Learning Mid-Level Features from Object Hierarchy for Image Classification

Loading...
Thumbnail Image
Date
2014
Authors
Albaradei, Somayah
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Abstract
One of the most active research areas in computer vision is image classification. Although there have been many research efforts in this area, it remains a difficult problem, especially when the number of categories is large. Most of the previous work in image classification uses low-level image features. We believe low-level features ignore a lot of the semantic structures of the image classes. In this thesis, we go beyond simple low-level features and propose new approaches for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representations implicitly capture the hierarchical structure in object classes. We show that our proposed approach outperforms other baseline methods in image classification.
Description
Keywords
Image Classification, Mid-Level Features
Citation
@inproceedings{albaradei2014, title = {Learning Mid-Level Features from Object Hierarchy for Image Classification}, author= {Albaradei, Somayah and Wang, Yang and Cao,Liangliang and Li,Jia}, booktitle = {Proceedings of IEEE Winter Conference on Applications of Computer Vision}, year = {2014} }