Sparse autoencoder based spatial pyramid facial feature learning

The spatial pyramid feature learning methods, such as Spatial Pyramid Matching (SPM) and Sparse Coding based Spatial Pyramid Matching (ScSPM), have achieved significant performance in image categorization. While most of these methods are still based on manual-design features, such as SIFT, HOG and L...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) s. 770 - 774
Hlavní autoři: Ma Xiao, Jufu Feng
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.11.2015
Témata:
Encoding
Face
Face recognition
Feature extraction
Learning systems
Training
ISSN:2327-0985
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The spatial pyramid feature learning methods, such as Spatial Pyramid Matching (SPM) and Sparse Coding based Spatial Pyramid Matching (ScSPM), have achieved significant performance in image categorization. While most of these methods are still based on manual-design features, such as SIFT, HOG and LBP, which limits the representation of data. In this paper, we propose a novel Sparse Autoencoder based Spatial Pyramid Matching (SaSPM) method, which exploits unsupervised sparse autoencoder network infeatures learning and then builds a spatial pyramid structure. There are three main contributions in SaSP-M: Firstly, SaSPM is a learning method directly learning features from original data. Secondly, SaSPM is a full feedforward method in feature extraction, which is more efficient for on-line systems comparing with ScSPM method. Thirdly, we design patch-shared and patch-specific SaSP-M models to learn different local features separatively on well-aligned face images. It is proven that SaSPM outperforms the original spatial pyramid features in varieties of challenging data sets.
ISSN:2327-0985
DOI:10.1109/ACPR.2015.7486607