Automatic identification method for milled rice

Abstract

The invention discloses a method for automatic identification of polished rice, comprising: placing a rice sample in an image collector to collect original image information; reading the original image information, storing the coordinates of each point on the individual contour of the rice sample, and obtaining The geometric mean of the coordinates of these points is used as the center point of the rice sample individual; the connection line between the center point and the contour point is used as the radius of the rice grain; with the longest radius as the reference direction, a radius is stored every 5 degrees counterclockwise, stored in In the counterclockwise radius table; calculate a standard meter according to the data stored in the rice grain radius table; carry out the judgment of the polished rice: distinguish each rice sample in the bitmap file respectively, if the grain length is greater than or equal to 73% of the standard rice grain length, it is regarded as the polished rice Selected; if the grain length is less than 73% of the standard grain length, it is regarded as untreated rice. The method of the invention can quickly, objectively and correctly identify the whole polished rice in the polished rice, and meets the requirements of fast, objective and high accuracy quality detection in the on-site purchase of rice and market transactions.

Description

technical field [0001] The invention relates to a detection method based on computer fuzzy identification. In particular, it relates to a method for automatic identification of whole milled rice, which is a detection method based on computer fuzzy identification. It belongs to the field of computer fuzzy recognition. Background technique [0002] The rate of whole milled rice is an important indicator for evaluating the quality of rice. In the GB / T 17891-1999 "Quality Rice" standard implemented in my country in 2000, this parameter was added as one of the indicators for evaluating the grade of rice. The so-called whole milled rice refers to the rice grains whose length is more than four-fifths (including four-fifths) of the average length of the whole milled rice grains when the brown rice is milled into first-class rice with an accuracy of the national standard. The percentage of whole milled rice in the net rice sample mass is the whole milled rice rate. It can be seen ...

AI Technical Summary

Problems solved by technology

Due to defects such as long detection time, strong subjectivity, low accuracy, poor operability and repeatability, this method is difficult to meet the requirements of rapid, objective and high-accuracy quality detection in on-site rice purchases and market transactions.

Images