Adaptive separation method of lean meat and fat meat based on hyperspectral image of Cantonese sausage

Abstract

A method for self-adaptive separation of lean meat and fat meat based on hyperspectral images of Cantonese-style sausages. The invention relates to the technical field of non-destructive detection of sausage quality. The invention provides a method for detecting the distribution of lean meat and fat meat based on near-infrared hyperspectral images of sausages The method solves the problems that after the fat meat and the lean meat in the bacon are mixed, the two cannot be distinguished simply and effectively, and the respective proportions of the lean meat and the fat meat in the sausage are difficult to be calculated. Using hyperspectral images for sausage detection can quickly and effectively obtain sample information and achieve real-time detection and judgment. Compared with the prior art, the beneficial effects of the present invention are: the present invention realizes the method of self-adaptive separation of lean meat and fat meat based on the hyperspectral image of Cantonese-style sausage, and does not need to be measured by chemical methods, which greatly simplifies the operation steps , which shortens the detection time, and K-means adaptive segmentation also avoids the consequences of inaccurate measurement results caused by artificial subjective factors.

Description

technical field [0001] The invention relates to the technical field of non-destructive detection of sausage quality, in particular to a method for detecting the distribution of lean meat and fat meat based on near-infrared hyperspectral images of sausages. Background technique [0002] Sausage (Sausage), commonly known as sausage, refers to the Chinese characteristic meat products made of meat as raw material, cut into cubes, mixed with auxiliary materials, poured into animal casings, fermented, matured and dried. It is the most diverse meat product in China. A large category of products. [0003] According to the new "Sanitary Standards for Cured Meat Products" implemented on October 1, 2005, Cantonese-style sausages are divided into excellent grades, first grades and second grades. At present, the quality identification and grading of Cantonese-style sausage mainly adopts the empirical sensory evaluation method, that is, the sampling method is used, and experienced sausag...

AI Technical Summary

Problems solved by technology

[0005] The invention provides a method for detecting the distribution of lean meat and fat meat based on near-infrared hyperspectral images of sausages, which solves the problem of the inability to simply and effectively distinguish the two after mixing fat meat and lean meat in bacon, and the difficulty in calculating the lean meat in sausages. and the proportion of fat

Images