Entropy method for filter defect characteristic parameter selection

Abstract

The invention discloses an entropy method for filter defect characteristic parameter selection, which comprises the steps of segmenting a bounding rectangle containing defects from defective filter images to form defects ROI; setting elements of a candidate characteristic set F and setting a selected characteristic set S as an empty set; calculating the characteristic values of the defects ROI and constructing a sample set; calculating normalized mutual information SU (fifk, C) of candidate characteristic fifk and class C; selecting a first element s1 of the S according to the maximum of SU (fifk, C); removing characteristics which are selected in the S from the candidate characteristic set F and the candidate characteristics with normalized mutual information SU (fifk, C) which is smaller than a threshold; calculating the value of an evaluation function J (fifk, C, S) of each candidate characteristic fifk in the candidate characteristic set F; selecting a next element of the selected characteristic set S according to the maximum of the evaluation function J (fifk, C, S); removing the characteristics which are selected in the S from the candidate characteristic F and the candidate characteristics with the evaluation function J (fifk, C, S) which is smaller than a threshold; judging whether the candidate characteristic set F is an empty set or not; outputting the selected characteristics.

Description

technical field [0001] The invention relates to the technical field of visual recognition of optical filter defects, in particular to a method for selecting characteristic parameters of optical filter defects using the principle of entropy. Background technique [0002] Optical thin film filters are widely used in optical communications, laser technology, optical imaging and detection, and play an important role in micro cameras, biomedical instruments, and advanced laser systems. For example, in the field of optical communication, optical filters are not only the key components for multiplexing and demultiplexing in wavelength division multiplexing systems, but also commonly used in gain flattening of erbium-doped fiber amplifiers, all-optical up and down channels, and wavelength switches. In optoelectronic products, each mobile phone camera must be equipped with a filter. There is a huge demand for optical filters in the domestic and international markets, and the domesti...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the above-mentioned technical problems, the object of the present invention is to provide a kind of entropy method of filter defect feature parameter selection, this method considers the situation that some features have poor distinguishing ability when acting alone and strong distinguishing ability when combined with other features, According to the correlation between candidate features and defect categories, and the amount of new information provided by candidate features for defect classification, an evaluation function for judging the importance of candidate features is designed. Selection of Characteristic Parameters of Optical Sheet Defects

Images