AM-FM models analyze an image in terms of amplitude and frequency modulated sinusoids. Such models are well suited to describe the local non-stationarities of an image. In this paper the invariance of AM-FM features w...
详细信息
ISBN:
(纸本)9781424442195
AM-FM models analyze an image in terms of amplitude and frequency modulated sinusoids. Such models are well suited to describe the local non-stationarities of an image. In this paper the invariance of AM-FM features with respect to scaling, rotation and illumination changes is presented. These properties can be used in applications of AM-FM image models where features for affine transformed images need to be computed. The application of invariance properties in template tracking is illustrated using a particle filter based tracker that uses the AM-FM features.
In most of the imageprocessing applications there is a maximum limit up to which an image can be compressed without adversely affecting the quality of the image to a great deal. In this paper, we propose a new waterm...
详细信息
ISBN:
(纸本)9781424442195
In most of the imageprocessing applications there is a maximum limit up to which an image can be compressed without adversely affecting the quality of the image to a great deal. In this paper, we propose a new watermarking scheme to embed text in images using an algorithm for finding the optimum bit plane that can be substituted from the image by the character bit plane. The maximum embedding capacity is kept as a function of minimum expected quality. This watermarking method is experimentally found to be highly robust against many imageprocessing attacks including JPEG 2000 as it takes in to consideration both the lossy stages of JPEG 2000 during its implementation.
Color harmonization is an artistic technique to adjust the colors of a given image in order to enhance their visual harmony. In this paper we present a method to automatically improve the color harmony of images. Harm...
详细信息
ISBN:
(纸本)9781424442195
Color harmonization is an artistic technique to adjust the colors of a given image in order to enhance their visual harmony. In this paper we present a method to automatically improve the color harmony of images. Harmonization is performed using a carefully designed optimization in the hue space, while keeping the saturation and intensity components unchanged. Finally, for videos, we pose the problem as an efficient joint optimization in space and time, thus minimizing flickering or visual artifacts in the harmonized output video. We report the performance of our algorithm on a variety of test images and video sequences.
With rapid improvements in the performance and programmability, graphicsprocessing Units (GPUs) have fostered considerable interest in substantially reducing the running time of compute intensive problems. The soluti...
详细信息
ISBN:
(纸本)9781424442195
With rapid improvements in the performance and programmability, graphicsprocessing Units (GPUs) have fostered considerable interest in substantially reducing the running time of compute intensive problems. The solution to the view-independent mutual point-pair visibility problem (required for inter-reflections in global illumination) can, it would seem, require the capabilities of the GPUs. In this paper, various ways of parallelizing the construction of the Visibility Map (V-map, a description of mutual visibility) are presented to lead the way for an implementation that achieves a speed up of 11 or more. We evaluate our scheme qualitatively and quantitatively, and conclude that parallelizing the V-map construction algorithm is eminently useful.
Tracking multiple deformable objects simultaneously in a video is a challenging problem. The tracking is more difficult when the objects are touching each other while they are moving or suddenly appear in or disappear...
详细信息
ISBN:
(纸本)9781424442195
Tracking multiple deformable objects simultaneously in a video is a challenging problem. The tracking is more difficult when the objects are touching each other while they are moving or suddenly appear in or disappear from a frame of the video. In this paper we propose a parametric active membrane, which can change its topology to detect and track multiple objects present in the video. The membrane evolves in image space and also along the image intensity surface and if requires, splits into multiple membranes to track multiple objects. The methodology is tested on real video segments that demonstrates the efficacy of the proposed scheme.
The goal of this article is twofold. First, it deals with color image segmentation in hue-saturation space. A model for circular data is provided by the vM-Gauss distribution, which is a joint distribution of von-Mise...
详细信息
ISBN:
(纸本)9781424442195
The goal of this article is twofold. First, it deals with color image segmentation in hue-saturation space. A model for circular data is provided by the vM-Gauss distribution, which is a joint distribution of von-Mises and Gaussian distributions. The mixture of W-Gauss distributions is used to model hue-saturation data. After segmentation, a post processing based on both spectral and spatial similarity of clusters is applied to separate such identifiable objects in the image. The results and comparisons are shown on Berkeley segmentation dataset. The problem of text extraction from a color image is taken as an application of the proposed method. We use a laboratory made text image dataset to test the method.
In this paper we address the problem of unsupervised learning of usual patterns of activities in an area under surveillance and detecting deviant patterns. We use video epitomes for segmenting foreground objects from ...
详细信息
ISBN:
(纸本)9781424442195
In this paper we address the problem of unsupervised learning of usual patterns of activities in an area under surveillance and detecting deviant patterns. We use video epitomes for segmenting foreground objects from background and obtain an approximate shape, trajectory and temporal information in the form of space-time patches. We apply pLSA for finding correlations among these patches to learn usual activities in the scene. We also extend pLSA to classify a novel video as usual or unusual.
Symmetry and affine repetitions are common in scenes with man-made structures. In this paper we propose a technique to exploit affine repetitions in a 3D scene for reconstruction and view synthesis from a single image...
详细信息
ISBN:
(纸本)9781424442195
Symmetry and affine repetitions are common in scenes with man-made structures. In this paper we propose a technique to exploit affine repetitions in a 3D scene for reconstruction and view synthesis from a single image. Assuming three vanishing points in the image, we show how the 3D structure of multiple objects and their affine repetitions may be computed and used for synthesizing new views. The reconstructed objects may also be inserted in other scenes to create augmented images.
In this paper a new robust watermarking scheme is proposed in multiresolution fractional Fourier transform domain using singular value decomposition. The watermark is embedded in the high frequency sub-band of the hos...
详细信息
ISBN:
(纸本)9781424442195
In this paper a new robust watermarking scheme is proposed in multiresolution fractional Fourier transform domain using singular value decomposition. The watermark is embedded in the high frequency sub-band of the host image at coarsest level. Although the schemes based on SVD are robust but fail under ambiguity attacks. In this attack, both the owner and attacker can extract their watermark from the watermarked image. To prevent ambiguity, the normalized mass matrix is formed and embedded in the host image. In extraction, normalized mass matrix is extracted first and compared with original one. If the similarity is found then the singular values are extracted to construct the watermark. Experimental evaluation demonstrates that the proposed scheme is able to withstand a variety of attacks.
This paper presents a fundamentally new algebraic approach to the analysis and synthesis of discrete orthogonal basis functions. It provides the theoretical background to unify Fourier Gabor and discrete orthogonal po...
详细信息
ISBN:
(纸本)9781424442195
This paper presents a fundamentally new algebraic approach to the analysis and synthesis of discrete orthogonal basis functions. It provides the theoretical background to unify Fourier Gabor and discrete orthogonal polynomial moments. For the first time, a set of objective tests are proposed to measure the quality of basis functions. It consists of two main sections: the theoretical background on the generation and orthogonalization of basis functions together with a new solution for the computation of spectra from incomplete data, as well as the implementation of interpolation for all orthogonal basis functions;a new approach to discrete orthogonal polynomials, proving that there is one and only one unitary discrete polynomial basis. Furthermore, the concept of anisotropic moments is introduced and applied to 2D seismic data, which is an imageprocessing problem. The new polynomial basis is numerically better conditioned than the discrete cosine transform. This opens the door to new image compression algorithms, offering a higher compression ratio than the well known JPEG method, for the same numerical effort.
暂无评论