Rapid object detection using a boosted cascade of simple features¶
Why this mattered¶
TBD
Abstract¶
This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.
Related¶
- cite → A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting — Viola-Jones uses AdaBoost from Freund and Schapire to select and weight simple Haar-like features for object detection.
- cite → A model of saliency-based visual attention for rapid scene analysis — Viola-Jones connects to saliency-based attention through the goal of rapidly focusing computation on visually important image regions.
- enables → Selective Search for Object Recognition — The boosted cascade detector established fast proposal-and-rejection object detection, motivating selective search's efficient generation of candidate object windows.
- cite ← Selective Search for Object Recognition — Selective Search compares generic object proposals with sliding-window detector cascades introduced by Viola-Jones-style boosted features.
- enables ← A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting — AdaBoost supplied the learning procedure Viola-Jones used to select simple Haar-like features and build its detection cascade.
- enables ← A model of saliency-based visual attention for rapid scene analysis — The saliency model's rapid attention-selection idea anticipates Viola-Jones's focus on fast candidate filtering before detailed recognition.