Javascript must be enabled for the correct page display

The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition

Jansen, S. (2014) The Neural-SIFT Feature Descriptor for Visual Vocabulary Object Recognition. Master's Thesis / Essay, Artificial Intelligence.

[img]
Preview
Text
AI-MAI-2014-S.JANSEN.pdf - Published Version

Download (1MB) | Preview
[img] Text
toestemming.pdf - Other
Restricted to Backend only

Download (23kB)

Abstract

In computer vision, one area of research which receives a lot of attention is recognizing the semantic content of an image. It’s a challenging problem where varying pose, occlusion, scale and differing light conditions affect the ease of recognition. A common approach is to extract local feature descriptors from images and attach object class labels to them, but choosing the best type of feature to use is still an open problem. Some use deep learning methods to learn to create features during training. Others apply local image descriptors to extract features from an image. In most cases these algorithms show good performance, however, the downside of these type of algorithms is that they are not trainable by design. After training there is no feedback loop to update the type of features to extract, while there possibly could be room for improvement. In this thesis, a continuous deep neural network feedback system is proposed, which consists of an adaptive neural network feature descriptor, the bag of visual words approach, and a neural classifier. Two initialization methods for the neural network feature descriptor were compared, one where it was trained on the popular Scale Invariant Feature Transform (SIFT) descriptor output, and one where it was randomly initialized. After initial training, the system propagates the classification error from the neural network classifier through the entire pipeline, updating not only the classifier itself, but also the type of features to extract. The feature descriptor, before and after additional training, was also applied using a support vector machine (SVM) classifier to test for generalizability. Results show that for both initialization methods the feedback system increased accuracy substantially when regular training was not able to increase it any further. The proposed neural-SIFT feature descriptor performs better than the SIFT descriptor itself even with limited number of training instances. Initializing on an existing feature descriptor is beneficial when not a lot of training samples are available. However, when there are a lot of training samples available the system is able to construct a well-performing feature descriptor when starting in a random state, solely based on classifier feedback. The improved feature descriptor did not only show improved performance in the setting in which it was trained, but also while using an SVM classifier. However, the improvements were small and were only demonstrated with one other classifier. Therefore, more experiments are needed to get a better grip on the generalizability of the improved descriptor.

Item Type: Thesis (Master's Thesis / Essay)
Degree programme: Artificial Intelligence
Thesis type: Master's Thesis / Essay
Language: English
Date Deposited: 15 Feb 2018 08:02
Last Modified: 15 Feb 2018 08:02
URI: http://fse.studenttheses.ub.rug.nl/id/eprint/12433

Actions (login required)

View Item View Item