones from these dangerous factors and problems. The proposed technology authenticates users by extracting key frames of user's facial images by real time, and also controls accesses to the smart phone. Authentication information is composed of multiple key frames, and the user' access is controlled by distinction algorism of similarity utilizing DC values of image's pixel and luminance.

• Journal of Digital Contents Society
• /
• v.11 no.1
• /
• pp.17-24
• /
• 2010

The purpose of this study is to design and implement a kernel for the support vector machine(SVM) to improve the performance of face recognition. Local feature analysis(LFA) has been well known for its good performance. SVM kernel plays a limited role of mapping low dimensional face features to high dimensional feature space but the proposed kernel using LFA is designed for face recognition purpose. Because of the novel method that local face information is extracted from training set and combined into the kernel, this method is expected to apply to various object recognition/detection tasks. The experimental results shows its improved performance.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.777-785
• /
• 2017

In the modern real world, we can extract and recognize some texts to get a lot of information from the scene containing them, so the techniques for extracting and recognizing text areas from a scene are constantly evolving. They can be largely divided into texture-based method, connected component method, and mixture of both. Texture-based method finds and extracts text based on the fact that text and others have different values such as image color and brightness. Connected component method is determined by using the geometrical properties after making similar pixels adjacent to each pixel to the connection element. In this paper, we propose a method to adaptively change to improve the accuracy of text region extraction, detect and correct the slope of the image using edge and image segmentation. The method only extracts the exact area containing the text by correcting the slope of the image, so that the extracting rate is 15% more accurate than MSER and 10% more accurate than EEMSER.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.63-68
• /
• 2017

In this paper, Distance recognition measurement using distance calculation correction algorithm, was realization through LED dimming control. The calculation values for the RSSI average filtering and the RSSI feedback filtering were calculated and applied to reduce the error of the RSSI value measured from a long distance. It was confirmed that the RSSI values through the average filtering and the RSSI values measured by setting the coefficient value of the feedback filtering to 0.5 were ranged from -61 dBm to - 52.5 dBm, which shows irregular and high values decrease slightly as much as about -2 dBm to -6 dBm as compared to general measurements. A distance calculation correction algorithm to improve the accuracy was applied, which confirmed that as the distance increases, the range of errors decreases. In conclusion, unstable signals were corrected using the RSSI measurement result filtering, and the distance calculation correction algorithm was applied and performed to reduce the range of errors. In addition, RGB colors were implemented by LED to indicate the distance determination and the signal stability.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.213-222
• /
• 2018

This study was conducted to derive the traffic accident risk index through the recognition of the elderly driver's driving pattern to reduce the traffic accident rate of elderly drivers and to reflect them in the renewal and return policy of driver's license accordingly. First, the traffic accident risk index is defined by analyzing the behavioral characteristics of older drivers to derive the major factors that lead to traffic accidents. Second, we present a method to measure the traffic accident risk index from the driving pattern of the elderly through the smart-phone, the camera and the distance sensor attached to the car. Finally, we derive three thresholds by computer simulation and determine the accident risk from the measured traffic accident risk index as four steps and suggest ways to ensure safe driving of older drivers. It is required to objectively assess the driving ability of an aged driver in accordance with the proposed method, and to induce the driver to reset the driver's license renewal cycle and voluntarily return the driver's license to minimize social costs due to increased traffic accidents.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.1
• /
• pp.115-123
• /
• 2002

In this paper, we present two types of vision algorithm that mobile robot has CCD camera. for obstacle avoidance and path plan. One is simple algorithm that compare with grey level from input images. Also, The mobile robot depend on image processing and move command from PC host. we has been studied self controlled mobile robot system with CCD camera. This system consists of TMS320F240 digital signal processor, step motor, RF module and CCD camera. we used wireless RF module for movable command transmitting between robot and host PC. This robot go straight until 95 percent filled screen from input image. And the robot recognizes obstacle about 95 percent filled something, so it could avoid the obstacle and conclude new path plan. Another is complex algorithm that image preprocessing by edge detection, converting, thresholding and image processing by labeling, segmentation, pixel density calculation.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.159-166
• /
• 2014

In this paper, we examine the role of emotional acoustic cues including both prosody and voice quality parameters for the modification of a word sense. For the extraction of prosody parameters and voice quality parameters, we used 60 pieces of speech data spoken by six speakers with five different emotional states. We analyzed eight different emotional acoustic cues, and used a discriminant analysis technique in order to find the dominant sequence of acoustic cues. As a result, we found that anger has a close relation with intensity level and 2nd formant bandwidth range; joy has a relative relation with the position of 2nd and 3rd formant values and intensity level; sadness has a strong relation only with prosody cues such as intensity level and pitch level; and fear has a relation with pitch level and 2nd formant value with its bandwidth range. These findings can be used as the guideline for find-tuning an emotional spoken language generation system, because these distinct sequences of acoustic cues reveal the subtle characteristics of each emotional state.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.9-14
• /
• 2018

The vision system is a device for acquiring images and analyzing and discriminating inspection areas. Demand for use in the automation process has increased, and the introduction of a vision-based inspection system has emerged as a very important issue. These vision systems are used for everyday life and used as inspection equipment in production processes. Image processing technology is actively being studied. However, there is little research on the area definition for extracting objects such as character recognition or semiconductor packages. In this paper, define a region of interest and perform edge extraction to prevent the user from judging noise as an edge. We propose a noise-robust alignment correction model that can extract the edge of a region to be inspected using the distribution of edges in a specific region even if noise exists in the image. Through the proposed model, it is expected that the product production efficiency will be improved if it is applied to production field such as character recognition of tire or inspection of semiconductor packages.