Two-stage binary image processing method

Abstract

The invention discloses a two-stage binarization method for inhibiting excessive segmentation of an image target object. The method at least comprises the following steps: obtaining a binarization image A of a gray level image and an intermediate image with a strong signal removed; performing binarization processing on the intermediate image to obtain a binarized image B; and superposing the binarized image A and the binarized image B to complete image processing. According to the method, binarization processing is carried out on the original grayscale image, so that a strong signal of the original grayscale image is reserved; the strong signal is removed from the original grayscale image, a weak signal is retained, and the weak signal is further amplified; and the two processing results are superposed to complete image processing. The foreground target object and the background of the image are effectively separated, the integrity of the target object in the image is ensured, the target object in the image is prevented from being excessively separated, and the efficiency and the accuracy of subsequent image recognition work are greatly improved.

Description

technical field [0001] The application relates to a two-stage binary image processing method, which belongs to the field of image processing. Background technique [0002] In recent years, image recognition technology has been widely used in various fields. As a process of recognizing or detecting objects or attributes in digital images, image binarization is the core step of the entire image recognition. Under complex environmental imaging conditions, the quality of the image is poor, the contrast is low, and the content of background impurities is high, which leads to the inability of the traditional binarization process to effectively separate the foreground object from the image background. The most common and important problem It is the problem that the target object of the image is over-segmented, which seriously affects the subsequent efficiency and accuracy of the entire image recognition process. [0003] Taking the identification of underwater plankton as an examp...

AI Technical Summary

Problems solved by technology

The main reason is that the binary processing of the in-situ image is difficult. On the one hand, when the turbidity of the water body is high, the gray value of the image is too low and the contrast is poor; on the other hand, the main body of plankton as the target is mostly In the semi-transparent state, its gray scale distribution range is wide, which causes the weaker signal in the target object to be suppressed by the strong signal in the binarization process, and the main part of the target object is discontinuous, resulting in subsequent image over-segmentation, image feature extraction information Not accurate enough, affecting the final classification results

Images