Finding Objects for Blind People Based on SURF Features

Nowadays computer vision technology is helping the visually impaired by recognizing objects in their surroundings. Unlike research of navigation and wayfinding, there are no camera-based systems available in the market to find personal items for the blind. This paper proposes an object recognition method to help blind people find missing items using Speeded-Up Robust Features (SURF). SURF features can extract distinctive invariant features that can be utilized to perform reliable matching between different images in multiple scenarios. These features are invariant to image scale, translation, rotation, illumination, and partial occlusion. The proposed recognition process begins by matching individual features of the user queried object to a database of features with different personal items which are saved in advance. Experiment results demonstrate the effectiveness and efficiency of the proposed method.