Project abstract for group papaniko

Fast Approximate Nearest Neighbors Search

These researchers have been investigating a new indexing method using sparse coding for fast approximate Nearest Neighbors (NN) on high dimensional image data using MSI resources. Inspired by the recent advances in signal processing and compressive sensing, the group's current research work is to sparse code each data point using a learned basis dictionary and indices of the dictionary’s support sets are used to generate one compact identifier for each data point. This generates a small code for each data point, which can be stored and retrieved fast using a hash table mechanism. Typically, most real world datasets consist of billions of high dimensional data points, and demand large computational and storage resources for the learning and coding phases. The computational and storage resources provided by MSI allow the group to continue their research productively

A bibliography of this group’s publications is attached.

Return to this PI's main page.