Due to a noticeable expansion of document recognition applicability, there is a high demand for recognition on mobiledevices. A mobile camera, unlike a scanner, cannot always ensure the absence of various image distortions, therefore thetask of improving the recognition precision is relevant. The advantage of mobile devices over scanners is the ability to usevideo stream input, which allows to get multiple images of a recognized document. Despite this, not enough attention iscurrently paid to the issue of combining recognition results obtained from different frames when using video stream input.In this paper we propose a weighted text string recognition results combination method and weighting criteria, and provideexperimental data for verifying their validity and effectiveness. Based on the obtained results, it is concluded that the useof such weighted combination is appropriate for improving the quality of the video stream recognition result.
展开▼