Automatic Image Annotation Using Deep Learning

Please enable javascript in your browser.

Bahramipoor, Misagh | 2016

573 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 48486 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Jamzad, Mansour
Abstract:
With the advances in technology, Nowadays digital cameras are everywhere. As a result very large amount of images are on the web. Searching through these images intelligently and purposively is an essential need. Recently the possibility of retrieving images with some conceptual words along side of content based image retrieval has been studied in computer vision. For this purpose it’s required that for each image several words that describe its content be assigned automatically. One of the main problems for this task is semantic gap, meaning that the low level features such as color, texture,… don’t have the ability to describe the high level concepts in images which are comprehensible by human. In machine learning, Deep learning methods with inspiration of how human brain works have been able to model and extract high level features that are comprehensible by human. In this study we try to utilize deep learning for perception of images and extraction of high level features. These features can decrease the existing semantic gap. Our results demonstrate that the new features were able to improve annotation’s performance
Keywords:
Deep Learning ; Image Annotation ; Semantic Gap ; Image Annotation ; High-Level Features

No TOC