Image Categorization using Color Blobs in a Mobile Environment

This paper generalizes the basic idea of blobs in preattentive perception using color information. This is used as the base of a basic classi cation of low resolution pictures taken with mobile phones. This classi cation, the blob-like representation of the image and other information in userʹs context, such as GPS information, can be used in the presented framework as the basis of a new graphical interface for HCI (Human Computer Interaction). Similar systems whether they work with global properties of the image, which leads to inaccurate results, or with complex segmentation process that fails to capture expected objects in the scene. Most of those systems do not pay attention on other information involved in the creation of the image, such as time or location. We describe a system which uses geographical information associated with a picture in a mobile phone terminal, and with a fast segmentation based on color categorization