Pattern Analysis and Applications

, Volume 17, Issue 2, pp 441–449

Fast training procedure for Viola–Jones type object detectors using Laplacian clutter models

  • Sri-Kaushik Pavani
  • David Delgado-Gomez
  • Alejandro F. Frangi
Industrial and Commercial Application

DOI: 10.1007/s10044-012-0309-3

Cite this article as:
Pavani, SK., Delgado-Gomez, D. & Frangi, A.F. Pattern Anal Applic (2014) 17: 441. doi:10.1007/s10044-012-0309-3
  • 233 Downloads

Abstract

This paper presents a fast training strategy for the Viola–Jones (VJ) type object-detection systems. The VJ object- detection system, popular for its high accuracy at real-time testing speeds, has a drawback that it is slow to train. A face detector, for example, can take days to train. In content-based image retrieval (CBIR), where search needs to be performed instantaneously, VJ’s long training time is not affordable. Therefore, VJ’s method is hardly used for such applications. This paper proposes two modifications to the training algorithm of VJ-type object detection systems which reduces the training time to the order of seconds. Firstly, Laplacian clutter (non-object) models are used to train the weak classifier, thus eliminating the need to read and evaluate thousands of clutter images. Secondly, the training procedure is simplified by removing the time-consuming AdaBoost-based feature selection procedure. An object detector, trained with 500 images, approximately takes 2 s for training in a conventional 3 GHz machine. Our results show that the accuracy of the detector, built with the proposed approach, is inferior to that of VJ for difficult object class such as frontal faces. However, for objects with lesser degree of intra-class variations such as hearts, state-of-the-art accuracy can be obtained. Importantly, for CBIR applications, the fast testing speed of the VJ type object detector is maintained.

Keywords

Object detectionHaar-like featuresClutter modelsLaplacian distribution

Supplementary material

10044_2012_309_MOESM1_ESM.avi (14.6 mb)
Supplementary material 1 (avi 14916 kb)
10044_2012_309_MOESM2_ESM.txt (2 kb)
Supplementary material 1 (TXT 2 kb)

Copyright information

© Springer-Verlag London 2012

Authors and Affiliations

  • Sri-Kaushik Pavani
    • 1
    • 2
  • David Delgado-Gomez
    • 3
  • Alejandro F. Frangi
    • 1
    • 2
    • 4
  1. 1.Center for Computational Imaging and Simulation Technologies in BiomedicineUniversitat Pompeu FabraBarcelonaSpain
  2. 2.Networking Research Center on Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN)San SebastainSpain
  3. 3.Universidad Carlos III de MadridMadridSpain
  4. 4.Catalan Institution for Research and Advanced Studies (ICREA)BarcelonaSpain