Yung-Nien Sun

Multiscale corner detection by using wavelet transform

A multiscale corner detection algorithm based on the wavelet transform of contour orientation is proposed. It can utilize both the information of the local extrema and modulus of transform results to detect corners and arcs effectively. The ramp-width of contour orientation profile, which can be computed using the transformed modulus of two scales, reveals the difference between corner and arc and is utilized in the determination of corner points. The experimental results have shown that the detector is more effective than both the single- and multiple-scale detectors. They also demonstrate that the detector is insensitive to boundary noise. In addition, the proposed method is more efficient than the other multiscale corner detector because it operates on fewer number of scales, which can be implemented by a fast transform algorithm.

Polygonal approximation using a competitive Hopfield neural network

Abstract Polygonal approximation plays an important role in pattern recognition and computer vision. In this paper, a parallel method using a Competitive Hopfield Neural Network (CHNN) is proposed for polygonal approximation. Based on the CHNN, the polygonal approximation is regarded as a minimization of a criterion function which is defined as the arc-to-chord deviation between the curve and the polygon. The CHNN differs from the original Hopfield network in that a competitive winner-take-all mechanism is imposed. The winner-take-all mechanism adeptly precludes the necessity of determining the values for the weighting factors in the energy function in maintaining a feasible result. The proposed method is compared to several existing methods by the approximation error norms L2 and L∞ with the result that promising approximation polygons are obtained.

Texture feature coding method for classification of liver sonography

This paper introduces a new texture analysis method called texture feature coding method (TFCM) for classification of ultrasonic liver images. The TFCM transforms a gray-level image into a feature image in which each pixel is represented by a texture feature number (TFN) coded by TFCM. The TFNs obtained are used to generate a TFN histogram and a TFN co-occurrence matrix (CM), which produces texture feature descriptors for classification. Four conventional texture analysis methods that are gray-level CM, texture spectrum, statistical feature matrix and fractal dimension, are used also to classify liver sonography for comparison. The supervised maximum likelihood (ML) classifiers implemented by different type texture features are applied to discriminate ultrasonic liver images into three disease states that are normal liver, liver hepatitis and cirrhosis. The 30 liver sample images proven by needle biopsy are used to train the ML system that classify on a set of 90 test sample images. Experimental results show that the ML classifier together with TFCM texture features outperforms one with the four conventional methods with respect to classification accuracy.

Wavelet-based fractal features with active segment selection: Application to single-trial EEG data

Feature extraction in brain-computer interface (BCI) work is one of the most important issues that significantly affect the success of brain signal classification. A new electroencephalogram (EEG) analysis system utilizing active segment selection and multiresolution fractal features is designed and tested for single-trial EEG classification. Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the proposed system consists of three main procedures including active segment selection, feature extraction, and classification. The active segment selection is based on the continuous wavelet transform (CWT) and Students two-sample t-statistics, and is used to obtain the optimal active time segment in the time-frequency domain. We then utilize a modified fractal dimension to extract multiresolution fractal feature vectors from the discrete wavelet transform (DWT) data for movement classification. By using a simple linear classifier, we find significant improvements in the rate of correct classification over the conventional approaches in all of our single-trial experiments for real finger movement. These results can be extended to see the good adaptability of the proposed method to imaginary movement data acquired from the public databases.

Polygonal approximation using genetic algorithms

A polygon approximation method based on genetic algorithms is proposed in this paper. In the method, a chromosome is used to represent a polygon and is represented by a binary string. Each bit, called a gene, represents a point on the object curve. The objective function is defined as the integral square error between the given curve and the approximated polygon. Three genetic operators namely selection, crossover and mutation, have been constructed for this specific problem. The proposed method when compared with three existing methods can obtain superior approximation results with less error norm with respect to the original curves.

EEG-based motor imagery analysis using weighted wavelet transform features.

In this study, an electroencephalogram (EEG) analysis system for single-trial classification of motor imagery (MI) data is proposed. Feature extraction in brain-computer interface (BCI) work is an important task that significantly affects the success of brain signal classification. The continuous wavelet transform (CWT) is applied together with Students two-sample t-statistics for 2D time-scale feature extraction, where features are extracted from EEG signals recorded from subjects performing left and right MI. First, we utilize the CWT to construct a 2D time-scale feature, which yields a highly redundant representation of EEG signals in the time-frequency domain, from which we can obtain precise localization of event-related brain desynchronization and synchronization (ERD and ERS) components. We then weight the 2D time-scale feature with Students two-sample t-statistics, representing a time-scale plot of discriminant information between left and right MI. These important characteristics, including precise localization and significant discriminative ability, substantially enhance the classification of mental tasks. Finally, a correlation coefficient is used to classify the MI data. Due to its simplicity, it will enable the performance of our proposed method to be clearly demonstrated. Compared to a conventional 2D time-frequency feature and three well-known time-frequency approaches, the experimental results show that the proposed method provides reliable 2D time-scale features for BCI classification.

Ultrasonic image analysis for liver diagnosis

The authors propose a new ultrasonic image analysis system that can be utilized as an effective tool in classifying liver states as normal, hepatitis, or liver cirrhosis. In this system, the authors first define suitable settings for the ultrasonic device, then remove the inhomogeneous structures from the area of interest in the image, and then, by using the forward sequential search method, look for the useful texture parameters from the co-occurrence matrix, the statistical feature matrix, the texture spectrum, and the fractal dimension descriptors. Finally, the selected parameters are fed into a probabilistic neural network for the classification of liver disease. Experimental results are presented that show the classification rate with and without the inclusion of the inhomogeneous structures.

Wavelet transformation for gray-level corner detection

Abstract Corners are very attractive features for many applications in computer vision. In this paper, a new gray-level corner detection algorithm based on the wavelet transform is presented. The wavelet transform is used because the evolution across scales of its magnitudes and orientations can be used to characterize localized signals like edges and corners. Most conventional corner detectors detect corners based on the edge detection information. However, these edge detectors perform poorly at corners, adversely affecting their overall performance. To overcome this drawback, we first propose a new edge detector based on the ratio of the inter-scale wavelet transform modulus. This edge detector can correctly detect edges at the corner positions, making accurate corner detection possible. To reduce the number of points required to be processed, we apply the non-minima suppression scheme to the edge image and extract the minima image. Based on the orientation variance, these non-corner edge points are eliminated. In order to locate the corner points, we propose a new corner indicator based on the scale invariant property of the corner orientations. By examining the corner indicator the corner points can be located accurately, as shown by experiments with our algorithm. In addition, since wavelet transform possesses the smoothing effect inherently, our algorithm is insensitive to noise contamination as well.

Three-Dimensional Modeling From Endoscopic Video Using Geometric Constraints Via Feature Positioning

The endoscope is a popular imaging modality used in many preevaluations and surgical treatments, and is also one of the essential tools in minimally invasive surgery. However, regular endoscopes provide only 2-D images. Even though stereoendoscopy systems can display 3-D images, the real anatomical structure of the observed lesion is unavailable and can only be judged by the surgeons imagination. In this paper, we present a constraint-based factorization method for reconstructing 3-D structures registered to the patient, from 2-D endoscopic images. The proposed method incorporates the geometric constraints from the tracked surgical instrument into the traditional factorization method based on frame-to-frame feature motion on the endoscopically viewed scene. Experiments with real and synthetic data demonstrate good real-scale 3-D extraction, with greater accuracy than is available from traditional methods. The reconstruction process can also be accomplished in a few seconds, making it suitable for on-line surgical applications to provide surgeons with additional 3-D shape information, critical distance monitoring and warnings.

Automatic seamless mosaicing of microscopic images: enhancing appearance with colour degradation compensation and wavelet‐based blending

In order to observe the fine details of biomedical specimens, various kinds of high‐magnification microscopes are used. However, they suffer from a limited field of view when visualizing highly magnified specimens. Image mosaicing techniques are necessary to integrate two or more partially overlapping images into one and make the whole specimen visible. In this study, we propose a new system that automatically creates panoramic images by mosaicing all the microscopic images acquired from a specimen. Not only does it effectively compensate for the congenital narrowness in microscopic views, but it also results in the mosaiced image containing as little distortion with respect to the originals as possible. The system consists of four main steps: (1) feature point extraction using multiscale wavelet analysis, (2) image matching based on feature points or by projection profile alignment, (3) colour difference adjustment and optical degradation compensation with a Gaussian‐like model and (4) wavelet‐based image blending. In addition to providing a precise alignment, the proposed system also takes into account the colour deviations and degradation in image mosaicing. The visible seam lines are eliminated after image blending. The experimental results show that the system performs well on differently stained image sequences and is effective on acquired images with large colour variations and degradation. It is expected to be a practical tool for microscopic image mosaicing.