Niblack Algorithm Modification Using Maximum-Minimum (Max-Min) Intensity Approaches on Low Contrast Document Images

In recent decades, detection or segmentation has been one of the major interesting research subjects due to the analysis of the information. However, most of the historical document has degraded and low contrast problem. Recently, many binarization methods were proposed in order to segment the text region from the background region in the low-quality image. In this paper, an improved binarization method was inspired by Niblack method was presented. The modification focuses to find the optimum threshold value by using the Maximum-Minimum intensity technique. The main target is to reduce the unwanted detection image and increase the resultant performance compared to the original Niblack method. The proposed method was applied to the document images from H-DIBCO 2012 and H-DIBCO 2014 dataset. The results of the numerical simulation indicate that the target was achieved by the F-Measure by F-measure (58.706), PSNR (10.778) and Accuracy (86.876). This finding will give a new benchmark to other researchers to propose an advance binarization method.