A two-step framework for text line segmentation in historical Arabic and Latin document images

A robust and efficient algorithm for Chinese historical document analysis and recognition

“…One efficient way is to develop a document digitization system, which requires accurate historical document recognition and understanding. With the rapid development of optical character recognition techniques, historical document understanding has made great progress [ 1 , 2 ] and several benchmarks have been established [ 3–5 ]. Nevertheless, real-world scenarios present several challenging artifacts [ 6 ], such as substantial variations in page layouts, image degradation, as well as diversity in text fonts and scales, which have seldom been taken into account in the current benchmarks.…”