An Interactive Framework For Web Image Annotation

With the exponential growth of web image applications and the popularization of image devices, there are more and more digital images over the internet. How to effectively manage and organize these web images for online-users' retrieving is a tough task. Image annotation techniques have been developed to address this problem to a certain extent.Image annotation plays a very important role in managing and retrieving abundant images over the internet nowadays.In this paper, we try to propose a Human-Computer interactive framework for web image annotation which fully considers the human-based computation and all online-users'feedback in Web 2.0.This paper focues on the the following four aspect:First, an interactive image annotation interface is demonstrated. It is utilized to interact with online-users and collect the original manual annotations.Second, an object-based image annotation framework is proposed to provide the automatic results for users. Then, the users'feedback can be recorded and integrated to help our system to achieve performance improvement.Third, a comprehensive method of annotation refinement is developed to remove the noisy keywords.Finally, a simple website crawler which can collect the web images is implemented, and this part will be very helpful for our futher work.