Shuifa Sun

Maximum similarity thresholding

Otsu method is one of the most popular image thresholding methods. The segmentation results of Otsu method are in general acceptable for the gray level images with bimodal histogram patterns that can be approximated with mixture Gaussian modal. However, it is difficult for Otsu method to determine the reliable thresholds for the images with mixture non-Gaussian modal, such as mixture Rayleigh modal, mixture extreme value modal, mixture Beta modal, mixture uniform modal, comb-like modal. In order to determine automatically the robust and optimum thresholds for the images with various histogram patterns, this paper proposes a new global thresholding method based on a maximum-image-similarity idea. The idea is inspired by analyzing the relationship between Otsu method and Pearson correlation coefficient (PCC), which provides a novel interpretation of Otsu method from the perspective of maximizing image similarity. It is then natural to construct a maximum similarity thresholding (MST) framework by generalizing Otsu method with the maximum-image-similarity concept. As an example, a novel MST method is directly designed according to this framework, and its robustness and effectiveness are confirmed by the experimental results on 41 synthetic images and 86 real world images with various histogram shapes. Its extension to multilevel thresholding case is also discussed briefly.

Three particle swarm algorithms to improve coverage of camera networks with mobile nodes

This paper studies how to improve the coverage of camera networks where the locations and orientations of the cameras can be adjusted. As the power energy limits the distance that each camera can move, the coverage problem is a constrained optimization. We provide three particle swarm optimization (PSO) algorithms for the problem, which are the penalty PSO, the absorbing PSO, and the reflecting PSO. The penalty PSO adds penalty to the coverage when a camera violates the distance constraint, while the last two PSO algorithms use the feasibility operators. By the absorbing PSO, the cameras out of the distance limit will stay at the boundary of the limit, while by the reflecting PSO their locations are randomly reinitialize into the feasible area. The three PSO algorithms are tested on the benchmarks, and the statistical analysis shows that their performance is in the descendant order of absorbing PSO, penalty PSO, and reflecting PSO. The results suggest that the absorbing PSO is a good choice for the coverage problem of camera networks.

A blind audio watermarking based on stochastic resonance signal processor

A blind audio watermarking algorithm in the time domain is proposed. The audio signal is divided into frames and the watermark is inserted on a frame by frame basis. The proposed algorithm detects the watermark using a signal processor based on the stochastic resonance mechanism. The watermark detection does not need the original audio. The parameter-induce stochastic resonance in audio watermarking is observed and the interpretation to this phenomenon is given. For the synchronization attack, the experimental results show that the stochastic resonance signal processor can catch up and surpass the performance of the matched filter. This reveals a robustness superiority of the stochastic resonance signal processor, compared to the matched filter operating outside its strict nominal conditions, which is especially helpful for the audio watermarking.

Stochastic resonance signal processor: Principle, capacity analysis and method

In this letter, a signal processor based on the bistable aperiodic stochastic resonance (ASR), that can be used to detect the base-band binary pulse amplitude modulation (PAM) signal transmitting over an additive white Gaussian noise (AWGN) channel, is studied. The principle of the ASR signal processor is analyzed and the information capacity of such a communication system is evaluated by the Bit Error Ratio (BER) and the bit rate, according to the well-known Shannon information theory. The roles played by the noise on this capacity are analyzed. It is observed that keeping the bit rate unchanged we can neither decrease BER nor increase the bit rate and keep BER unchanged by adjusting the density of the noise. Simulation results also agree well with this observation. In addition, a statistical method to improve the performance of the system is proposed with theory and experiment.

On-line boosting based real-time tracking with efficient HOG

In this paper, a real-time visual tracking system that delivers superior performance under difficult situations is proposed. The system is based on Histogram of Oriented Gradient (HOG) within the on-line boosting framework. For environmental adaptation, the HOG feature is calculated with blocks of random scale, position and aspect ratio which form a feature pool. The on-line boosting can then select the best distinguishable features from this pool for the robust tracking. The randomness of the blocks guarantees the existence of those features. Three experiments are conducted to highlight different characteristics of this new system. The first experiment proves the validity for the system to be able to pick out the best possible HOG features. The second experiment shows its robustness against bad illuminations and small foreground background difference. The third experiment demonstrates its advancement compared with the Haar-based state-of-the-art system. All those are offered without sacrificing the computation load.

Image edge detection based on rotating kernel transformation

An edge detection algorithm based on improved Rotating Kernel Transformation, IRKT edge detection method (IRKTE), is proposed in this paper. The algorithm adopt the line detection approach RKT, and defines a new model of edge detection according to the direction difference between edge and smooth regions. Simultaneously, an accurate edge location approach based on edge normal direction is presented to overcome the wide width caused by a large scale kernel in IRKT. Furthermore, the improvement of previous IRKT with weight edge detection (IRKTEW) is proposed to improve the ability to resist the noise effectively. A series of experiments are carried out through the picture libraries with ground truth and the performance is analyzed with ROC curves. The experimental results show that the proposed method can effectively detect the edge under the strong noises, and the performance of edge detection is improved with the proposed approach.

Median-based thresholding, minimum error thresholding, and their relationships with histogram-based image similarity

A popular histogram-based thresholding method is minimum error thresholding (MET) proposed by Kittler and Illingworth [Minimum error thresholding, Pattern Recognition 19 (1) (1986) 41-47], whereas Xue and Titterington recently proposed a median-based thresholding (MBT) [Median-based image thresholding, Image and Vision Computing 29 (9) (2011) 631-637]. Both MET and MBT can be derived from the maximization of log-likelihood. In this paper, we present a different theoretical interpretation about MBT and MET, from the perspective of minimizing Kullback-Leibler (KL) divergence. Since the KL divergence is a measure of the difference between two probability distributions, it is reasonable to regard MET and MBT as the special applications of histogram-based image similarity (HBIS) in the image thresholding. Further, it is natural to suggest a more universal image thresholding framework based on image similarity concept, since HBIS is just one of many image similarity methodologies. This thresholding framework directly transforms the threshold determining problem into an image comparison issue. Its significance is that it provides a concise and clear theoretical framework for developing potential thresholding methods with the plentiful image similarity theories.

Haar-Like and HOG Fusion Based Object Tracking

Only unitary feature for object is adopted in the conventional tracking system, making it difficult for robust tracking. Regarding the characteristic of both Haar-like and HOG features, a tracking algorithm fusing these two features is proposed: using the Haar-like features for the structure of the object and HOG features for the edge. A mixed feature pool is constructed with these two features. The On-line Boosting feature selection framework is adopted to select out the notable features, and update these features on line to realize the optimal selection. Four representative videos are used to test the performance of the proposed algorithm in the aspect of illumination change, tacking small targets, complex motion of the object, similar object interference during tracking and so on. Statistical analysis Results of the error show that the tracking system using the fused features outperforms the system using either of the two features.

Improved Rotating Kernel Transformation Based Contourlet Domain Image Denoising Framework

A contourlet domain image denoising framework based on a novel Improved Rotating Kernel Transformation is proposed, where the difference of subbands in contourlet domain is taken into account. In detail: (1). A novel Improved Rotating Kernel Transformation (IRKT) is proposed to calculate the direction statistic of the image; The validity of the IRKT is verified by the corresponding extracted edge information comparing with the state-of-the-art edge detection algorithm. (2). The direction statistic represents the difference between subbands and is introduced to the threshold function based contourlet domain denoising approaches in the form of weights to get the novel framework. The proposed framework is utilized to improve the contourlet soft-thresholding (CTSoft) and contourlet bivariate-thresholding (CTB) algorithms. The denoising results on the conventional testing images and the Optical Coherence Tomography (OCT) medical images show that the proposed methods improve the existing contourlet based thresholding denoising algorithm, especially for the medical images.

Optical Coherence Tomography heart tube image denoising based on contourlet transform

Optical Coherence Tomography(OCT) gradually becomes a very important imaging technology in the Biomedical field for its noninvasive, nondestructive and real-time properties. However, the interpretation and application of the OCT images are limited by the ubiquitous noise. In this paper, a denoising algorithm based on contourlet transform for the OCT heart tube image is proposed. A bivariate function is constructed to model the joint probability density function (pdt) of the coefficient and its cousin in contourlet domain. A bivariate shrinkage function is deduced to denoise the image by the maximum a posteriori (MAP) estimation. Three metrics, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and equivalent number of look (ENL), are used to evaluate the denoised image using the proposed algorithm. The results show that the signal-to-noise ratio is improved while the edges of object are preserved by the proposed algorithm. Systemic comparisons with other conventional algorithms, such as mean filter, median filter, RKT filter, Lee filter, as well as bivariate shrinkage function for wavelet-based algorithm are conducted. The advantage of the proposed algorithm over these methods is illustrated.