Image binaryzation method and device

Abstract

The invention discloses an image binaryzation method and a device, belonging to the field of image processing and optical character recognition. The method comprises the following steps as follows: dividing an image to be processed into image blocks, implementing edge detection, and calculating the number of edge pixel points in each of the image blocks; marking the binaryzation attribute of each image block according to the number of edge pixel points; calculating the binaryzation information of a prospect image block, screening the prospect image block of which the binaryzation threshold value needs to be adjusted; subjecting the prospect image of which the binaryzation threshold value needs to be adjusted to binaryzation threshold value adjustment; binarizing the prospect image of which the binaryzation threshold value needs to be adjusted, and binarizing the rest image blocks to obtain a binary image of the image to be processed. The image binaryzation method and the device have the advantages that the effect of binarization processing by means of the method provided by the invention under the condition of uneven image brightness is good by dividing the image to be processed to carry out binarization processing and adjusting the binaryzation threshold value of the prospect image block influenced by uneven brightness, and the time performance of the method is greatly superior to that of the local binaryzation method.

Description

technical field [0001] The invention belongs to the field of image processing and optical character recognition, and relates to an image binarization method and device. Background technique [0002] Image binarization is an important step in optical character recognition. Usually, the image binarization process is as follows: firstly, a threshold plane is calculated for the image to be processed, and then each pixel in the image to be processed is subjected to binary segmentation according to the threshold plane. There are many methods for calculating the binarization threshold, among which there are two main ones: Otsu method and NiBlack method. The Otsu method is a global image processing method. This method divides all pixels into binary values, and the calculation speed is fast. It can obtain good results when the brightness of the image to be processed is uniform, but the brightness of the image to be processed When the distribution is uneven, binary segmentation works...

AI Technical Summary

Problems solved by technology

However, the position of the light source in the scanning pen is fixed. When the scanning pen scans at different inclination angles, the brightness distribution in the frame image obtained is not uniform. When the contrast between characters and background in the scanned medium is weak or scanned This non-uniformity of brightness distribution will be more serious when the brightness of the medium is darker

At this time, if a global binarization method is used, such as the Otsu method, the inhomogeneity of the brightness distribution will make the binarization effect poor; if a local binarization method that is calculated pixel by pixel is used, such as the NiBlack method, the calculation The amount is too large, which is not suitable for the scanning pen's requirements for image binarization processing speed

Images