An Automatic Image Content Retrieval Method for better Mobile Device Display User Experiences

A growing number of commercially available mobile phones come with integrated\nhigh-resolution digital cameras. That enables a new class of dedicated\napplications to image analysis such as mobile visual search, image cropping,\nobject detection, content-based image retrieval, image classification. In this\npaper, a new mobile application for image content retrieval and classification\nfor mobile device display is proposed to enrich the visual experience of users.\nThe mobile application can extract a certain number of images based on the\ncontent of an image with visual saliency methods aiming at detecting the most\ncritical regions in a given image from a perceptual viewpoint. First, the most\ncritical areas from a perceptual perspective are extracted using the local\nmaxima of a 2D saliency function. Next, a salient region is cropped using the\nbounding box centred on the local maxima of the thresholded Saliency Map of the\nimage. Then, each image crop feds into an Image Classification system based on\nSVM and SIFT descriptors to detect the class of object present in the image.\nImageNet repository was used as the reference for semantic category\nclassification. Android platform was used to implement the mobile application\non a client-server architecture. A mobile client sends the photo taken by the\ncamera to the server, which processes the image and returns the results (image\ncontents such as image crops and related target classes) to the mobile client.\nThe application was run on thousands of pictures and showed encouraging results\ntowards a better user visual experience with mobile displays.\n