• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.49-59
• /
• 2009

Contents-based image retrieval methods are in general more objective and effective than text-based image retrieval algorithms since they use color and texture in search and avoid annotating all images for search. SIM(Self-organizing Image browsing Map) is one of contents-based image retrieval algorithms that uses only browsable mapping results obtained by SOM(Self Organizing Map). However, SOM may have an error in selecting the right BMU in learning phase if there are similar nodes with distorted color information due to the intensity of light or objects' movements in the image. Such images may be mapped into other grouping nodes thus the search rate could be decreased by this effect. In this paper, we propose an improved SIM that uses HSV color model in extracting image features with color quantization. In order to avoid unexpected learning error mentioned above, our SOM consists of two layers. In learning phase, SOM layer 1 has the color feature vectors as input. After learning SOM Layer 1, the connection weights of this layer become the input of SOM Layer 2 and re-learning occurs. With this multi-layered SOM learning, we can avoid mapping errors among similar nodes of different color information. In search, we put the query image vector into SOM layer 2 and select nodes of SOM layer 1 that connects with chosen BMU of SOM layer 2. In experiment, we verified that the proposed SIM was better than the original SIM and avoid mapping error effectively.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.514-528
• /
• 2004

An emotion-based video scene retrieval algorithm is proposed in this paper. First, abrupt/gradual shot boundaries are detected in the video clip representing a specific story Then, five video features such as 'average color histogram' 'average brightness', 'average edge histogram', 'average shot duration', and 'gradual change rate' are extracted from each of the videos and mapping between these features and the emotional space that user has in mind is achieved by an interactive genetic algorithm. Once the proposed algorithm has selected videos that contain the corresponding emotion from initial population of videos, feature vectors from the selected videos are regarded as chromosomes and a genetic crossover is applied over them. Next, new chromosomes after crossover and feature vectors in the database videos are compared based on the similarity function to obtain the most similar videos as solutions of the next generation. By iterating above procedures, new population of videos that user has in mind are retrieved. In order to show the validity of the proposed method, six example categories such as 'action', 'excitement', 'suspense', 'quietness', 'relaxation', 'happiness' are used as emotions for experiments. Over 300 commercial videos, retrieval results show 70% effectiveness in average.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.146-149
• /
• 2014

최근 자동차 산업과 IT 기술의 융합이 활발해지면서 스마트카, 자율주행 자동차(무인 자동차)와 같은 지능형 자동차 개발이 활발히 진행되고 지능형 자동차의 비전 기반 기술개발도 활발히 진행되고 있다. 고속도로와 같이 포장된 도로나 자갈길과 같은 비포장 도로에서도 운전자의 승차감을 고려한 능동적 안전시스템과 안정적인 자율주행 자동차의 주행능력을 보장하는 기술들 중 도로 유형을 판단하는 것이 중요 요소 중 하나이다. 따라서 본 논문에서는 가중치 기반 클러스터링 기술을 이용하여 도로표면 유형을 분류하는 알고리즘을 제안한다. 아스팔트, 자갈길, 흙길, 눈길의 도로표면 영상 데이터를 히스토그램의 분포도와 최고점 위치, 에지 영상의 에지량, 채도성분을 이용하여 특징값을 추출하고 클러스터를 구성한다. 분류할 입력 도로표면 영상에 대해 특징값을 분석한 후 탐색범위 내 선택된 각 클러스터의 벡터와의 거리를 측정하여 가중치를 계산하고 가중치가 높은 클러스터를 분류하여 입력 영상에 대한 도로표면을 결정한다. 실험결과 제안하는 방법이 각 도로표면 영상의 특징값과 이를 이용한 가중치만을 이용하여 약 91.25%의 정확도로 도로의 표면을 분류해 내는 것을 볼 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.706-714
• /
• 2012

The Korea Meteorological Administration provided the recent four-years records of weather dataset for our very short-term heavy rainfall prediction. We divided the dataset into three parts: train, validation and test set. Through feature selection, we select only important features among 72 features to avoid significant increase of solution space that arises when growing exponentially with the dimensionality. We used a differential evolution algorithm and two classifiers as the fitness function of evolutionary computation to select more accurate feature subset. One of the classifiers is Support Vector Machine (SVM) that shows high performance, and the other is k-Nearest Neighbor (k-NN) that is fast in general. The test results of SVM were more prominent than those of k-NN in our experiments. Also we processed the weather data using undersampling and normalization techniques. The test results of our differential evolution algorithm performed about five times better than those using all features and about 1.36 times better than those using a genetic algorithm, which is the best known. Running times when using a genetic algorithm were about twenty times longer than those when using a differential evolution algorithm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.4
• /
• pp.363-371
• /
• 2010

In an effort to enhance the quality of feature vector classification and thereby reduce the recognition error rate for the speaker-independent speech recognition, we study the effect of spectral tilt on the Fourier magnitude spectrum en route to the extraction of MFCC. The effect of FIR filtering on the speech signal on the speech recognition is also investigated in parallel. Evaluation of the proposed methods are performed by two independent ways of the Fisher discriminant objective function and speech recognition test by hidden Markov model with fuzzy vector quantization. From the experiments, the recognition error rate is found to show about 10% relative improvements over the conventional method by an appropriate choice of the tilt factor.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.5
• /
• pp.111-117
• /
• 2008

In this paper, we propose an approach to improve the performance of voiced/unvoiced (V/UV) decision under background noise environments for the selectable mode vocoder (SMV) of 3GPP2. We first present an effective analysis of the features and the classification method adopted in the SMV. And then feature vectors which are applied to the GMM are selected from relevant parameters of the SMV for the efficient voiced/unvoiced classification. For the purpose of evaluating the performance of the proposed algorithm, different experiments were carried out under various noise environments and yields better results compared with the conventional scheme of the SMV.

• Journal of Korea Society of Industrial Information Systems
• /
• v.18 no.4
• /
• pp.25-35
• /
• 2013

This paper focuses on building a generalized mood classification model with many mood classes instead of a personalized one with few mood classes. Two methods are adopted to improve the performance of mood classification. The one of them is feature reduction based on standard deviation of feature values, which is designed to solve the problem of lowered performance when all 391 features provided by MIR toolbox used to extract features of music. The experiments show that the feature reduction methods suggested in this paper have better performance than that of the conventional dimension reduction methods, R-Square and PCA. As performance improvement by feature reduction only is subject to limit, modular neural network is used as another method to improve the performance. The experiments show that the method also improves performance effectively.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.5
• /
• pp.183-191
• /
• 2010

Unique and invariant biometric characteristics have been used for secure user authentication. Storing original biometric data is not acceptable due to privacy and security concerns of biometric technology. In order to enhance the security of the biometric data, the cancelable biometrics was introduced. Using revocable and non-invertible transformation, the cancelable biometrics can provide a way of more secure biometric authentication. In this paper, we present a new cancelable bits extraction method for the facial data. For the feature extraction, the Subpattern-based Principle Component Analysis (PCA) is adopted. The Subpattern-based PCA divides a whole image into a set of partitioned subpatterns and extracts principle components from each subpattern area. The feature extracted by using Subpattern-based PCA is discretized with a helper data based method. The elements of the obtained bits are evaluated and ordered according to a measure based on the fisher criterion. Finally, the most discriminative bits are chosen as the biometric bits string and used for authentication of each identity. Even if the generated bits string is compromised, new bits string can be generated simply by changing the helper data. Because, the helper data utilizes partial information of the feature, the proposed method does not reveal privacy sensitive biometric information of the user. For a security evaluation of the proposed method, a scenario in which the helper is compromised by an adversary is also considered.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.3
• /
• pp.323-329
• /
• 2002

This paper proposes a frame reliability weighting method to compensate for a time-selective noise that occurs at random positions of speech signal contaminating certain parts of the speech signal. Speech frames have different degrees of reliability and the reliability is proportional to SNR (signal-to noise ratio). While it is feasible to estimate frame Sl? by using the noise information from non-speech interval under a stationary noisy situation, it is difficult to obtain noise spectrum for a time-selective noise. Therefore, we used statistical models of clean speech for the estimation of the frame reliability. The proposed MFR (model-based frame reliability) approximates frame SNR values using filterbank energy vectors that are obtained by the inverse transformation of input MFCC (mal-frequency cepstral coefficient) vectors and mean vectors of a reference model. Experiments on various burnt noises revealed that the proposed method could represent the frame reliability effectively. We could improve the recognition performance by using MFR values as weighting factors at the likelihood calculation step.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.142-147
• /
• 2008

In this paper, we propose a novel a roach to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the support vector machine (SVM). The SVM makes it possible to build on an optimal hyperplane that is separated without the error where the distance between the closest vectors and the hyperplane is maximal. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then feature vectors which are a lied to the SVM are selected from relevant parameters of the SMV for the efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.