TEXT LINE DETECTION IN IMAGES

摘要

Techniques for detecting and recognizing text may be provided. For example, an image may be analyzed to detect and recognize text therein. The analysis may involve detecting text components in the image. For example, multiple color spaces and multiple-stage filtering may be applied to detect the text components. Further, the analysis may involve extracting text lines based on the text components. For example, global information about the text components can be analyzed to generate best-fitting text lines. The analysis may also involve pruning and splitting the text lines to generate bounding boxes around groups of text components. Text recognition may be applied to the bounding boxes to recognize text therein.

主权项

1. A computer-implemented method comprising:
detecting, by a processor, text components in an image, each of the text components comprising a different respective portion of the image identified as likely containing text; generating, by the processor, lines between pairs of the text components; matching, by the processor, a first line of the lines with a set of the text components based on features of the text components of the set; and recognizing, by the processor, text from the set of the text components.