Results 1 -
4 of
4
Blur and contrast invariant fast stereo matching.
- Lecture Notes in Comput. Sci.
, 2008
"... Abstract. We propose a novel approach for estimating a depth-map from a pair of rectified stereo images degraded by blur and contrast change. At each location in image space, information is encoded with a new class of descriptors that are invariant to convolution with centrally symmetric PSF and to ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Abstract. We propose a novel approach for estimating a depth-map from a pair of rectified stereo images degraded by blur and contrast change. At each location in image space, information is encoded with a new class of descriptors that are invariant to convolution with centrally symmetric PSF and to variations in contrast. The descriptors are based on local-phase quantization, they can be computed very efficiently and encoded in a limited number of bits. A simple measure for comparing two encoded templates is also introduced. Results show that, the proposed method can represent a cheap but still effective way for estimating disparity maps from degraded images, without making restrictive assumptions; these advantages make it attractive for practical applications.
Interactive digital photography at scale
, 2013
"... Interactive editing and manipulation of digital media is a fundamental component in digital content creation. One media in particular, digital imagery, has seen a recent increase in popularity of its large or even massive image formats. Unfortunately, current systems and techniques are rarely concer ..."
Abstract
- Add to MetaCart
Interactive editing and manipulation of digital media is a fundamental component in digital content creation. One media in particular, digital imagery, has seen a recent increase in popularity of its large or even massive image formats. Unfortunately, current systems and techniques are rarely concerned with scalability or usability with these large images. Moreover, processing massive (or even large) imagery is assumed to be an off-line, automatic process, although many problems associated with these datasets require human intervention for high quality results. This dissertation details how to design interactive image techniques that scale. In particular, massive imagery is typically constructed as a seamless mosaic of many smaller images. The focus of this work is the creation of new technologies to enable user interaction in the formation of these large mosaics. While an interactive system for all stages of the mosaic creation pipeline is a long-term research goal, this dissertation concentrates on the last phase of the mosaic creation pipeline – the composition of registered images into a seamless composite. The work detailed in this dissertation provides the technologies to fully realize interactive editing in mosaic composition on image collections
A Hybrid Method for Blur Invariants in Images using Contourlet Transforms
"... Radiometric degradation is a common problem in the image restoration part of many applications. The degradation may involve blurring, information loss due to sampling, quantization effects and various sources of noise. The purpose of image restoration is to estimate the original image from the degra ..."
Abstract
- Add to MetaCart
(Show Context)
Radiometric degradation is a common problem in the image restoration part of many applications. The degradation may involve blurring, information loss due to sampling, quantization effects and various sources of noise. The purpose of image restoration is to estimate the original image from the degraded image. There is much research carried out in an effort to deblur such images. To tackle this problem, different blur invariants had existed so far. Wavelet domain blurs invariants are used only for discrete 2D signals in spatial domain where it is concentrated in centrally symmetric blurs and also in the wavelet domain, directional prediction is so hard to find smoother contours. In this paper, the Contourlet Transform was proposed to address the lack of geometrical structure in the separable 2D Wavelet Transform. Because of
Image Registration using Blur Invariants in Wavelet Domain
"... Image registration is an important step in all image analysis and it performs the operation of overlaying images of the alike picture taken at various times, from various viewpoints, and/or by various sensors. The wavelet domain provides invariant that are centrally symmetric to blur. Blur invariant ..."
Abstract
- Add to MetaCart
(Show Context)
Image registration is an important step in all image analysis and it performs the operation of overlaying images of the alike picture taken at various times, from various viewpoints, and/or by various sensors. The wavelet domain provides invariant that are centrally symmetric to blur. Blur invariants are constructed from different wavelet function. Template image is chosen in the degraded images using similarity the template image is matched with the original image. Using Daubuchies wavelet functions the images are accurately registered, even in the severely degraded images compared to the spatial domain blur invariants which may result in misfocus registration of an image. Key words
