2014 5th European Workshop on Visual Information Processing (EUVIP)
DOI: 10.1109/euvip.2014.7018369
Full text: Download
In this article we address the issue of adopting a local sparse coding representation (Histogram of Sparse Codes), in a part-based framework for inferring the locations of facial land-marks. The rationale behind this approach is that unsupervised learning of sparse code dictionaries from face data can be an effective approach to cope with such a challenging problem. Results obtained on the CMU Multi-PIE Face dataset are presented providing support for this approach.