Chang-Hsing Lee

A new 3D model retrieval approach based on the elevation descriptor

The advances in 3D data acquisition techniques, graphics hardware, and 3D data modeling and visualizing techniques have led to the proliferation of 3D models. This has made the searching for specific 3D models a vital issue. Techniques for effective and efficient content-based retrieval of 3D models have therefore become an essential research topic. In this paper, a novel feature, called elevation descriptor, is proposed for 3D model retrieval. The elevation descriptor is invariant to translation and scaling of 3D models and it is robust for rotation. First, six elevations are obtained to describe the altitude information of a 3D model from six different views. Each elevation is represented by a gray-level image which is decomposed into several concentric circles. The elevation descriptor is obtained by taking the difference between the altitude sums of two successive concentric circles. An efficient similarity matching method is used to find the best match for an input model. Experimental results show that the proposed method is superior to other descriptors, including spherical harmonics, the MPEG-7 3D shape spectrum descriptor, and D2.

Automatic Music Genre Classification Based on Modulation Spectral Analysis of Spectral and Cepstral Features

In this paper, we will propose an automatic music genre classification approach based on long-term modulation spectral analysis of spectral (OSC and MPEG-7 NASE) as well as cepstral (MFCC) features. Modulation spectral analysis of every feature value will generate a corresponding modulation spectrum and all the modulation spectra can be collected to form a modulation spectrogram which exhibits the time-varying or rhythmic information of music signals. Each modulation spectrum is then decomposed into several logarithmically-spaced modulation subbands. The modulation spectral contrast (MSC) and modulation spectral valley (MSV) are then computed from each modulation subband. Effective and compact features are generated from statistical aggregations of the MSCs and MSVs of all modulation subbands. An information fusion approach which integrates both feature level fusion method and decision level combination method is employed to improve the classification accuracy. Experiments conducted on two different music datasets have shown that our proposed approach can achieve higher classification accuracy than other approaches with the same experimental setup.

An adaptive digital image watermarking technique for copyright protection

An adaptive digital image watermarking technique is proposed. The proposed method exploits the sensitivity of human eyes to adaptively embed a visually recognizable watermark in an image without affecting the perceptual quality of the underlying host image. In addition, the watermark will still be present if some lossy image processing operations such as low-pass filtering, median filtering, resampling, requantization, and lossy JPEG image compression are applied to the watermarked image. Experimental results show the effectiveness of the proposed watermarking method.

A fast motion estimation algorithm based on the block sum pyramid

In this correspondence, a fast approach to motion estimation is presented. The algorithm uses the block sum pyramid to eliminate unnecessary search positions. It first constructs the sum pyramid structure of a block. Successive elimination is then performed hierarchically from the top level to the bottom level of the pyramid. Many search positions can be skipped from being considered as the best motion vector and, thus, the search complexity can be reduced. The algorithm can achieve the same estimation accuracy as the full search block matching algorithm with much less computation time.

A fast search algorithm for vector quantization using mean pyramids of codewords

One of the most serious problems for vector quantization, especially for high dimensional vectors, is the high computational complexity of searching for the closest codeword in the codebook design and encoding phases. Although quantizing high dimensional vectors rather than low dimensional vectors results in better performance, the computation time needed for vector quantization grows exponentially with the vector dimension. This makes high dimensional vectors unsuitable for vector quantization. To overcome this problem, a fast search algorithm, under the assumption that the distortion is measured by the squared Euclidean distance, is proposed. Using the mean pyramids of codewords, the algorithm ran reject many codewords that are impossible matches and hence save a great deal of computation time. The algorithm is efficient for high dimensional codeword searches. Experimental results confirm the effectiveness of the proposed method. >

Automatic Classification of Bird Species From Their Sounds Using Two-Dimensional Cepstral Coefficients

This paper presents a method for automatic classification of birds into different species based on the audio recordings of their sounds. Each individual syllable segmented from continuous recordings is regarded as the basic recognition unit. To represent the temporal variations as well as sharp transitions within a syllable, a feature set derived from static and dynamic two-dimensional Mel-frequency cepstral coefficients are calculated for the classification of each syllable. Since a bird might generate several types of sounds with variant characteristics, a number of representative prototype vectors are used to model different syllables of identical bird species. For each bird species, a model selection method is developed to determine the optimal mode between Gaussian mixture models (GMM) and vector quantization (VQ) when the amount of training data is different for each species. In addition, a component number selection algorithm is employed to find the most appropriate number of components of GMM or the cluster number of VQ for each species. The mean vectors of GMM or the cluster centroids of VQ will form the prototype vectors of a certain bird species. In the experiments, the best classification accuracy is 84.06% for the classification of 28 bird species.

Automatic recognition of animal vocalizations using averaged MFCC and linear discriminant analysis

In this paper we propose a method that uses the averaged Mel-frequency cepstral coefficients (MFCCs) and linear discriminant analysis (LDA) to automatically identify animals from their sounds. First, each syllable corresponding to a piece of vocalization is segmented. The averaged MFCCs over all frames in a syllable are calculated as the vocalization features. Linear discriminant analysis (LDA), which finds out a transformation matrix that minimizes the within-class distance and maximizes the between-class distance, is utilized to increase the classification accuracy while to reduce the dimensionality of the feature vectors. In our experiment, the average classification accuracy is 96.8% and 98.1% for 30 kinds of frog calls and 19 kinds of cricket calls, respectively.

Scene-based event detection for baseball videos

A lot of research has lately been focusing on scene analysis in sport videos. By extracting the semantics of successive frames or segmented shots, various kinds of video scenes may be identified. However, general baseball events, e.g., strikeout and ground outs, are hard to be detected because a general baseball event is composed of a series of video scenes and each scene is further composed of several video shots. Hence, the detection of general baseball events has to be developed in terms of scenes to facilitate the retrieval of the required video clips. To do this, the baseball video is firstly segmented into many video shots. Then, various visual features including the image-based features, object-based features, and global motion are extracted to analyze the semantics for each video shot. Each video shot is then classified into the predefined semantic scenes according to its semantics. Finally, the hidden Markov model (HMM) is applied to detect the general baseball events by regarding the classified scenes as observation symbols. The accuracy analysis for the scene classification and event detection are illustrated with a large amount of video data consisting of several hours of video frames. Experimental results show that the proposed system detects the four kinds of general baseball events with reasonable accuracy.

High-speed closest codeword search algorithms for vector quantization

Abstract One of the most serious problems for vector quantization is the high computational complexity involved in searching for the closest codeword through a codebook in both codebook design and encoding phases. In this paper, based on the assumption that the distortion is measured by the squared Euclidean distance, two high-speed search methods will be proposed to speed up the search process. The first one uses the difference between the mean values of two vectors to reduce the search space. The second is to find the Karhunen-Loeve transform (KLT) for the distribution of the set of training vectors and then applies the partial distortion elimination method to the transformed vectors. Experimental results show that the proposed methods can reduce lots of mathematical operations.

Automatic Music Genre Classification using Modulation Spectral Contrast Feature

In this paper, we proposed a novel feature, called octave-based modulation spectral contrast (OMSC), for music genre classification. OMSC is extracted from long-term modulation spectrum analysis to represent the time-varying behavior of music signals. Experimental results have shown that OMSC outperforms MFCC and OSC. If OMSC is integrated with MFCC and OSC, the classification accuracy is 84.03% for seven music genre classification.