Image annotation by search

• Main Author: Lee, Ernest Shao Lun
• Other Authors: Sun Aixin
• Format: Final Year Project
• Language: English
• Published: 2016
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/66555
• Institution: Nanyang Technological University

Media has become easily accessibility through phones, portal devices and this has lead in exponential growth in the world of media available in the internet. Today many application revolves around some multimedia content such as famous Instagram, Facebook and Twitter. Thus, there is an increasing interest in developing technologies such as automatic image annotation for organizing and indexing such multimedia content. Hence the objective in this project we will be looking into the digital images and how we can use the semantic meaning of the query images to retrieve appropriate image annotations of the query images. This can take out the process where the user has to manually tag and organize their multimedia content and it can ease users’ experience as who doesn’t like automatic. In this report, different approach of techniques was used to approach this problem and in the end the technique which yields the best result to this problem was implemented. Various image features extraction techniques are used with classification techniques such as SVM, k-mean clustering, Bag of Visual Word model and etc.