An Efficient Algorithm for Segmenting Warped Text-Lines in Document Images

Warped text-lines often appear whenever one performs the digitalization of bound documents using flatbed scanners or digital cameras. Compensating such distortion is an important pre-processing step in document transcription via OCR, for instance. This paper presents an efficient algorithm for text-line segmentation for document images. A typographic study and parameter tuning are done yielding into high values for precision, recall and f-measure metrics. The method presented outperforms the competing algorithms using a public available dataset.