Segmentation > Advanced > Find Facial Features
Finds facial features in the Current Image such as frontal faces, profile faces, eyes, nose, mouth, and others.
Sets type of facial feature to detect
- Face Frontal: Detects front-facing faces using CART-based classifiers 
- Face Profile: Detects upright face profiles using Haar features passed through a decision stump
- Eye Pair (small): Detects pairs of eyes. Better suited for smaller eye pairs .
- Eye Pair (large): Detects pairs of eyes. Better suited for larger eye pairs .
- Left Eye: Detects left eye using Haar features passed through a decision stump 
- Right Eye: Detects right eye using Haar features passed through a decision stump 
- Nose: Detects nose using Haar features passed through a decision stump 
- Mouth: Detects mouth using Haar features passed through a decision stump 
- Upper Body: Detects the upper body (i.e., head and shoulders area) 
- Pedestrians 1 (small): Detects pedestrians at a distance using HOG features 
- Pedestrians 1 (large): Detects pedestrians close up 
- Pedestrians 2: Detects pedestrians using ACF features trained on the INRIA Person dataset 
- Pedestrians 3: Detects pedestrians using ACF features trained on the Caltech Pedestrian dataset 
Factor which controls the detection strength of facial feature finding. Increase the slider to increase the sensitivity of feature-finding algorithm. (Recommended: 4-10)
 Lienhart R., Kuranov A., and V. Pisarevsky “Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection.”, Proceedings of the 25th DAGM Symposium on Pattern Recognition. Magdeburg, Germany, 2003.
 Castrillón Marco, Déniz Oscar, Guerra Cayetano, and Hernández Mario, “ENCARA2: Real-time detection of multiple faces at different resolutions in video streams”. In Journal of Visual Communication and Image Representation, 2007 (18) 2: pp. 130-140.
 Kruppa H., Castrillon-Santana M., and B. Schiele. “Fast and Robust Face Finding via Local Context”. Proceedings of the Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, 2003, pp. 157–164.
 Dalal, N. and B. Triggs. “Histograms of Oriented Gradients for Human Detection,“Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, June 2005, pp. 886-893.
 Dollar, C. Wojeck, B. Shiele, and P. Perona. “Pedestrian detection: An evaluation of the state of the art.” Pattern Analysis and Machine Intelligence, IEEE Transactions.Vol. 34, Issue 4, 2012, pp. 743–761.
Need more help with this?
Chat with an expert now ››