Generic vs. person specific active appearance models

By Ralph Gross, Iain Matthews, Simon Baker. Image and Vision Computing, 2005

327 citations recorded by the source corpus.

Active Appearance Models (AAMs) are generative parametric models that have been successfully used in the past to model faces. Anecdotal evidence, however, suggests that the performance of an AAM built to model the variation in appearance of a single person across pose, illumination, and expression (a Person Specific AAM) is substantially better than the performance of an AAM built to model the variation in appearance of many faces, including unseen subjects not in the training set (a Generic AAM). In this paper, we present an empirical evaluation that shows that Person Specific AAMs are, as expected, both easier to build and more robust to fit than Generic AAMs. Moreover, we show that: (1) building a generic shape model is far easier than building a generic appearance model, and (2) the shape component is the main cause of the reduced fitting robustness of Generic AAMs. We then proceed to describe two refinements to Generic AAMs to improve their performance: (1) a refitting procedure to improve the quality of the ground-truth data used to build the AAM and (2) a new fitting algorithm. For both refinements we demonstrate dramatically improved fitting performance. Finally, we evaluate the effect of these improvements on a combined model construction and fitting task.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e36f5fab8758194fcad043e23288330657fe7742

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

1. Luc Van Gool
2. Juergen Gall
3. Jiwen Lu
4. G. Wang
5. Xiaogang Wang
6. Dacheng Tao
7. Yi Yang
8. Bernt Schiele

Citations in the corpus

• Discriminative multi-manifold analysis for face recognition from a single training sample per person (2011, methodology): “Person-specific feature representation and extraction methods usually gain better recognition accuracy than generic face recognition methods, as shown in [13], [27], and [54].”
• Continuous sign language recognition: Towards large vocabulary statistical recognition systems handling multiple signers (2015, methodology): “We chose to use the efficient version of the simultaneous inverse-compositional AAM (SICAAM) proposed in [28], which is more robust to large variations in shape and appearance.”
• Facial Landmark Detection: A Literature Survey (2018, background): “Compared to POIC, SIC is more computationally intensive, but generalizes better than POIC [38].”
• Random Forests for Real Time 3D Face Analysis (2012, methodology): “Moreover, these methods perform poorly on unseen identities (Gross et al. 2005) and cannot handle low-resolution images well.”
• Image and Vision Computing (2016, unknown): “For each such subset, we build and fit a Person Specific Model (PSM) [40] in an “one-vs-rest” manner, that is we fit each image i ∈ Qp using the PSM trained on the rest Np − 1 images.”
• Real-time facial feature detection using conditional regression forests (2012, methodology): “Moreover, these methods perform poorly on unseen identities [18] and deal poorly with lowresolution images.”