This Small Business Innovation Research (SBIR) Phase II research project develops the concept of using hand-held, mobile devices to link the physical world to information networks using advanced pattern and symbol recognition technology that will be deployed on the mobile device. The proposed mobile symbol recognition technology will enable many opportunities for mobile e-commerce by recognizing bar codes, text on documents and user-customizable icons that are used to carry and convey information. To address these opportunities, technical challenges associated with limited processing power and memory resources, lower-quality optics in cameras, varying available network bandwidth, and the diversified development platforms they represent must be overcome. The advances proposed include the ability to unwarp images to account for distortions due to perspective imaging and lenses, removing imaging artifacts such as non-uniform lighting and highlights, deblurring images caused by fixed focus and motion, and improving the image contrast all within the resource constraints of the mobile devices. Recognition algorithms in the system must be able to automatically identify and decode various barcodes symbologies, handle multiple languages and fonts for Optical Character Recognition (OCR), and be trainable for user customizable icons. Special consideration must be given to cross platform development so algorithms can be efficiently and robustly embedded in different development platforms.
The ability to perform image processing and pattern recognition algorithms on diversified handheld devices will provide advances in fields such as computer vision, mobile computing, and software engineering. This concept is powerful in that it requires no new infrastructure, since it uses popular mobile devices, and existing symbols such as barcode tags, text, and user-customizable icons. The downloadable symbol recognition component will enable many applications. Other than service providers and OEMs, merchants, advertisers, information providers and other service providers are likely partners and customers for our technology. Finally, the technology can be used to help disadvantaged groups (handicapped or visually impaired, for example) get access to product information (prescription drug instructions, for example) or transact commerce activity conveniently, using a device they may already have, or that is easily acquired. These include applications in medical care delivery, military applications, sign recognition for the visually challenged, and others.
