Ilan Shimshoni

2 accepted papers

2018

Efficient Sliding Window Computation for NN-Based Template Matching

ECCV 2018poster

Template matching is a fundamental problem in computer vision, with many applications. Existing methods use sliding window computation for choosing an image-window that best matches the tem- plate. For classic algorithms based on SSD, SAD and normalized cross- correlation, efficient algorithms have…

Cited by 18 Source ↗PDF ↗Scholar ↗

2016

Using Spatial Order to Boost the Elimination of Incorrect Feature Matches

Lior Talker, Yael Moses, Ilan Shimshoni

CVPR 2016poster

Correctly matching feature points in a pair of images is an important preprocessing step for many computer vision applications. In this paper we propose an efficient method for estimating the number of correct matches without explicitly computing them. In addition, our method estimates the region of…

Cited by 8 PDF ↗Scholar ↗