General quality detection method of block average resolution combination without reference underwater images

Abstract

The invention discloses a method for universally detecting the quality of non-reference underwater images on the basis of a combination of block average definition. The method includes setting the quality Q of an underwater image I; setting a value of the quality Q as a weight of the contract and the average brightness of the underwater image if objects do not exist on the underwater image; determining that the objects exist on the image if the total amount of detected edges in the image is larger than a threshold value Edge_threshold<1>, selecting image blocks with detection significance if the quantities of edge pixels in the image blocks P are larger than a threshold value Edge_threshold<2>, and setting the value of the quality Q as the weighted sum of an average definition value, the contract and the average brightness of the image blocks. The objects are contained in the image and are clear along with increase of the value of the quality Q, and are not contained in the image or are blurred along with decrease of the value of the quality Q. The method has the advantages that quality detection values of all the underwater optical visual grayscale images can be provided by the method and are good in consistency with subjective judgment, and the problem that an existing method for evaluating the quality of partial underwater images only can be used for evaluating the underwater images of objects can be solved.

Description

technical field

[0001] The invention belongs to the technical field of image processing and analysis, in particular to the processing and analysis of images taken in environments with absorption and scattering optical attenuation, such as underwater environments. The invention relates to the quality detection of underwater images, in particular to a generalized block-average underwater image quality detection method based on contrast and sharpness. Background technique

[0002] The research of image quality objective evaluation algorithm is a very basic scientific problem in the field of image processing and image analysis. People hope to find a reliable and reasonable method for objective evaluation of image quality, which can approach the evaluation results of human visual system. In water, the speed of light is less affected by changes in temperature and salinity, the detection direction is good, and the positioning is more accurate. Target. Typical underwater visual i...

Images