An Efficient Multilayer Perceptron Neural Network for Mobile Image Annotation on the Cloud?

With the development of mobile device, large amount of digital images are produced every day. The requirements of effective indexing and searching image are growing rapidly. There is an apparent shift in research from content based image retrieval to automatic image annotation in order to bridge the gap between low level features and high level semantics of image. Automatic Image Annotation techniques facilitate extraction of high level semantic concepts from images by machine learning techniques. So in this research, the association between mobile and cloud opens a new avenue for image annotation, because the heavy computation can be shifted to the cloud for immediately responding user actions. This paper describes and evaluates an automatic image annotation which uses SURF descriptor to select right number of features and right features for annotation. The proposed framework uses Semi-supervised Multilayer Perceptron Neural Network (MLP) in training phase and annotation phase. Finally, the user captures the image from mobile and then forwards it to the cloud and then Annotating the mobile image by the trained MLP. At last, return the annotated image to the mobile.