Robust Face Detection Using the Hausdorff Distance

By Oliver Jesorsky, Klaus J. Kirchberg, Robert Frischholz. International Conference on Audio- and Video-Based Biometric Person Authentication, 2001

1,054 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4053e3423fb70ad9140ca89351df49675197196a

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

Citations in the corpus

Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces (2008, background): “[25] and the measures by Rodriguez et al.”
To learn image super-resolution, use a GAN to learn how to do image degradation first (2018, background): “Similarly to image super-resolution, the vast majority of face super-resolution methods [18–23] are based on a paired setting for training and evaluation which is typically done on frontal datasets (e.g. CelebA [24], Helen [25], LFW [26], BioID [27]).”
Feature Detection and Tracking with Constrained Local Models (2006, methodology): “Distance metric (m e ) Cumulative Error Distribution CLM PSM AVG (a) BIOID Results -CLM vs PSM vs AVG 0 0.05 0.1 0.15 0.2 0.25 0.3 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1”
Automatic feature localisation with constrained local models (2008, methodology): “The fully automatic localisation accuracy of the CLM and AAM algorithms was tested by applying the methods to the publicly available BIOID [25] and XM2VTS [26] data sets.”
Facial point detection using boosted regression and graph models (2010, background): “Of the works described above, [ 3, 14] have been evaluated on the same publicly available database: the BioID database [11].”
Localizing Parts of Faces Using a Consensus of Exemplars (2013, background): “The publicly available BioID dataset contains 1,521 images, each showing a frontal view of a face of one of 23 different subjects [16].”
Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, methodology): “This dataset is selected because it is more challenging than other conventional datasets, such as BioID [46] and LFPW [14].”
An expectation maximization approach to the synergy between image segmentation and object categorization (2005, methodology): “For faces the MRF-based detection system and the morphable model were trained using 100 hand-labelled face images from the database in [15], and the system was evaluated on the data set of [29].”
Interactive Facial Feature Localization (2012, methodology): “In this experiment, following [19] we train we train our algorithm on MUCT dataset [19] and test on BioID dataset [20].”
Accurate Eye Centre Localisation by Means of Gradients (2011, neutral): “0%) (Jesorsky et al., 2001) (38.”
Robust Face Landmark Estimation under Occlusion (2013, background): “Other popular modern approaches to detect the pose or parts of an object involve first detecting the object parts independently and then estimating pose and/or shape through flexible parts models [5, 27, 2, 20] or directly from detections [21, 19, 8].”
Learning Face Localization Using Hierarchical Recurrent Networks (2002, methodology): “Fig. 5. Localization performance: (a) percentage of examples having small deye for the proposed method (TRN, TST) and for the hybrid system (Hausdorff+MLP)[ 5 ]; (b) rejecting the least confident examples lowers the number of mislocalizations.”
Projection functions for eye detection (2004, methodology): “In [14], when the same detection method and evaluation criteria were applied to both XM2VTS and BioID face databases, the successful detection rates are 98.4% and 91.8% respectively.”
How to solve classification and regression problems on high-dimensional data with a supervised extension of slow feature analysis (2013, methodology): “To increase image variability and improve generalization, face images from several databases were used, namely 1,521 images from BioID (Jesorsky et al., 2001), 9,030 from CAS-PEAL (Gao et al.”
Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment (2014, background): “Impressive results are achieved on two public datasets, BioID [16] and LFPW [3].”
Annotated Facial Landmarks in the Wild: A large-scale, real-world database for facial landmark localization (2011, background): “BioID 1,521 20 23 384x286 grayscale [15]”
Learn to Combine Multiple Hypotheses for Accurate Face Alignment (2013, background): “Due to its importance, a lot of works were proposed to advance face alignment, and achieved remarkable improvements on standard benchmarks, such as BioID [14] and LFPW [1].”