The recognition of off-line unconstrained handwriting is one of the most challenging and interesting problems in Optical Character Recognition (OCR). Although many research have been done in this field for about 40 years, a number of problems are still open to us. In this seminars, an integrated recognition system for off-line unconstrained handwriting is proposed. The proposed system consists of seven main modules: skew angle correction, printed-handwritten text discrimination, line segmentation, slant correction, word segmentation, character segmentation, and character recognition. Except line segmentation and word segmentation resulting from the known algorithms, all other else are new algorithms. Experimental results based on different handwriting databases show the proposed system has different performances, which are from 65.6% to 100%. Finally, the future work in this field will be discussed.