Joint Haar-like features for face detection

By Takeshi Mita, Toshimitsu Kaneko, Osamu Hori. Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

365 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Survey of Recent Advances in Face Detection (2010, methodology): “It has been advocated in various works [46] [6] [101] [62] that RealBoost yields better performance than the original AdaBoost algo- rithm.”
A survey on face detection in the wild: Past, present and future (2015, methodology): “RepresentativeWorks General AdaBoost[17] boosting RealBoost[59] [60] [61] [62] schemes GentleBoost[107] [66] FloatBoost[59] Reuseprevious Boostingchain[110] nodes'results Nestedcascade[61] Introduce AsymmetricBoosting[111] [112] [113] asymmetry Linearasymmetricclassifier[116]…”
High-Performance Rotation Invariant Multiview Face Detection (2007, positive): “Moreover,afinerparti-tionofthefeaturespacewasadoptedtoalleviatetheweaknessofstumpfunction,e.g.,LiuandShum’shistogrammethod [16],Wuetal.’spiece-wisefunction[13],andMitaetal.’sjoint binarizationsofHaar-likefeature[17].”
Aggregate channel features for multi-view face detection (2014, methodology): “These methods mainly get the performance gains in two aspects, more complicated features [17, 19, 26] and (or) more powerful learning algorithms [14, 1, 25].”
Face Detection Based on Multi-Block LBP Representation (2007, background): “However, the Haar-like features seem too simple and show some limits [7].”