Seed cotton mulching film hyperspectral visual label algorithm for deep learning

Abstract

The invention discloses a seed cotton mulching film hyperspectral visual label algorithm for deep learning, and belongs to the technical field of hyperspectral imaging and deep learning. The method comprises the following steps: analyzing a characteristic spectrum section of a spectrum by utilizing an adjacent alternative algorithm, performing dimensionality reduction on image data by combining adichotomy, generating a hyperspectral pseudo-color image of the seed cotton mulching film, marking the pseudo-color image in a frame selection marking form, and correspondingly generating an image label of a high-dimensional spectrum through two-dimensional image marking. The hyperspectral technology is applied to the field of seed cotton mulching film recognition, for residual transparent mulching films which cannot be recognized by a color camera and a black-white camera, hyperspectral images of the seed cotton mulching films at 1000-2500 nm are collected through a hyperspectral imager, andthen the residual films with different spectral characteristics from seed cotton are recognized and classified.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral imaging and deep learning, and in particular relates to a hyperspectral visual labeling algorithm for seed cotton mulch film for deep learning. Background technique [0002] my country is a big country in cotton production and consumption, and cotton processing and textile play an important role in the national economy. The mulching technology is widely used in cotton planting, and the picking and production of cotton is highly mechanized. During the mechanical picking process, the seed cotton is mixed with a large amount of mulching film. If the cleaning is not thorough, it will enter the lint with the processing link, which will definitely affect the quality of textiles and the production of lint. Dyeing quality of textiles. At present, deep learning is an effective way to solve the mulch debris contained in machine-picked cotton, but deep learning requires a large amount of labeled data,...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the following problems in the existing technology: the recognition of mulch film in mixed seed cotton requires the near-infrared spectrum in the 1000-2500nm band, which is invisible to the human eye, so it is difficult to obtain intuitive perception from the imaging spectrum to distinguish, using the depth Learning to identify spectra requires a large amount of manually labeled data, which is in conflict with the problem that the human eye is difficult to distinguish near-infrared spectra, making it impossible for users to intuitively mark invisible hyperspectral data

Images