Main Page
Deanship
The Dean
Dean's Word
Curriculum Vitae
Contact the Dean
Vision and Mission
Organizational Structure
Vice- Deanship
Vice- Dean
KAU Graduate Studies
Research Services & Courses
Research Services Unit
Important Research for Society
Deanship's Services
FAQs
Research
Staff Directory
Files
Favorite Websites
Deanship Access Map
Graduate Studies Awards
Deanship's Staff
Staff Directory
Files
Researches
Contact us
عربي
English
About
Admission
Academic
Research and Innovations
University Life
E-Services
Search
Deanship of Graduate Studies
Document Details
Document Type
:
Thesis
Document Title
:
Enhancement of Automatic Image Annotation Using Association Rules
تحسين شرح الصور التلقائي باستخدام قواعد الربط
Subject
:
Faculty of Computing and Information Technology
Document Language
:
Arabic
Abstract
:
Effective and fast retrieval of images from an image database is not an easy task, especially with the continuous and fast growth of digital images on the web. Images can be retrieved based on text describing or surrounding them, or based on the visual features. In both approaches, the retrieved images are not always semantically related to the query image. The automatic image annotation (AIA) is an approach that has been proposed and used by researchers to facilitate the retrieval of images semantically related to a query image. The AIA can be achieved with different approaches, text-based approach, content-based approach and the multimodal approach when the two modalities (text and visual features) are used to annotate the image. A novel multimodal image annotation method is proposed in this thesis. The main purpose is to enhance the multimodal image annotation by taking advantages of textual and visual information and combine them using the association rules (ARs). The proposed method relies on clustering to regroup the text and visual features into clusters and on association rules mining to generate the rules that associate text clusters to visual clusters. The semantic ARs are generated during the training phase and later used in the annotation phase of the system. These rules semantically relate text clusters with visual clusters to predict a list of tags for each query image. In the experimental evaluation, two datasets of the photo annotation tasks are considered; ImageCLEF 2011 and ImageCLEF 2012. The results achieved by the proposed method are better than all the multimodal methods of participants in ImageCLEF 2011 photo annotation task and state-of-the-art methods. Moreover, the MiAP of the proposed method is better than the MiAP of 7 participants out of 11 when using ImageCLEF 2012 in the evaluation.
Supervisor
:
Dr. Mounira Tayeb
Thesis Type
:
Master Thesis
Publishing Year
:
1440 AH
2019 AD
Added Date
:
Friday, February 8, 2019
Researchers
Researcher Name (Arabic)
Researcher Name (English)
Researcher Type
Dr Grade
Email
إيمان صالح الأحمدي
Alahmadi, Eman Saleh
Researcher
Master
Files
File Name
Type
Description
43964.pdf
pdf
Back To Researches Page