Our protocol, like theirs, is based on the Fast Distributed Mining (FDM) algorithm of Cheung et al., which is an unsecured distributed version of the Apriori algorithm. The main ingredients in our protocol each of the interacting players hold, and another that tests the inclusion of an element held by ...

Read More »## HORIZONTALLY DISTRIBUTED DATABASES USING SECURE MINING OF ASSOCIATION RULE

There are several sites (or players) that hold homogeneous databases, i.e., databases that share the same schema but hold information on different entities. The goal is to find all association rules with support at least s and confidence at least c , for some given minimal support size s and ...

Read More »## PHOTOMETRIC STEREO FOR GENERAL DIFFUSE SURFACES USING SPARSE BAYESIAN REGRESSION

Photometric stereo algorithm used for stably and accurately estimating the surface normals of a scene in the presence of various non-Lambertian effects. Most conventional algorithms for non-Lambertian photometric stereo can be partitioned into two categories. The first category is built upon stable outlier rejection techniques while assuming a dense Lambertian ...

Read More »## A GENERALISED APPROXIMATE NEAREST NEIGHBOUR FIELD (ANNF) COMPUTATION FRAMEWORK BETWEEN SOURCE AND TARGET IMAGE

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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »## 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 ...

Read More »