Face recognition: component-based versus global approaches
By Bernd Heisele, Purdy Ho, Jane Wu, Tomaso A. Poggio. Computer Vision and Image Understanding, 2003
465 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/43b249b6398cf759cebde761c97aac557ba48450
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
- A Comparative Study of Local Matching Approach for Face Recognition (2007, background): “Heisele et al. compared component (local) and global (holistic) approaches and observed that " the component system outperformed the global systems for recognition rates larger than 60% " [18].”
- Face Recognition with Convolutional Neural Networks and subspace learning (2017, background): “[6] demonstrated that the local component system outperforms the global system for recognition accuracies larger than 60% and local features are more robust to changes in poses than holistic features.”
- Facial expression recognition using radial encoding of local Gabor features and classifier synthesis (2012, background): “The face recognition performance is significantly improved when the local features are involved, compared to that of only using global features, as reported in [15,16].”
- Creating efficient codebooks for visual recognition (2005, unknown): “Representations based on loose collections of invariant appearance descriptors extracted from local image patches have become very popular for texture analysis and visual recognition [1, 5, 7, 9, 12, 17, 18, 19, 25, 24, 26, 27].”
- A Survey of Face Recognition Techniques (2009, background): “Face recognition methods for intensity images fall into two main categories: feature-based and holistic [46-48].”
- Hello! My name is... Buffy'' -- Automatic Naming of Characters in TV Video (2006, background): “Extracting descriptors based on the feature locations [1, 17] gives robustness to pose variation, lighting, and partial occlusion compared to a global face descriptor [8, 15].”
- Partial Face Recognition: Alignment-Free Approach (2013, methodology): “3) We extend the MKD-SRC method for partial face verification, which is effective on the LFW database.”
- A survey on activity recognition and behavior understanding in video surveillance (2013, unknown): “in [44, 57, 200], which proposes several unsupervised tech-”