If you drive through a toll booth or leave a gas station without paying, a camera takes a picture of your license plate and you receive a ticket. Search engines require someone to enter key words associated with images to “find” them, but shouldn’t we be able to programmatically “label” an image by text it contains (like a license plate)?
Project Developer: Hanna Strohm
Project Description: Write an optical character recognition application that identifies and recognizes printed text within an image
General Description and Requirements: 1.Investigate existing algorithms and libraries. 2.Initially, try black text on a white background. 3.Design a uniform API so that you can plug in alternative OCR functions. 4.Evaluate the effectiveness of your OCR compared to existing algorithms. 5.Develop an application that employs augmented reality for text within an image (e.g geo-tag state park signs, license plates, campus building signs, ..) CS460: Capstone Experience Project Definition 2019 Pankratz/McVey