• The Journal of the Acoustical Society of Korea
• /
• 제22권4E호
• /
• pp.141-149
• /
• 2003

As music of digital form has been widely used, many people have been interested in the automatic extraction of natural information of music itself, such as key of a music, chord progression, melody progression, tempo, etc. Although some studies have been tried, consistent and reliable results of musical information extraction had not been achieved. In this paper, we propose a method to extract chord and tempo information from general polyphonic music signals. Chord can be expressed by combination of some musical notes and those notes also consist of some frequency components individually. Thus, it is necessary to analyze the frequency components included in musical signal for the extraction of chord information. In this study, we utilize a sinusoidal modeling, which uses sinusoids corresponding to frequencies of musical tones, and show reliable chord extraction results of sinusoidal modeling. We could also find that the tempo of music, which is the one of remarkable feature of music signal, interactively supports the chord extraction idea, if used together. The proposed scheme of musical feature extraction is able to be used in many application fields, such as digital music services using queries of musical features, the operation of music database, and music players mounting chord displaying function, etc.

• 한국군사과학기술학회지
• /
• 제12권4호
• /
• pp.524-531
• /
• 2009

In this paper, we propose an automatic image registration method for multi-sensor image fusion such as visible and infrared images. The registration is achieved by finding corresponding feature points in both input images. In general, the global statistical correlation is not guaranteed between multi-sensor images, which bring out difficulties on the image registration for multi-sensor images. To cope with this problem, mutual information is adopted to measure correspondence of features and to select faithful points. An update algorithm for projective transform is also proposed. Experimental results show that the proposed method provides robust and accurate registration results.

• Journal of Biosystems Engineering
• /
• 제23권6호
• /
• pp.607-614
• /
• 1998

An automatic grading algorithm was developed to replace the manual trading of white ginseng. The algorithm consists of three consecutive stages, (a) image acquisition and preprocessing, (b) mathematical feature extraction, and (c) grade decision using artificial neural network. Mathematical features such as area ratio, mean and standard deviation of graylevel, skewness of graylevel histogram, and the number of run segment are extracted from five equally divided parts of ginseng. An artificial neural network model was used to classify white ginsengs into three categories. The performance of the algorithm was evaluated using 120 ginseng samples and the rate of successful classification was 74%.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.525-528
• /
• 2009

Recently, image classification has been an important task in various fields. Generally, the performance of image classification is not good without the adjustment of image features. Therefore, it is desired that the way of automatic feature extraction. In this paper, we propose an image classification method which adjusts image features automatically. We assume that texture features are useful in image classification tasks because natural images are composed of several types of texture. Thus, the classification accuracy rate is improved by using distribution of texture features. We obtain texture features by calculating image features from a current considering pixel and its neighborhood pixels. And we calculate image features from distribution of textures feature. Those image features are adjusted to image classification tasks using Genetic Algorithm. We apply proposed method to classifying images into "head" or "non-head" and "male" or "female".

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.214-217
• /
• 2000

Many researches have been performed for human recognition and coding schemes recently. For this situation, we propose an automatic facial feature extraction algorithm. There are two main steps: the face region evaluation from original background image such as office, and the facial feature extraction from the evaluated face region. In the face evaluation, Genetic Algorithm is adopted to search face region in background easily such as office and household in the first step, and Template Matching Method is used to extract the facial feature in the second step. We can extract facial feature more fast and exact by using over the proposed Algorithm.

• ETRI Journal
• /
• 제41권6호
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권12호
• /
• pp.6038-6053
• /
• 2017

In this study, we propose an automatic melody extraction algorithm using deep learning. In this algorithm, feature images, generated using the energy of frequency band, are extracted from polyphonic audio files and a deep learning technique, a convolutional neural network (CNN), is applied on the feature images. In the training data, a short frame of polyphonic music is labeled as a musical note and a classifier based on CNN is learned in order to determine a pitch value of a short frame of audio signal. We want to build a novel structure of melody extraction, thus the proposed algorithm has a simple structure and instead of using various signal processing techniques for melody extraction, we use only a CNN to find a melody from a polyphonic audio. Despite of simple structure, the promising results are obtained in the experiments. Compared with state-of-the-art algorithms, the proposed algorithm did not give the best result, but comparable results were obtained and we believe they could be improved with the appropriate training data. In this paper, melody extraction and the proposed algorithm are introduced first, and the proposed algorithm is then further explained in detail. Finally, we present our experiment and the comparison of results follows.

• Journal of Information Processing Systems
• /
• 제14권4호
• /
• pp.824-836
• /
• 2018

The automatic extraction of temporal information from written texts is a key component of question answering and summarization systems and its efficacy in those systems is very decisive if a temporal expression (TE) is successfully extracted. In this paper, three different approaches for TE extraction in Uyghur are developed and analyzed. A novel approach which uses lexical semantics as an additional information is also presented to extend classical approaches which are mainly based on morphology and syntax. We used a manually annotated news dataset labeled with TIMEX3 tags and generated three models with different feature combinations. The experimental results show that the best run achieved 0.87 for Precision, 0.89 for Recall, and 0.88 for F1-Measure in Uyghur TE extraction. From the analysis of the results, we concluded that the application of semantic knowledge resolves ambiguity problem at shallower language analysis and significantly aids the development of more efficient Uyghur TE extraction system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.1030-1032
• /
• 1998

In this paper, an efficient feature vector extraction method and MLP neural network are utilized to automatically detect and classify power quality disturbances, where the proposed classification procedure consists of the following three parts: i.e., (i) PQ disturbance detection using discrete wavelet transform. (ii) feature vector extraction from the detected disturbance. using several methods, such as FFT, DWT, Fisher's criterion. etc.. and (iii) classification of the corresponding type of each PQ disturbance by recognizing the pattern of the extracted feature vector. To demonstrate the performance and, applicability of the proposed classification algorithm. some test results obtained by analyzing 10-class PQ disturbances are also provided.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.316-326
• /
• 2022

The prompt development in the field of video is the outbreak of online services which replaces the television media within a shorter period in gaining popularity. The online videos are encouraged more in use due to the captions displayed along with the scenes for better understandability. Not only entertainment media but other marketing companies and organizations are utilizing videos along with captions for their product promotions. The need for captions is enabled for its usage in many ways for hearing impaired and non-native people. Research is continued in an automatic display of the appropriate messages for the videos uploaded in shows, movies, educational videos, online classes, websites, etc. This paper focuses on two concerns namely the first part dealing with the machine learning method for preprocessing the videos into frames and resizing, the resized frames are classified into multiple actions after feature extraction. For the feature extraction statistical method, GLCM and Hu moments are used. The second part deals with the deep learning method where the CNN architecture is used to acquire the results. Finally both the results are compared to find the best accuracy where CNN proves to give top accuracy of 96.10% in classification.