Adaptive thresholding methods for documents image binarization

摘要: Binarization process is easy when applying simple thresholding method onto good quality image. However, this task becomes difficult it deals with degraded Most current binarization methods involve complex algorithm and less ability to recover important information from a degradation We introduce an adaptive overcome the state of art. This also aims solve problem low contrast images thin pen stroke problems. It can enhance effectiveness solving all other As well as, does not need specify values factors manually. compare proposed known methods, which are Niblack, Sauvola, NICK methods. The results show that gave higher performance than previous