Face detection with the modified census transform

By Bernhard Fröba, Andreas Ernst. Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings., 2004

518 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1ad3f52c75c618132a6eab13cb544ad845fcd398

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

A survey on face detection in the wild: Past, present and future (2015, methodology): “In [69] a modified census transform was adopted to generate illumination-insensitive features for face detection.”
Motion-based counter-measures to photo attacks in face recognition (2014, methodology): “In this particular setup, faces are detected using a cascade of classifiers based on a variant of Local Binary Patterns (LBP) referred as Modified Census Transform (MCT) [18].”
Face Detection Based on Multi-Block LBP Representation (2007, background): “Many other features are also proposed to represent facial images, including rotated Haar-like features [6], census transform [3], sparse features [4], etc.”
Context based face anti-spoofing (2013, methodology): “On both datasets, the face locations are retrieved using Modified Census Transform (MCT) based face detector [14].”
Local binary patterns variants as texture descriptors for medical image analysis (2010, background): “ILBP, the improved local binary pattern [18,19] with P = 18.”
We Are Family: Joint Pose Estimation of Multiple Persons (2010, methodology): “For this we combine a face detector [24] with the upper and full human body models in the detection framework of [25].”
MACH: my automated conversation coach (2013, methodology): “We used the Sh ore Framework [22] to detect faces and facial features in order to distinguish smiles.”
Counter-measures to photo attacks in face recognition: A public database and a baseline (2011, methodology): “In this particular setup, faces are detected using a cascade of classifiers based on a variant of Local Binary Patterns (LBP) [21] referred as Modified Census Transform (MCT) [22].”
Template Matching Techniques in Computer Vision: Theory and Practice (2009, methodology): “[13] A Mahalanobis, BVKV Kumar, and D Casasent.”
Better Appearance Models for Pictorial Structures (2009, methodology): “the upper-body detector of [11], or a face detector [13, 28]), we enlarge the window by a predefined factor, to make it cover the whole person (as done in [11]).”
Local Binary Patterns and Its Application to Facial Image Analysis: A Survey (2011, unknown): “Later, CT and its variations were exploited for facial image analysis [43]-[45].”
Local Transform Features and Hybridization for Accurate Face and Human Detection (2013, methodology): “The weak classifiers are constructed using AdaBoost training [35], which updates the weight of each training sample such that misclassified instances are given a higher weight in the subsequent iteration.”
LBP − T OP based countermeasure against face spooﬁng attacks (2012, methodology): “First, each frame of the original frame sequence was gray-scaled and passed through a face detector using MCT features [9].”
A Survey of Recent Advances in Face Detection (2010, methodology): “In [21] a modified census transform was adopted to generate illumination-insensitive features for face detection.”
“Knock! Knock! Who is it?” probabilistic person identification in TV-series (2012, methodology): “We initialize tracks by scanning the whole image every fifth frame, using frontal, half-profile and profile face detectors [8].”
On the effectiveness of local binary patterns in face anti-spoofing (2012, unknown): “similarly to Modified Census Transform (MCT) features proposed in [16], compares the values of the neighboring pixels to the average of the intensity values in the 3x3 neighborhood.”