Main Article Content
Abstract
With the glowing popularity of smartphones and other mobile devices, high-quality cameras are increasingly pervasive. As a result, capturing images and sharing them on social platforms like Facebook, Instagram and Foursquare has become a common part of our daily life. However, without the proper privacy protection, the shared images with or without text can reveal much of users' personal and social environments and their private lives since images can intuitively tell when and where a special moment took place, who participated and what were their relationships. Unfortunately, many people especially young users of social networks often share private images about themselves, their friends and classmates without being aware of the potential impact on their future lives caused by unwanted disclosure and privacy violations. This paper introduces the concept of Maximally Stable Extremal Regions (MSER) and CNN to the privacy settings prevailing. The Convolutional Neural Network (CNN) is employed to protect the sensitive objects in the image. The Maximally Stable Extremal Regions (MSER) is adapted to protect the text regions under the images.