• 대한공간정보학회지
• /
• 제12권2호
• /
• pp.53-59
• /
• 2004

본 연구에서는 고해상도 위성영상의 분류에 적합한 형상 기반 분류 소프트웨어를 개발하기 위한 연구를 수행하였다. 형상 기반 분류에 필요한 영상분할과 퍼지 기반의 분류 알고리즘을 개발하고, 형상 기반 분류에 요구되는 다양한 요소들을 고려하여 사용자와의 원활한 상호작용을 지원하기 위한 사용자 인터페이스를 구현하였다. 개발된 소프트웨어의 성능을 평가하고자 본 연구에서 개발된 소프트웨어와 현재 전 세계적으로 널리 보급되고 있는 형상 기반 분류 관련 상용 소프트웨어인 eCognition을 적용하여 동일한 영상을 시험적으로 처리해 본 결과 유사한 영상 분류결과를 얻을 수 있었다. 영상분할의 경우에는 본 연구에서 개발한 소프트웨어의 처리속도가 우수하였다. 형상 기반 분류를 수행하는 데에는 프로그램과 사용자간의 고도의 상호작용이 요구되므로, 향후에 이를 편리하게 하기 위한 사용자 인터페이스의 보완이 필요하다는 것을 알 수 있었다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권3호
• /
• pp.186-191
• /
• 2015

Hand gesture is the most common tool used to interact with and control various electronic devices. In this paper, we propose a novel hand gesture recognition method using fuzzy logic based classification with a new type of sensor array. In some cases, feature patterns of hand gesture signals cannot be uniquely distinguished and recognized when people perform the same gesture in different ways. Moreover, differences in the hand shape and skeletal articulation of the arm influence to the process. Manifold features were extracted, and efficient features, which make gestures distinguishable, were selected. However, there exist similar feature patterns across different hand gestures, and fuzzy logic is applied to classify them. Fuzzy rules are defined based on the many feature patterns of the input signal. An adaptive neural fuzzy inference system was used to generate fuzzy rules automatically for classifying hand gestures using low number of feature patterns as input. In addition, emotion expression was conducted after the hand gesture recognition for resultant human-robot interaction. Our proposed method was tested with many hand gesture datasets and validated with different evaluation metrics. Experimental results show that our method detects more hand gestures as compared to the other existing methods with robust hand gesture recognition and corresponding emotion expressions, in real time.

• 음성과학
• /
• 제11권1호
• /
• pp.7-20
• /
• 2004

In this paper, we propose a two-step noise compensation algorithm in feature extraction for achieving robust speech recognition. The proposed method frees us from requiring a priori information on noisy environments and is simple to implement. First, in frequency domain, the Harmonics-based Spectral Subtraction (HSS) is applied so that it reduces the additive background noise and makes the shape of harmonics in speech spectrum more pronounced. We then apply a judiciously weighted variance Feature Vector Normalization (FVN) to compensate for both the channel distortion and additive noise. The weighted variance FVN compensates for the variance mismatch in both the speech and the non-speech regions respectively. Representative performance evaluation using Aurora 2 database shows that the proposed method yields 27.18% relative improvement in accuracy under a multi-noise training task and 57.94% relative improvement under a clean training task.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.504-509
• /
• 2008

Support Vector Machine (SVM) is one of powerful learning machine and has been applied to varying task with generally acceptable performance. The success of SVM for classification tasks in one domain is affected by features which represent the instance of specific class. Given the representative and discriminative features, SVM learning will give good generalization and consequently we can obtain good classifier. In this paper, we will assess the problem of feature choices for human detection tasks and measure the performance of each feature. Here we will consider HOG-family feature. As a natural extension of SVM, we combine SVM with Principal Component Analysis (PCA) to reduce dimension of features while retaining most of discriminative feature vectors.

• 말소리와 음성과학
• /
• 제5권1호
• /
• pp.11-16
• /
• 2013

This paper proposes robust feature extraction for accurate voice activity detection (VAD). VAD is one of the principal modules for speech signal processing such as speech codec, speech enhancement, and speech recognition. Noisy environments contain nonstationary noises causing the accuracy of the VAD to drastically decline because the fluctuation of features in the noise intervals results in increased false alarm rates. In this paper, in order to improve the VAD performance, harmonic-weighted energy is proposed. This feature extraction method focuses on voiced speech intervals and weighted harmonic-to-noise ratios to determine the amount of the harmonicity to frame energy. For performance evaluation, the receiver operating characteristic curves and equal error rate are measured.

• Journal of the Korean Data and Information Science Society
• /
• 제18권2호
• /
• pp.315-326
• /
• 2007

The rapid proliferation of wireless networks and mobile computing applications has changed the landscape of network security. Anomaly detection is a pattern recognition task whose goal is to report the occurrence of abnormal or unknown behavior in a given system being monitored. This paper presents a dynamic anomaly detection scheme that can effectively identify a group of especially harmful internal masqueraders in cellular mobile networks. Our scheme uses the trace data of wireless application layer by a user as feature value. Based on the feature values, the use pattern of a mobile's user can be captured by rough sets, and the abnormal behavior of the mobile can be also detected effectively by applying a roughness membership function with both the age of the user profile and weighted feature values. The performance of our scheme is evaluated by a simulation. Simulation results demonstrate that the anomalies are well detected by the proposed dynamic scheme that considers the age of user profiles.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2355-2358
• /
• 2003

The purpose of this paper is to investigate two major feature extraction techniques based on generic modular face recognition system. Detailed algorithms are described for principal component analysis (PCA) and independent component analysis (ICA). PCA and ICA ate statistical techniques for feature extraction and their incorporation into a face recognition system requires numerous design decisions. We explicitly state the design decisions by introducing a modular-based face recognition system since some of these decision are not documented in the literature. We explored different implementations of each module, and evaluate the statistical feature extraction algorithms based on the FERET performance evaluation protocol (the de facto standard method for evaluating face recognition algorithms). In this paper, we perform two experiments. In the first experiment, we report performance results on the FERET database based on PCA. In the second experiment, we examine performance variations based on ICA feature extraction algorithm. The experimental results are reported using four different categories of image sets including front, lighting, and duplicate images.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.72-81
• /
• 2022

Visual Object Tracking is known as the most fundamental problem in the field of computer vision. Object tracking localize the region of target object with bounding box in the video. In this paper, a custom CNN is created to extract object feature that has strong and various information. This network was constructed as a Siamese network for use as a feature extractor. The input images are passed convolution block composed of a bottleneck layers, and features are emphasized. The feature map of the target object and the search area, extracted from the Siamese network, was input as a local proposal network. Estimate the object area using the feature map. The performance of the tracking algorithm was evaluated using the OTB2013 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.611 in Success Plot and 0.831 in Precision Plot were achieved.

• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1671-1679
• /
• 2004

This study has proposed visual-feature extraction methods for each band in wavelet domain with both spatial frequency features and multi resolution features. In addition, it has brought forward similarity measurement method using fuzzy theory and new color feature expression method taking advantage of the frequency of the same color after color quantization for reducing quantization error, a disadvantage of the existing color histogram intersection method. Experiments are performed on a database containing 1,000 color images. The proposed method gives better performance than the conventional method in both objective and subjective performance evaluation.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.169-171
• /
• 2020

CNN의 중간 단계에서 추출되는 feature를 인코딩했을 때 결과 성능평가에 미치는 영향을 알아보는 실험을 수행하였다. 물체검출(Object detection)과 물체영역분할(Object segmentation)에 대하여 성능평가를 하였으며, 비교를 위해 원본 이미지와 256채널의 feature들을 한 장으로 합친 이미지 두 가지에 대해 인코딩하여 성능 평가를 실시하는 실험을 하여 결과를 도출했다. 실험 결과, 인코딩 시 압축 정도를 약하게 했을 경우 성능이 거의 떨어지지 않거나 심지어는 더 높은 경우도 있다. 하지만 256채널의 feature들에 대하여 인코딩을 하기 때문에 이미지의 용량과 해상도가 높아지는 단점이 있다.