Optimal training sample selection method for broad band spectrum imaging system

Abstract

The invention discloses an optimal training sample selection method for a broad band spectrum imaging system. The method includes the steps that an actual broad band spectrum imaging system is built, and parameters of the spectrum imaging system are calibrated; a spectrum imaging commonly used sample set is prepared, and spectrum reflectivity of the spectrum imaging commonly used sample set is measured; by means of the actual spectrum imaging system, the sample set is shot, and a digital response value of the sample set is corrected according to the calibration information of the system; the sample set is reconstructed through a pseudo-inverse spectrum reconstruction method, and training samples are selected from the sample set to from a training sample set according to the spectrum error minimization principle; when each training sample is selected to add into the training sample set, all samples in the sample set are traversed once until a spectrum reconstruction error of the training sample set to a main sample set begins to converge to a certain minimum value Jmin, the optimal training sample set is locked, and selection of a board band spectrum imaging optimal training sample is achieved. The method has the technical advantages of remarkably reducing spectrum imaging complexity, improving spectrum construction precision and the like.

Description

technical field [0001] The invention belongs to the technical field of spectral reconstruction in broadband spectral imaging, and in particular relates to an optimal training sample selection method based on minimizing the spectral reconstruction error of a broadband spectral imaging system. Background technique [0002] Spectral imaging technology is currently one of the mainstream digital imaging technologies in the field of color and image science at home and abroad. This technology takes the spectrum as the real color "fingerprint" representation of the surface of the object as the core basis. Through the established spectral imaging system, the spectral data value of the surface of the object is photographed and recorded. The current spectral imaging systems are mainly divided into two categories, one is the narrow-band spectral imaging system, which is composed of a narrow-band filter or a narrow-band light source and a photoelectric recording element; the other is a b...

AI Technical Summary

Problems solved by technology

It should be pointed out that the above training sample selection methods are all based on the feature analysis of the sample set itself. Although the spectral reflectance of all sample sets can be effectively reconstructed, they do not consider and connect the actual spectral imaging system characteristics, resulting in the selected The training sample set is not the optimal training sample set in the actual spectral imaging process

For the above problems, the academic and industrial circles have not yet proposed a method to achieve the optimal training sample selection from the perspective of the characteristics of the actual spectral imaging system

Images