Robust Logo Recognition for Mobile Phone Applications

In the paper, a new recognition method for logos imaged by mobile phone cameras is presented which can be incorporated with mobile phone services for use in enterprise identification, corporate website access, traffic sign reading, security check, content awareness, and the related applications. The main challenge in applying the logo recognition for mobile phone applications is the inevitable photometric and geometric transformations encountered when a handheld mobile phone camera operates at a varying viewpoint under different lighting environments. A new distinctive logo feature vector and an associated similarity measure are proposed for logo recognition using the Zernike moment (ZM) phase information. The discriminative power of the new logo recognition method is compared with three major existing methods. The experimental results indicate that the proposed ZM phase method has the best performance in terms of the precision and recall criterion under the above inevitable imaging variations. An analysis on the performances of the four recognition methods is given to account for the performance discrepancy.