Zhenwei Miao

Weighted Iterative Truncated Mean Filter

The iterative truncated arithmetic mean (ITM) filter was proposed recently. It offers a way to estimate the sample median by simple arithmetic computing instead of the time consuming data sorting. In this paper, a rich class of filters named weighted ITM (WITM) filters are proposed. By iteratively truncating the extreme samples, the output of the WITM filter converges to the weighted median. Proper stopping criterion makes the WITM filters own merits of both the weighted mean and median filters and hence outperforms the both in some applications. Three structures are designed to enable the WITM filters being low-, band- and high-pass filters. Properties of these filters are presented and analyzed. Experimental evaluations are carried out on both synthesis and real data to verify some properties of the WITM filters.

Interest point detection using rank order LoG filter

This paper proposes a novel nonlinear filter, named rank order Laplacian of Gaussian (ROLG) filter, based on which a new interest point detector is developed. The ROLG filter is a weighted rank order filter. It is used to detect the image local structures where a significant majority of pixels are brighter or darker than a significant majority of pixels in their corresponding surroundings. Compared to linear filter based detectors, e.g. SIFT detector, the proposed rank order filter based detector is more robust to abrupt variations of images caused by illumination and geometric changes. Experiments on the benchmark databases demonstrate that the proposed ROLG detector achieves superior performance comparing to four state-of-the-art detectors. Evaluation experiments are also conducted on face recognition problems. The results on five face databases further demonstrate that the ROLG detector significantly outperforms the other detectors.

Further Properties and a Fast Realization of the Iterative Truncated Arithmetic Mean Filter

The iterative truncated arithmetic mean (ITM) filter has been recently proposed. It possesses merits of both the mean and median filters. In this brief, the Cramer-Rao lower bound is employed to further analyze the ITM filter. It shows that this filter outperforms the median filter in attenuating not only the short-tailed Gaussian noise but also the long-tailed Laplacian noise. A fast realization of the ITM filter is proposed. Its computational complexity is studied. Experimental results demonstrate that the proposed algorithm is faster than the standard median filter.

Additive and exclusive noise suppression by iterative trimmed and truncated mean algorithm

An iterative trimmed and truncated arithmetic mean (ITTM) algorithm is proposed, and the ITTM filters are developed. Here, trimming a sample means removing it and truncating a sample is to replace its value by a threshold. Simultaneously trimming and truncating enable the proposed filters to attenuate the mixed additive and exclusive noise in an effective way. The proposed trimming and truncating rules ensure that the output of the ITTM filter converges to the median. It offers an efficient method to estimate the median without time-consuming data sorting. Theoretical analysis shows that the ITTM filter of size n has a linear computational complexity O(n). Compared to the median filter and the iterative truncated arithmetic mean (ITM) filter, the proposed ITTM filter suppresses noise more effectively in some cases and has lower computational complexity. Experiments on synthetic data and real images verify the filters properties.

A novel rank order LoG filter for interest point detection

This paper proposes a novel non-linear filter, named rank order LoG (ROLG) filter, and a new interest point detector, named ROLG detector. The ROLG filter is a weighted rank order filter. It is used to detect image structures whose significant majority of pixels are brighter (or darker) than the significant majority of pixels in their corresponding surroundings. The ROLG detector is built on this filter. Compared to linear filter based detectors, the proposed rank order filter based detector is more robust to abrupt variations of images. Experiments on the benchmark databases demonstrate that the ROLG detector achieves superior performance compared to four state-of-the-art detectors. Evaluation experiments are also conducted on face recognition. The results further demonstrate that the ROLG detector has better performance compared to other detectors.

A vote of confidence based interest point detector

In this paper, a vote of confidence (VC) based detector is proposed to detect bright and dark regions from images. Whether a local region is bright or dark is voted by all the pixels in this region. Compared to the contrast based detectors, such as the popular SIFT detector, the VC detector is invariant to illumination change and robust to abrupt variations. Experiments are conducted on benchmark databases to verify the superior performance of the VC detector in terms of the repeatability and matching score. The proposed detector is also evaluated in the application of face recognition.

Contrast Invariant Interest Point Detection by Zero-Norm LoG Filter

The Laplacian of Gaussian (LoG) filter is widely used in interest point detection. However, low-contrast image structures, though stable and significant, are often submerged by the high-contrast ones in the response image of the LoG filter, and hence are difficult to be detected. To solve this problem, we derive a generalized LoG filter, and propose a zero-norm LoG filter. The response of the zero-norm LoG filter is proportional to the weighted number of bright/dark pixels in a local region, which makes this filter be invariant to the image contrast. Based on the zero-norm LoG filter, we develop an interest point detector to extract local structures from images. Compared with the contrast dependent detectors, such as the popular scale invariant feature transform detector, the proposed detector is robust to illumination changes and abrupt variations of images. Experiments on benchmark databases demonstrate the superior performance of the proposed zero-norm LoG detector in terms of the repeatability and matching score of the detected points as well as the image recognition rate under different conditions.The Laplacian of Gaussian (LoG) filter is widely used in interest point detection. However, low-contrast image structures, though stable and significant, are often submerged by the high-contrast ones in the response image of the LoG filter, and hence are difficult to be detected. To solve this problem, we derive a generalized LoG filter, and propose a zero-norm LoG filter. The response of the zero-norm LoG filter is proportional to the weighted number of bright/dark pixels in a local region, which makes this filter be invariant to the image contrast. Based on the zero-norm LoG filter, we develop an interest point detector to extract local structures from images. Compared with the contrast dependent detectors, such as the popular scale invariant feature transform detector, the proposed detector is robust to illumination changes and abrupt variations of images. Experiments on benchmark databases demonstrate the superior performance of the proposed zero-norm LoG detector in terms of the repeatability and matching score of the detected points as well as the image recognition rate under different conditions.

Hybrid feature-based wallpaper visual search

In this paper we propose a hybrid feature-based wallpaper visual search system. As opposed to conventional techniques that use global features to perform wallpaper search, this paper proposes to integrate local and global features to support both functions of recognition (identify the product ID of the query images) and retrieval (search wallpapers that are visually similar to the query images). An adaptive SIFT is designed to extract sufficient number of local features from both the query and reference images. The combination of the sparse and dense SIFT features results in a significant improvement of the recognition rate. Global features are further incorporated in the system for the visually similar image retrieval. A new query expansion is proposed to alleviate the problems caused by cluttered background, occlusion, scale change and illumination changes. Experiments on a dataset consisting of 2,208 reference images from 218 different designs show that the proposed method can achieve a recognition rate of more than 90%.

Feature weighting in visual product recognition

Significant progress towards visual search has been made in the past two decades through the development of local invariant features. Among existing local feature detectors, the Scale Invariant Feature Transform (SIFT) is widely used since it is designed to be invariant to minimal illumination changes and certain geometric transformations. However, in practice, the recognition performance is still subject to actual condition. Some keypoints are more stable while others are less stable and can not be repeatedly detected. Besides, in visual object recognition where the foreground object is to be recognized while the background suppressed, the current scalable vocabulary tree (SVT) framework treats each descriptor as equally important, hence restricting its performance. This paper aims to study the effect of SIFT respect to illumination and geometric changes and develop a feature weighting algorithm to incorporate the stability of SIFT and saliency information into weighted scalable vocabulary tree (WSVT) based recognition. Experimental results on a commercial product database show the proposed feature weighting algorithm outperforms the baseline SVT recognition by 5%.

Laplace gradient based Discriminative and Contrast Invertible descriptor

The performance of local descriptors such as SIFT drops under severe illumination changes. In this paper, we propose a Discriminative and Contrast Invertible (DCI) local feature descriptor. In order to increase the discriminative ability of the descriptor under illumination changes, a Laplace gradient based histogram is proposed. Moreover, a robust contrast flipping estimate is proposed based on the divergence of a local region. Experiments on fine-grained object recognition and retrieval applications demonstrate the superior performance of the DCI descriptor to others.