Automatic knowledge extraction from web images

• Main Author: Li, Baoyan
• Other Authors: Mao Kezhi
• Format: Final Year Project
• Language: English
• Published: 2017
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/71264
• Institution: Nanyang Technological University

This report will provide an in-depth insight into my final year project (FYP) for the title of the project is automatic knowledge extraction for web images. It will be a brief introduction of the project and the software that used for this project. With the development of science and technology, human beings are more desirable for automation systems. Currently images are already widely used by the World Wide Web (WWW). This is important to build impressive ways to manage with retrieve images’ data or information. Beneficially, the network image contains rich context data compared to a conventional image that provides very little information. This project is to develop a program that can automatically obtain knowledge of web page. By using the program method, automatically upload the pictures to Google, and then extract similar images such as the URL, date and location. The two main problems that may bring many difficulties in developing the program: i) that the amount of data currently available on the Web keep changing, mostly in the form of natural language text; ii) The release data speed may be approaching the real-time processing of the text stream. Throughout the research and found out that the problems can be solved by using the python.