Tang Xiaoou

No Thumbnail Available
Last Name
Tang
First Name
Xiaoou
ORCID

Filters

1993 - 1997 3
2 1
3
Reset filters

Settings

Search Results

Now showing 1 - 3 of 3
  • Technical Report
    A preliminary study of shallow-water sonar issues : signal motion loss and reverberation noise
    (Woods Hole Oceanographic Institution, 1993-09) Stewart, W. Kenneth ; Chu, Dezhang ; Tang, Xiaoou
    This preliminary investigation addresses key program elements for sonar sensing in a shallow-water environment to establish bounds on possible solutions and to reduce program uncertainty. The modeling and experimental program focuses on two issues - the potential degradation of sonar data due to signal masking by shallow-water reverberation and signal loss caused by extreme platform motions. The research program combines theoretical analysis, experimental validation in a shallow-water environment, and development of a computer model to explore parametric sensitivity. Results from an initial dock-side test show good agreement with the theoretical predictions. From the shallow-water experiments and acoustic modeling we conclude that: (1) Signal motion loss can influence the reverberation level significantly but is not the dominant factor in target detection for sonars in the frequency range of interest (>200 kHz); a high-quality (velocity-aided) inertial navigation and attitude system will be sufficient to correct for geometric distortions caused by platform motion. (2) Although surface reverberation and multipath noise can be a factor, partcularly in shadow-mode imaging, reverberation levels are rapidly attenuated at the frequencies of interest and beam patterns can be manipulated to reject most interferences; echo-mode imaging is still dominated by the contrast between target strength and bottom reverberation.
  • Technical Report
    Dominant run-length method for image classification
    (Woods Hole Oceanographic Institution, 1997-06) Tang, Xiaoou
    In this paper, we develop a new run-length texture feature extraction algorithm that significantly improves image classification accuracy over traditional techniques. By directly using part or all of the run-length matrix as a feature vector, much of the texture information is preserved. This approach is made possible by the introduction of a new multi-level dominant eigenvector estimation algorithm. It reduces the computational complexity of the Karhunen-Loeve Transform by several orders of magnitude. Combined with the Bhattacharya distance measure, they form an efficient feature selection algorithm. The advantage of this approach is demonstrated experimentally by the classification of two independent texture data sets. Perfect classification is achieved on the first data set of eight Brodatz textures. The 97% classification accuracy on the second data set of sixteen Vistex images further confirms the effectiveness of the algorithm. Based on the observation that most texture information is contained in the first few columns of the run-length matrix, especially in the first column, we develop a new fast, parallel run-length matrix computation scheme. Comparisons with the co-occurrence and wavelet methods demonstrate that the run-length matrices contain great discriminatory information and that a method of extracting such information is of paramount importance to successful classification.
  • Thesis
    Transform texture classification
    (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1996-05) Tang, Xiaoou
    This thesis addresses the three major components of a texture classification system: texture image transform, feature extraction/selection, and classification. A unique theoretical investigation of texture analysis, drawing on an extensive survey of existing approaches, defines the interrelations among 11 types of texture analysis methods. A novel unification of the different methods defines a framework of transformation and representation in which three major classes of transform matrices capture texture information of increasing coherence length or correlation distance: the spatial domain method (co-occurrence method), the micro-structural method (run-length method), and the frequency multi-channel method (Fourier spectrum method). A more concise vector representation of a selected transform matrix is then needed for input to a classifier. Unlike traditional methods, which use various special functions to describe the properties of each transform matrix, a new approach directly applies a principle component analysis technique to the transform matrix. The Karhunen-Loeve Transfonn (KLT) extracts a vector of dominant features, optimally preserving texture information in the matrix. This approach is made possible by the introduction of a novel Multi-level Dominant Eigenvector Estimation (MDEE) algorithm, which reduces the computational complexity of the standard KLT by several orders of magnitude. The statistical Bhattacharyya distance measure is then used to rank dominant features according to their discrimination power. Experimental results of applying the new algorithm to the three transform matrix classes show a strong increase in performance by texture analysis methods traditionally considered to be least efficient For example, the power spectrum and run-length methods now rank among the best. Using the same MDEE algorithm, the three extracted feature vectors are then combined into a more complete description of texture images. The same approach is also used for a study of object recognition, where the combined vector also include granulometric; object-boundary, and moment-invariant features. In most classification experiments, a simple statistical Gaussian classifier is used. The plankton object recognition experiments use a Learning Vector Quantization (LVQ) neural-net classifier to achieve superior performance on the highly non-uniform plankton database. By introducing a new parallel LVQ learning scheme, the speed of network training is dramatically increased. Tests show a 95% classification accuracy on six plankton taxa taken from nearly 2,000 images. This result is comparable with what a trained biologist can accomplish by traditional manual techniques, making possible for the first time a fully automated, at-sea approach to real-time mapping of plankton populations.