• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.436-441
• /
• 2017

Computing music similarity is indispensable in constructing music retrieval system. This paper focuses on the cover song search among various music-retrieval tasks. We investigate the cover song search method based on the chroma n-gram to reduce storage for feature DB and enhance search accuracy. Specifically we propose t-tab n-gram, n-gram selection method, and n-gram set comparison method. Experiments on the widely used music dataset confirmed that the proposed method improves cover song search accuracy as well as reduces feature storage.

• Journal of Broadcast Engineering
• /
• v.18 no.5
• /
• pp.713-721
• /
• 2013

This paper describes an efficiency of chroma based tonal features for speech emotion recognition. As the tonality caused by major or minor keys affects to the perception of musical mood, so the speech tonality affects the perception of the emotional states of spoken utterances. In order to justify this assertion with respect to tonality and emotion, subjective hearing tests are carried out by using synthesized signals generated from chroma features, and consequently show that the tonality contributes especially to the perception of the negative emotion such as anger and sad. In automatic emotion recognition tests, the modified chroma-based tonal features are shown to produce noticeable improvement of accuracy when they are supplemented to the conventional log-frequency power coefficient (LFPC)-based spectral features.

• Journal of Korea Multimedia Society
• /
• v.15 no.1
• /
• pp.18-31
• /
• 2012

This paper proposes a matching engine of query-by-singing/humming (QbSH) system which retrieves the most similar music information by comparing the input data with the extracted feature information from polyphonic music like MP3. The feature sequences transcribed from polyphonic music may have many errors. So, to reduce the influence of errors and improve the performance, the chroma-scale representation, compensation and asymmetric DTW (Dynamic Time Warping) are adopted in the matching engine. The performance of various distance metrics are also investigated in this paper. In our experiment, the proposed QbSH system achieves MRR (Mean Reciprocal Rank) of 0.718 for 1000 singing/humming queries when searching from a database of 450 polyphonic musics.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.8
• /
• pp.114-123
• /
• 1996

In this paper, we propose an automatic recognition algorithm using the object centroid of a facial image. First, we separate the facial image from the background image using the chroma-key technique and we find the centroid of the separated facial image. Second, we search nose in the facial image based on knowledge of human faces and the coordinate of the object centroid and, we calculate 17 feature parameters automatically. Finally, we recognize the facial image by using feature parameters in the neural networks which are trained through error backpropagation algorithm. It is illustrated by experiments by experiments using the proposed recogniton system that facial images can be recognized in spite of the variation of the size and the position of images.

• Journal of Broadcast Engineering
• /
• v.7 no.1
• /
• pp.2-9
• /
• 2002

Recently. VR( Virtual Reality) applications such as virtual studio and virtual character are wifely used In TV programs. and AR( Augmented Reality) applications are also belong taken an interest increasingly. This paper introduces a virtual screen system. which Is a new AR application for broadcasting. The virtual screen system is a real-time video augmentation system by tracking a chroma-patterned moving panel. We haute recently developed a virtual screen system.'K-vision'. Our system enables the user to hold and morse a simple panel on which live video, pictures of 3D graphics images can appear. All the Images seen on the panel change In the correct perspective, according to movements of the camera and the user holding the panel, in real-time. For the purpose of tracking janet. we use some computer vision techniques such as blob analysis and feature tracking. K-vision can work well with any type of camera. requiring no special add-ons. And no need for sensor attachments to the panel. no calibration procedures required. We are using K-vision in some TV programs such as election. documentary and entertainment.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.518-524
• /
• 2018

The cover song refers to live recordings or reproduced albums. This paper studies two-dimensional Fourier transform as a feature-dimension reduction method to search cover song fast. The two-dimensional Fourier transform is conducive in feature-dimension reduction for cover song search due to musical-key invariance. This paper extends the previous work, which only utilize the magnitude of the Fourier transform, by introducing an invariant from phase based on the assumption that adjacent frames have the same musical-key change. We compare the cover song retrieval accuracy of the Fourier-transform based methods over two datasets. The experimental results show that the addition of the invariant from phase improves the cover song retrieval accuracy over the previous magnitude-only method.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.13 no.4
• /
• pp.7-13
• /
• 1999

The purpose of this study was to suggest the c1ata which were useful to apply the color for clothes resign 29 female university students were se10cted in this experirrental study for the perception scope of primroy color from July to Dec. in 1998. The results of this study are as the following : 1) The perception scope of red perceived by more than 30% of the subjects was wider in Chroma-axis than in Value-axis, including 5R 4/12, 5R 4/10 and 5R 5/14 in standard color 5R standard color 5R 4/14. The perception scope of yellow was wider in Chroma-axis in standard color 5Y 8/14. And the perception scope of blue was wider in Value-axis in standard color 5B 4/10. 2) In chromaticity diagram, the perception scope of red perceived by one subjoct and over was large, covering three-quarters and being extended in X -axis. The perception scope of yellow was awuximately a half, without being linked together. A few of it were separated. And the perception scope of blue was about two-thirds, including all color chips in the line. In conclusion, the perception scope of red was comprehensively broad and there aweared relatively strong corrnron feature between the subjects. The perception scq;e of yellow was awuximate1y a half and there was little cormnon feature between the subjects. And the perception sccpe of blue was sorrewhat wide and the sUbiects expressed strong cornrmn feature. feature.

• Journal of Korea Multimedia Society
• /
• v.19 no.5
• /
• pp.826-836
• /
• 2016

Mastering a musical instrument for an unskilled beginning learner is not an easy task. It requires playing every note correctly and maintaining the tempo accurately. Any music comes in two forms, a music score and it rendition into an audio music. The proposed method of assisting beginning music players in both aspects employs two popular pattern recognition methods for audio-visual analysis; they are support vector machine (SVM) for music score recognition and hidden Markov model (HMM) for audio music performance tracking. With proper synchronization of the two results, the proposed music learning assistant system can give useful feedback to self-training beginners.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.143-146
• /
• 2006

Music is now digitally produced and distributed via internet and we face a huge amount of music day by day. A music summarization technology has been studied in order to help people concentrate on the most impressive section of the song andone can skim a song as listening the climax(chorus, refrain) only. Recent studies try to find the climax section using various methods such as finding diagonal line segment or kernel based segmentation. All these methods fail to capture the inherent structure of music due to polyphonic and noisy nature of music. In this paper, after applying moving average filter to time domain of MFCC/chroma feature, we achieved a remarkable result to capture the music structure.