A robust hash, or content-based fingerprint, is a succinct representation of the perceptually most relevant parts of a multimedia object. A key requirement of fingerprinting is that elements with perceptually similar content should map to the same fingerprint, even if their bit-level representations are different. In this work we propose BAMBOO (Binary descriptor based on AsymMetric pairwise BOOsting), a binary local descriptor that exploits a combination of content-based fingerprinting techniques and computationally efficient filters (box filters, Haar-like features, etc.) applied to image patches. In particular, we define a possibly large set of filters and iteratively select the most discriminative ones resorting to an asymmetric pair-wise boosting technique. The output values of the filtering process are quantized to one bit, leading to a very compact binary descriptor. Results show that such descriptor leads to compelling results, significantly outperforming binary descriptors having comparable complexity (e.g., BRISK), and approaching the discriminative power of state-of-the-art descriptors which are significantly more complex (e.g., SIFT and BinBoost).

Bamboo: A fast descriptor based on AsymMetric pairwise BOOsting

BAROFFIO, LUCA;CESANA, MATTEO;REDONDI, ALESSANDRO ENRICO CESARE;TAGLIASACCHI, MARCO
2014

Abstract

A robust hash, or content-based fingerprint, is a succinct representation of the perceptually most relevant parts of a multimedia object. A key requirement of fingerprinting is that elements with perceptually similar content should map to the same fingerprint, even if their bit-level representations are different. In this work we propose BAMBOO (Binary descriptor based on AsymMetric pairwise BOOsting), a binary local descriptor that exploits a combination of content-based fingerprinting techniques and computationally efficient filters (box filters, Haar-like features, etc.) applied to image patches. In particular, we define a possibly large set of filters and iteratively select the most discriminative ones resorting to an asymmetric pair-wise boosting technique. The output values of the filtering process are quantized to one bit, leading to a very compact binary descriptor. Results show that such descriptor leads to compelling results, significantly outperforming binary descriptors having comparable complexity (e.g., BRISK), and approaching the discriminative power of state-of-the-art descriptors which are significantly more complex (e.g., SIFT and BinBoost).
Image Processing (ICIP), 2014 IEEE International Conference on
filtering theory; fingerprint identification; image representation; Bamboo; binary descriptor based on asymmetric pairwise boosting technique; bit-level representations; content-based fingerprint; content-based fingerprinting techniques; filtering process; image patches; multimedia object; robust hash-based fingerprint; Boosting; Computer vision; Conferences; Dictionaries; Hamming distance; Robustness; Training; Binary descriptors; digital fingerprinting; robust hash
File in questo prodotto:
File Dimensione Formato  
BaroffioICIP2014-2.pdf

accesso aperto

: Pre-Print (o Pre-Refereeing)
Dimensione 363.64 kB
Formato Adobe PDF
363.64 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/945561
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 5
social impact