The state-of-the-art image retrieval approaches usually quantize SIFT features into visual words. Researchers proposed the notion of bundled feature which simply employs MSER to bundle SIFT features into groups. In this paper, we propose a large scale partial-duplicate image retrieval scheme using invariance weight of SIFT and SROA geometric consistency based on the bundled feature. We calculate the invariance weight of a SIFT feature by voting the number of the SIFT features in the transformed image space. Considering each bundled feature in polar coordinate system, we propose two consistency parameters: the Scale and Radius consistency parameter, and the Orientation and Angle consistency parameter (SROA geometric consistency). Experiments demonstrate that the invariance weight of SIFT feature can improve the performance of image retrieval, and the SROA geometric constraint is more effective and powerful than the existing geometric constraints for the bundled feature.

This paper proposes an effective scale- and rotation-invariant local binary pattern (LBP) feature for texture classification. A circular neighboring set of an image pixel is defined as a scale-adaptive texton by taking into account the fundamental local structure property of the pixel. The scale space of a texture image is derived by the Laplacian of the Gaussian and then employed to determine the optimal scale of each pixel reflecting the characteristic length of the corresponding structure and determining the radius of the scale-adaptive texton. Different pixels have different optimal scales, resulting in the scale invariance. Contrary to the traditional LBP features that usually ignore global spatial information, the proposed method also defines subuniform patterns of each uniform pattern to improve the discrimination. For each uniform pattern, the subuniform pattern with the maximum statistical value is defined as the dominant orientation subuniform pattern. It is moved to the first column, and the others are circularly shifted. Experimental results demonstrate a good discrimination capability of the proposed scale- and rotation-invariant LBP in texture classification. Particularly, the LBP based on the scale-adaptive texton is promising to be powerful for texture description and scale-invariant texture classification, and the circular shift subuniform LBP can further improve the performance in the rotation-invariant texture classification.

Scale and rotation invariant texture classification is a challenging and significant topic in texture analysis. This paper presents a scale and rotation invariant Gabor Texture Descriptor (GTD) for texture classification. Firstly, Gabor filters with different orientations and scales are carried out on an image. Secondly, to obtain a scale invariant GTD, different scale energies of these Gabor filtered images are calculated, and the optimal matching scales of the GTD are chosen by the sliding window filter with the scale energies. Thirdly, to extract a rotation invariant GTD, a new method using Discrete Fourier Transform is employed on the scale invariant GTD. At last, the distances between the GTDs of a query image and the target images are calculated for texture classification. Five different GTDs are employed for texture classification to demonstrate the effectiveness of the proposed scale and rotation invariant GTD.

Object categorization plays an important role in computer vision, semantic based image content understanding, and image retrieval. Wavelet packet transform provides a very good observation for the images by sub-band filtering. Different objects have distinctive characteristics in the sub-bands of wavelet packets, which should be discriminative for objects classification. In this paper, an object categorization method using hierarchical wavelet packet texture descriptors is proposed. Comparisons between Gabor texture descriptor, pyramid of histograms of orientation gradients (PHOG) and the proposed hierarchical wavelet packet texture descriptors on the widely used OT, Scene-13 and Sport event datasets are also given. Experimental results show that object categorization performances of the proposed texture descriptors are better than that of Gabor texture descriptor and as good as that of PHOG shape descriptor. Object categorization performances of the texture descriptors under various decomposition levels and wavelet bases are discussed. Performances of texture descriptors of global and local images with different partition patterns are also analyzed.

This paper proposes a novel scene change detection algorithm based on the 3D wavelet transform. In scene change including cut, dissolve and fade, the frames have particular temporal and spatial layouts. The dissolve and the fade have strong temporal and spatial correlation; on the contract the correlation of the cut is weak. The 3D wavelet transform can effectively express the correlation of the several successive frames since the low-frequency and high-frequency component coefficients have the proper statistics regularities which can effectively identify the shot transitions. Three features are computed to describe the correlation of the shot transitions, which are input to support vector machines for scene change detection. Experimental results show that the method is effective for the gradual shot transition detection.

The starting and ending (S & E) frames of each text that embeds in a scene or is graphically added to video, provide not only important clues for highlight events detection in semantic-based video analysis, indexing and retrieval but also hint for decoding the videos structure and classification. In this paper, a fast text tracking method of determining S & E frames is proposed, which consists of two modules: text matching, where a mean absolute difference (MAD) based line against line matching (LALM) criterion is proposed to determine whether the detected texts in two frames are similar or not; and S & E frames determination, where an MAD based line matching algorithm is introduced in the direct current (DC) domain to determine the accurate positions of the S & E frame. Experiments conducted with a variety of video sources show that the proposed text tracking method is fast and robust.