From an image to a text description of an image

This project presents an implementation of a search feature that allows user to look for a particular object of interest in a video. The main idea is to train a very deep neural network architecture that outputs a sequence of words that describe an image. The network consists of a convolutional neur...

Full description

Saved in:
Bibliographic Details
Main Author: Peter
Other Authors: Chng Eng Siong
Format: Final Year Project
Language:English
Published: 2017
Subjects:
Online Access:http://hdl.handle.net/10356/70223
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-70223
record_format dspace
spelling sg-ntu-dr.10356-702232023-03-03T20:27:54Z From an image to a text description of an image Peter Chng Eng Siong School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering This project presents an implementation of a search feature that allows user to look for a particular object of interest in a video. The main idea is to train a very deep neural network architecture that outputs a sequence of words that describe an image. The network consists of a convolutional neural network (CNN) that learns features found on an image, and a long short-term memory (LSTM) unit that predicts the sequence of words from learnt features of the image. This project is not about real-time object detection, instead a video has to be preprocessed before a user may search for an object found visually inside the video. Bachelor of Engineering (Computer Science) 2017-04-17T07:22:49Z 2017-04-17T07:22:49Z 2017 Final Year Project (FYP) http://hdl.handle.net/10356/70223 en Nanyang Technological University 59 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Peter
From an image to a text description of an image
description This project presents an implementation of a search feature that allows user to look for a particular object of interest in a video. The main idea is to train a very deep neural network architecture that outputs a sequence of words that describe an image. The network consists of a convolutional neural network (CNN) that learns features found on an image, and a long short-term memory (LSTM) unit that predicts the sequence of words from learnt features of the image. This project is not about real-time object detection, instead a video has to be preprocessed before a user may search for an object found visually inside the video.
author2 Chng Eng Siong
author_facet Chng Eng Siong
Peter
format Final Year Project
author Peter
author_sort Peter
title From an image to a text description of an image
title_short From an image to a text description of an image
title_full From an image to a text description of an image
title_fullStr From an image to a text description of an image
title_full_unstemmed From an image to a text description of an image
title_sort from an image to a text description of an image
publishDate 2017
url http://hdl.handle.net/10356/70223
_version_ 1759858272626540544