Fine-grained Image Classification

Please enable javascript in your browser.

Souri, Yaser | 2015

1576 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 47459 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Kasaei, Shohreh
Abstract:
Fine-grained image classification is image classification where the considered classes are all sub-classes of a certain, more general class. In this setting of the problem, the classes are visually very similar to each other, such that an unskilled human cannot discriminate between them. In this case, proposed methods for the ordinary image classification problem do not obtain good classification accuracy. So proposing new methods for solving this problem is necessary. In this thesis two new methods, based on recent advances in deep learning are proposed for solving the fine-grained image classification problem. First by improving several parts of one of the recent proposed methods for this problem, its mean accuracy is improved by more than 10%.Then a novel method for localizing object parts, which is very important in fine-grained classification, is proposed. This novel method is an order of magnitude faster than the state-of-the-art method, while the mean accuracy resulted from using it is comparable to state-of-the-art
Keywords:
Computer Vision ; Object Recognition ; Deep Learning ; Images Classification ; Fine Grained Recognition