• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.4
• /
• pp.459-466
• /
• 2014

This paper deals with the method to classify the aircraft target by analyzing its JEM signal. We propose the method to classify the engine model by analyzing JEM spectrum using the harmonic frequency mask generated from the blade information of jet engine. The proposed method does not need the complicated logic algorithm to find the chopping frequency in each rotor stage and the pre-simulated engine spectrum DB used in the previous methods. In addition, we propose the method to estimate the precise spool rate and it reduces the error in estimating the number of blades or in calculating the harmonic frequency of frequency mask.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.45-50
• /
• 2003

Recently, robots technique has been developed remarkably. Emotion recognition is necessary to make an intimate robot. This paper shows the simulator and simulation result which recognize or classify emotions by learning pitch pattern. Also, because the pitch is not sufficient for recognizing emotion, we added acoustic elements. For that reason, we analyze the relation between emotion and acoustic elements. The simulator is composed of the DRNN(Dynamic Recurrent Neural Network), Feature extraction. DRNN is a learning algorithm for pitch pattern.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.535-542
• /
• 2013

In this paper, we proposed a advanced hardware engine architecture for high speed and high detection rate image recognitions. We adopted the HOG-LBP feature extraction algorithm and more parallelized architecture in order to achieve higher detection rate and high throughput. As a simulation result, the designed engine which can search about 90 frames per second detects 97.7% of pedestrians when false positive per window is $10^{-4}$.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.2
• /
• pp.111-119
• /
• 2013

Face recognition has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous applications, such as access control, surveillance, security, credit-card verification, and criminal identification. In this paper, we propose a simple descriptor called an ECSP(Extended Center-Symmetric Pattern) for illumination-robust face recognition. The ECSP operator encodes the texture information of a local face region by emphasizing diagonal components of a previous CS-LBP(Center-Symmetric Local Binary Pattern). Here, the diagonal components are emphasized because facial textures along the diagonal direction contain much more information than those of other directions. The facial texture information of the ECSP operator is then used as the input image of an image covariance-based feature extraction algorithm such as 2D-PCA(Two-Dimensional Principal Component Analysis). Performance evaluation of the proposed approach was carried out using various binary pattern operators and recognition algorithms on the Yale B database. The experimental results demonstrated that the proposed approach achieved better recognition accuracy than other approaches, and we confirmed that the proposed approach is effective against illumination variation.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.67-77
• /
• 2008

In this paper, we implemented a robust speech recognizer using the TMS320VC33 DSP. For this implementation, we had built speech and noise database suitable for the recognizer using spectral subtraction method for noise removal. The recognizer has an explicit structure in aspect that a speech signal is enhanced through spectral subtraction before endpoints detection and feature extraction. This helps make the operation of the recognizer clear and build HMM models which give minimum model-mismatch. Since the recognizer was developed for the purpose of controlling car facilities and voice dialing, it has two recognition engines, speaker independent one for controlling car facilities and speaker dependent one for voice dialing. We adopted a conventional DTW algorithm for the latter and a continuous HMM for the former. Though various off-line recognition test, we made a selection of optimal conditions of several recognition parameters for a resource-limited embedded recognizer, which led to HMM models of the three mixtures per state. The car noise added speech database is enhanced using spectral subtraction before HMM parameter estimation for reducing model-mismatch caused by nonlinear distortion from spectral subtraction. The hardware module developed includes a microcontroller for host interface which processes the protocol between the DSP and a host.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1E
• /
• pp.89-95
• /
• 1994

This paper describes development of a real-time voice dialing system which can recognize around one hundred word vocabularies in speaker independent mode. The voice recognition algorithm in this system is implemented on a DSP board with a telephone interface plugged in an IBM PC AT/486. In the DSP board, procedures for feature extraction, vector quantization(VQ), and end-point detection are performed simultaneously in every 10 msec frame interval to satisfy real-time constraints after detecting the word starting point. In addition, we optimize the VQ codebook size and the end-point detection procedure to reduce recognition time and memory requirement. The demonstration system has been displayed in MOBILAB of the Korean Mobile Telecom at the Taejon EXPO'93.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.492-497
• /
• 2008

최근 모바일 장치의 사용 영역 확대와 더불어 기기장치 내의 다양한 영상 데이터에 대한 효율적인 관리와 검색에 관한 기술 연구가 요구되고 있다. 그러나 모바일 장치의 낮은 CPU성능과 한정적인 메모리를 극복하기 위해 저 용량 그리고 고속의 검색 엔진 개발이 요구된다. 이 문제를 해결하기 위하여, 본 논문에서는 RGB 색상 공간에서 HSV 색상 공간 상의 36개의 특징 값으로 변환하는 검색 테이블 방법을 제안한다. 제안하는 방법에 의해, 입력 영상은 검색 테이블에 기반하여 빠르게 색상과 위치에 대한 두개의 특징 히스토그램으로 변환된다. 여기서, 특징추출에 필요한 연산은 본 논문의 실험 결과에서 보는 바와 같이 매우 낮다. 제안하는 방법을 이용하여, 우리는 영상, 색상 그리고 블랍에 의한 질의가 가능한 모바일 기반 영상 검색 시스템을 구현하였다. 본 논문에서 제시하는 실험결과는 제안하는 방법이 충분히 모바일에서 운용 가능한 가볍고 빠른 방법임을 알 수 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.164-166
• /
• 2012

In this paper, we proposed a method for extracting predominant melody of polyphonic music based on harmonic structure. Harmonic structure is an important feature parameter of monophonic signal that has spectral peaks at the integer multiples of its fundamental frequency. We extract all fundamental frequency candidates contained in the polyphonic signal by verifying the required condition of harmonic structure. Then, we combine those harmonic peaks corresponding to each extracted fundamental frequency and assign a rank to each after calculating its harmonic average energy. We run pitch tracking based on the rank of extracted fundamental frequency and continuity of fundamental frequency, and determine the predominant melody. For the query by singing/humming (QbSH) task, we proposed Dynamic Time Warping (DTW) based matching engine. Our system reduces false alarm by combining the distances of multiple DTW processes. To improve the performance, we introduced the asymmetric sense, pitch level compensation, and distance intransitiveness to DTW algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3090-3102
• /
• 2015

The accuracy of an augmented reality (AR) application is highly dependent on the resolution of the object's image and the device's computational processing capability. Naturally, a mobile smart device equipped with a high-resolution camera becomes the best platform for portable AR services. AR applications require significant energy consumption and very fast response time, which are big burdens to the smart device. However, there are very few ways to overcome these burdens. Computation offloading via mobile cloud computing has the potential to provide energy savings and enhance the performance of applications executed on smart devices. Therefore, in this paper, adaptive mobile computation offloading of mobile AR applications is considered in order to determine optimal offloading points that satisfy the required quality of experience (QoE) while consuming minimum energy of the smart device. AR feature extraction based on SURF algorithm is partitioned into sub-stages in order to determine the optimal AR cloud computational offloading point based on conditions of the smart device, wireless and wired networks, and AR service cloud servers. Tradeoffs in energy savings and processing time are explored also taking network congestion and server load conditions into account.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.51-60
• /
• 2020

Optical character recognition (OCR) has been studied for decades because it is very useful in a variety of places. Nowadays, OCR's performance has improved significantly due to outstanding deep learning technology. Thus, there is an increasing demand for commercial-grade but affordable OCR systems. We have developed a low-cost, high-performance OCR system for the industry with the cheapest embedded developer kit that supports GPU acceleration. To achieve high accuracy for industrial use on limited computing resources, we chose a state-of-the-art text recognition algorithm that uses an end-to-end deep learning network as a baseline model. The model was then improved by replacing the feature extraction network with the best one suited to our conditions. Among the various candidate networks, EfficientNet-B3 has shown the best performance: excellent recognition accuracy with relatively low memory consumption. Besides, we have optimized the model written in TensorFlow's Python API using TensorFlow-TensorRT integration and TensorFlow's C++ API, respectively.