Attribute recognition from clothing using a Faster R-CNN based multitask network
Authors:
- 25 March 2018
- journal article
- research article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Wavelets, Multiresolution and Information Processing
- Vol. 16 (02)
Abstract
Appearance information such as clothing and hairstyle can provide rich clues to identify a person in surveillance videos. This paper proposes a Faster R-CNN based multi-task neural network to recognize attributes such as gender, nationality, etc. from clothing of a person. Toward this end, a fine-tuned Faster R-CNN is applied to locate people in images. Then hierarchical features are extracted from these regions to perform attributes recognition. The recognition network and Faster R-CNN share the same weights, and they can be trained in an end-to-end manner. Experiments are conducted on a newly collected and well-labeled image dataset. The experimental results show that our network can locate a human body and identify its attributes efficiently.Keywords
This publication has 21 references indexed in Scilit:
- Soft Biometrics; Human Identification Using Comparative DescriptionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- GABOR-BASED TENSOR LOCAL DISCRIMINANT EMBEDDING AND ITS APPLICATION ON PALMPRINT RECOGNITIONInternational Journal of Wavelets, Multiresolution and Information Processing, 2010
- Multiscale facial structure representation for face recognition under varying illuminationPattern Recognition, 2009
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Soft Biometric Traits for Personal Recognition Systems2004
- Skeletonization of ribbon-like shapes based on a new wavelet functionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- New method for feature extraction based on fractal behaviorPattern Recognition, 2002
- Characterization of Dirac-structure edges with wavelet transformIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2000
- Off-line recognition of Chinese handwriting by multifeature and multilevel classificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998