Approximate Nearest Neighbour Field (ANNF) computations are a recent development in the image processing community which have gained wide popularity, especially in the graphics community, due to their fast computation times. In this abstract, we propose FeatureMatch, a generalised approximate nearest-neighbour field (ANNF) computation framework, between a source and target image. The proposed algorithm can […]
SHARING VISUAL SECRETS IN SINGLE IMAGE RANDOM DOT STEREOGRAMS BASED ON BVCS
In this abstract, a binocular VCS (BVCS), called the ( 2 , n ) -BVCS, and an encryption algorithm are proposed to hide the shared pixels in the single image random dot stereograms (SIRDSs). Because the SIRDSs have the same 2D appearance as the conventional shares of a VCS, this paper tries to use SIRDSs […]
BVCS: SHARING VISUAL SECRETS IN SINGLE IMAGE RANDOM DOT STEREOGRAMS
Visual cryptography (VC) is a technique that encrypts a secret image into n shares, with each participant holding one share; Conventional VCSs suffer from a transmission risk problem because the noise-like shares will raise the suspicion of attackers and the attackers might intercept the transmission. Previous research has involved in hiding shared content in halftone […]
AS-PROJECTIVE-AS-POSSIBLE WARPS WITH MOVING DIRECT LINEAR TRANSFORMATION
Image stitching or photo stitching is the process of combining multiple photographic images with overlapping fields of view to produce a segmented panorama or high-resolution image. Commonly performed through the use of computer software, most approaches to image stitching require nearly exact overlaps between images and identical exposures to produce seamless results. We investigate projective […]
FEATUREMATCH ALGORITHM FOR A GENERAL ANNF ESTIMATION TECHNIQUE AND ITS APPLICATIONS
The proposed algorithm can estimate ANNF maps between any image pairs, not necessarily related. This generalisation is achieved through appropriate spatial-range transforms. To compute ANNF maps, global colour adaptation is applied as a range transform on the source image. Image patches from the pair of images are approximated using low-dimensional features, which are used along […]
EFFICIENT LEARNING FOR IMAGE STITCHING WITH MOVING DIRECT LINEAR TRANSFORMATION
This abstract propose as-projective-as-possible warps, i.e., warps that aim to be globally projective, yet allow local non-projective deviations to account for violations to the assumed imaging conditions. Based on a novel estimation technique called Moving Direct Linear Transformation (Moving DLT), our method seamlessly bridges image regions that are inconsistent with the projective model. The result […]
A NOVEL HUB-BASED CLUSTERING FOR HIGH-DIMENSIONAL DATA
Clustering becomes difficult due to the increasing sparsity of such data, as well as the increasing difficulty in distinguishing distances between data points. Hubness is the tendency of some data points in high-dimensional data sets to occur much more frequently in k-nearest-neighbor lists of other points than the rest of the points from the set, […]
2D TO STEREOSCOPIC 3D CONVERSION USING ROBUST SEMI-AUTOMATIC DEPTH MAP GENERATION IN UNCONSTRAINED IMAGES AND VIDEO SEQUENCES
Stereoscopic imaging has been around for many decades, it has recently seen a rise in interest due to the availability of consumer 3D displays and 3D films. This surge is seen in the recent proliferation of big budget 3D movies, or with some portions of the film being offered in 3D. 3D films show novel […]
THE ROLE OF HUB-BASED CLUSTERING FOR HIGH-DIMENSIONAL DATA
Clustering in general is an unsupervised process of grouping elements together, so that elements assigned to the same cluster are more similar to each other than to the remaining data points. In this abstract, we take a novel perspective on the problem of clustering high-dimensional data. Instead of attempting to avoid the curse of dimensionality […]
UNCONSTRAINED IMAGES AND VIDEO SEQUENCES CONTAINS ROBUST SEMI-AUTOMATIC DEPTH MAP GENERATION FOR 2D TO STEREOSCOPIC 3D CONVERSION
Our framework relies on the user providing an initial estimate of the depth, where the user marks objects and regions as closer or farther from the camera. We allow the user to mark with monochromatic intensities, as well as a varying color palette from dark to light, serving in the same function as the intensities. […]
- « Previous Page
- 1
- …
- 16
- 17
- 18
- 19
- 20
- …
- 108
- Next Page »