Title :
Temporal context in object recognition
Author :
Chalasani, Rakesh ; Principe, Jose C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Florida, Gainesville, FL, USA
Abstract :
Sparse coding has become a popular way to learn feature representation from the data itself. However, temporal context, when present, can provide useful information and alleviate instability in sparse representation. Here we show that when sparse coding is used in conjunction with a dynamical system, the extracted features can provide better descriptors for time-varying observations. We show a marked improvement in classification performance on COIL-100 and animal datasets using our model. We also propose a simple extension to our model to learn invariant representations.
Keywords :
feature extraction; image coding; image representation; object recognition; COIL-100; animal datasets; feature representation; features extraction; invariant representations; object recognition; sparse coding; sparse representation; temporal context; time-varying observations; Animals; Context; Dictionaries; Encoding; Feature extraction; Mathematical model; Object recognition; Classification; Feature extraction; Sparse Coding; Temporal Context;
Conference_Titel :
Machine Learning for Signal Processing (MLSP), 2012 IEEE International Workshop on
Conference_Location :
Santander
Print_ISBN :
978-1-4673-1024-6
Electronic_ISBN :
1551-2541
DOI :
10.1109/MLSP.2012.6349758