In this work, we propose a novel fragile watermarking scheme in wavelet transform domain, which is sensitive to all kinds of manipulations and has the ability to localize the tamp...
In video surveillance, the size of face images is very small. However, few works have been done to investigate scale invariant face recognition. Our experiments on appearance-base...
Sets of local features that are invariant to common image transformations are an effective representation to use when comparing images; current methods typically judge feature set...
We present an approach for synthesizing transformations to enhance locality in imperfectly-nested loops. The key idea is to embed the iteration space of every statement in a loop ...
Fast retrieval methods are critical for large-scale and
data-driven vision applications. Recent work has explored
ways to embed high-dimensional features or complex distance
fun...