Browsing by Author "Lee, Chang-Hsing"

Now showing 1 - 6 of 6

An interactive flower image recognition system
(2011-05-01)
Hsu, Tzu-Hsiang
;
Lee, Chang-Hsing
;
Chen, Ling-Hwei
;
多媒體工程研究所
;
Institute of Multimedia Engineering
In this paper, we present an interactive system for recognizing flower images taken by digital cameras. The proposed system provides an interactive interface allowing each user to draw an appropriate bounding window that contains the interested flower region. Then, a flower boundary tracing method is developed to extract the flower region as accurately as possible. In addition to the color and shape features of the whole flower region, the color and shape features of the pistil/stamen area will also be used to represent the flower characteristics more precisely. Experiments conducted on two distinct databases consisting of 24 species and 102 species have shown that our proposed system outperforms other approaches in terms of the recognition rate.
Illumination Robust Face Recognition Using Spatial Expansion Local Histogram Equalization and Locally Linear Regression Classification
(2018-01-01)
Chang, Pei-Chun
;
Chen, Yong-Sheng
;
Lee, Chang-Hsing
;
Lien, Cheng-Chang
;
Han, Chin-Chuan
Robust face recognition under illumination variations is a critical problem in a face recognition system, particularly for face recognition in the wild. In this paper, a face image preprocessing approach, called spatial expansion local histogram equalization (SELHE), is proposed to enhance face images due to illumination variations. First, a face image is divided into several non-overlapped blocks. Then, local histogram equalization with spatial expansion is proposed to enhance the contrast of each local image block. Local linear regression classification will then be used to recognize the enhanced image blocks. Experiments performed on the Yale B and Yale B extended databases have shown that the proposed approach yields promising recognition accuracy.
Image Contrast Enhancement Using Classified Virtual Exposure Image Fusion
(2012-11-01)
Lee, Chang-Hsing
;
Chen, Ling-Hwei
;
Wang, Wei-Kang
;
資訊工程學系
;
Department of Computer Science
In our daily life, digital cameras and smart phones have been widely used to take pictures. However, digital cameras and smart phones have a limited dynamic range, which is much lower than that human eyes can perceive. Thus, the photographs taken in high dynamic range scenes often exhibit under-exposure or over-exposure artifacts in shadow or highlight regions. In this study, an image fusion based approach, called classified virtual exposure image fusion (CVEIF), is proposed for image enhancement. First, a function imitating the F-stop concept in photography is designed to generate several virtual images having different intensity. Then, a classified image fusion method, which blends pixels in distinct luminance classes using different fusion functions, is proposed to produce a fused image in which every image region is well exposed. Experimental results on four different kinds of generic images, including a normal image, a low-contrast images, a backlight image, and a dark scene image, have shown that the proposed CVEIF approach produced more pleasingly enhanced images than other methods(1).
Image enhancement approach using the just-noticeable-difference model of the human visual system
(2012-07-01)
Lee, Chang-Hsing
;
Lin, Pei-Ying
;
Chen, Ling-Hwei
;
Wang, Wei-Kang
;
多媒體工程研究所
The low-contrast images taken by digital cameras or camera phones are not always satisfactory due to the limitation of the capturing devices or improper illumination/exposure conditions. Conventional image contrast enhancement methods may either fail to produce satisfactory and undistorted images, or they cannot improve every region of interest appropriately, especially faces. In this paper, a histogram equalization (HE) approach exploiting the just-noticeable-difference (JND) model of the human visual system (HVS), denoted by JND-HE, is proposed for generic image contrast enhancement. Further, the proposed JND-HE approach is combined with the exposure correction (EC) method (denoted by JND-HE-EC) for face image enhancement. The proposed JND-HE-EC approach can improve the contrast in face regions and provide proper illumination in the background. Experimental results on both generic images and faces have shown that our proposed approach can produce more pleasing and appealing enhanced images than other methods. (C) 2012 SPIE and IS&T. [DOI: 10.1117/1.JEI.21.3.033007]
Local Wavelet Acoustic Pattern: A Novel Time-Frequency Descriptor for Birdsong Recognition
(2018-12-01)
Hsu, Sheng-Bin
;
Lee, Chang-Hsing
;
Chang, Pei-Chun
;
Han, Chin-Chuan
;
Fan, Kuo-Chin
Investigating the identity, distribution, and evolution of bird species is important for both biodiversity assessment and environmental conservation. The discrete wavelet transform (DWT) has been widely exploited to extract time-frequency features for acoustic signal analysis. Traditional approaches usually compute statistical measures (e.g., maximum, mean, standard deviation) of the DWT coefficients in each subband independently to yield the feature descriptor, without considering the intersubband correlation. A new acoustic descriptor, called the local wavelet acoustic pattern (LWAP), is proposed to characterize the correlation of the DWT coefficients in different subbands for birdsong recognition. First, we divide a variable-length birdsong segment into a number of fixed-duration texture windows. For each texture window, several LWAP descriptors are extracted. The vector of locally aggregated descriptors (VLAD) is then used to aggregate the set of LWAP descriptors into a single VLAD vector. Finally, principal component analysis (PCA) plus linear discriminant analysis (LDA) are employed to reduce the feature dimensionality for classification purposes. Experiments on two birdsong datasets show that the proposed LWAP descriptor outperforms other local descriptors, including linear predictive coding cepstral coefficients, Mel-frequency cepstral coefficients, perceptual linear prediction cepstral coefficients, chroma features, and prosody features. Furthermore, the proposed LWAP descriptor, followed by VLAD encoding, PCA plus LDA feature extraction, and a simple distance-based classifier, yields promising results that are competitive with those obtained by the state-of-the-art convolutional neural networks.
Music Classification Using the Bag of Words Model of Modulation Spectral Features
(2015)
Lee, Chang-Hsing
;
Lin, Hwai-San
;
Chen, Ling-Hwei
;
資訊工程學系
;
Department of Computer Science
In this paper, the bag of words (BoW) representation of modulation spectral analysis of spectral as well as cepstral features will be constructed for music genre classification. First, the modulation spectrum of each spectral and cepstral feature will be obtained through modulation spectral analysis of a longer texture window. Then, the BoW model of the modulation spectral features will be constructed and used for music classification. Experiments conducted on the music database employed in the ISMIR2004 Audio Description Contest have shown that the proposed BoW representation of modulation spectral features can achieve promising classification accuracy, particularly when it is combined with the BoW representation of frame features.