Page 249 -

228 4 Feature detection and matching

those by van de Weijer and Schmid (2006); Abdel-Hakim and Farag (2006); Winder and
Brown (2007); Hua, Brown, and Winder (2007). Techniques for efficiently matching features
include k-d trees (Beis and Lowe 1999; Lowe 2004; Muja and Lowe 2009), pyramid match-
ing kernels (Grauman and Darrell 2005), metric (vocabulary) trees (Nist´ er and Stew´ enius
2006), and a variety of multi-dimensional hashing techniques (Shakhnarovich, Viola, and
Darrell 2003; Torralba, Weiss, and Fergus 2008; Weiss, Torralba, and Fergus 2008; Kulis and
Grauman 2009; Raginsky and Lazebnik 2009).
The classic reference on feature detection and tracking is (Shi and Tomasi 1994). More
recent work in this field has focused on learning better matching functions for specific features
(Avidan 2001; Jurie and Dhome 2002; Williams, Blake, and Cipolla 2003; Lepetit and Fua
2005; Lepetit, Pilet, and Fua 2006; Hinterstoisser, Benhimane, Navab et al. 2008; Rogez,
¨
Rihan, Ramalingam et al. 2008; Ozuysal, Calonder, Lepetit et al. 2010).
A highly cited and widely used edge detector is the one developed by Canny (1986).
Alternative edge detectors as well as experimental comparisons can be found in publica-
tions by Nalwa and Binford (1986); Nalwa (1987); Deriche (1987); Freeman and Adelson
(1991); Nalwa (1993); Heath, Sarkar, Sanocki et al. (1998); Crane (1997); Ritter and Wilson
(2000); Bowyer, Kranenburg, and Dougherty (2001); Arbel´ aez, Maire, Fowlkes et al. (2010).
The topic of scale selection in edge detection is nicely treated by Elder and Zucker (1998),
while approaches to color and texture edge detection can be found in (Ruzon and Tomasi
2001; Martin, Fowlkes, and Malik 2004; Gevers, van de Weijer, and Stokman 2006). Edge
detectors have also recently been combined with region segmentation techniques to further
improve the detection of semantically salient boundaries (Maire, Arbelaez, Fowlkes et al.
2008; Arbel´ aez, Maire, Fowlkes et al. 2010). Edges linked into contours can be smoothed
and manipulated for artistic effect (Lowe 1989; Finkelstein and Salesin 1994; Taubin 1995)
and used for recognition (Belongie, Malik, and Puzicha 2002; Tek and Kimia 2003; Sebastian
and Kimia 2005).
An early, well-regarded paper on straight line extraction in images was written by Burns,
Hanson, and Riseman (1986). More recent techniques often combine line detection with van-
ishing point detection (Quan and Mohr 1989; Collins and Weiss 1990; Brillaut-O’Mahoney
1991; McLean and Kotturi 1995; Becker and Bove 1995; Shufelt 1999; Tuytelaars, Van Gool,
and Proesmans 1997; Schaffalitzky and Zisserman 2000; Antone and Teller 2002; Rother
2002; Koˇ seck´ a and Zhang 2005; Pflugfelder 2008; Sinha, Steedly, Szeliski et al. 2008; Tardif
2009).

4.5 Exercises

Ex 4.1: Interest point detector Implement one or more keypoint detectors and compare
their performance (with your own or with a classmate’s detector).
Possible detectors:

• Laplacian or Difference of Gaussian;
• F¨ orstner–Harris Hessian (try different formula variants given in (4.9–4.11));

• oriented/steerable filter, looking for either second-order high second response or two
edges in a window (Koethe 2003), as discussed in Section 4.1.1.