Non-reference definition evaluating method and system for full-slice image

Abstract

The invention provides a non-reference definition evaluating method and a non-reference definition evaluating system for a full-slice image. The non-reference definition evaluating method comprises the steps of: adopting a pyramid multi-layer data structure for storing digital images, and segmenting the images in each layer of the pyramid multi-layer data structure into a plurality of image blocks evenly; dividing a strong edge in a gradient amplitude histogram of the image blocks by adopting an Otsu threshold segmentation method, calculating to obtain strong edge intensity according to a gradient maximum value and width of the strong edge, correcting the strong edge intensity by utilizing background complexity, and determining definition of each single image block; setting a standard value of the definition, and determining whether a current image block is a clear image or a blurred image; and finally determining whether the images in each layer are clear images or not according to proportions of clear image blocks in each layer. The non-reference definition evaluating method and the non-reference definition evaluating system avoid the image definition score differences caused by image content differences, correct the influence of the image background complexity on the image definition, and realizes effective identification of the image which is partially clear and partially blurred.

Description

technical field [0001] The present invention relates to the technical field of digital image processing, in particular to a reference-free definition evaluation method and system for full-slice images. Background technique [0002] With the development of information technology, digital full-section pathological images have been widely used in the fields of clinical diagnosis and pathological research. Due to various uncertain factors in the process of slice making and microscopic scanning, the imaging quality of pathological slices is likely to decline. The decrease in image clarity not only directly affects the diagnostic quality of pathological slides, but also cannot be used as an important sample for intelligent diagnostic research such as data mining. Therefore, a fast and effective digital pathology image sharpness assessment method is crucial for the development of digital pathology. [0003] According to the degree of dependence on reference images, objective eval...

AI Technical Summary

Problems solved by technology

At present, the following deficiencies generally exist in the practical application of digital pathology image sharpness evaluation methods: 1) The sharpness is seriously affected by the image content. Under the same sharpness, images with complex content

Images