AI Visual Sorting System Grain Quality Analyzer For Corn Kernels

Detection technics

KVS-G series grain quality analyzer is composed of visual system, software system and other module structures. When the grain enters the field of view of the camera, two high-resolution cameras take pictures of the front and back of the grain. Through the registration algorithm, the front and back grain images are Perform one-to-one registration to obtain the characteristics of a complete grain, and then use an algorithm to segment the grain in the image, and finally use an artificial intelligence algorithm to identify the attributes of the segmented grain to determine whether there are disease spots, mildew, germination, breakage, insect erosion, etc.

Application Background

1. In the process of manual inspection, the inspection personnel have a large deviation in the implementation of the standard, and the management is difficult
2. In the manual inspection process, there are subjective differences in the inspection standards of different inspectors, and the consistency is low.
3. The process of manual inspection cannot be accurately recorded, and the traceability is low
4. In the process of manual inspection, long-term work will lead to visual fatigue of inspectors, and false inspections and missed inspections are prone to occur

Inspection principle

The corn on-line quality analyzer developed and produced by our company is connected to the flour processing production line, connected to the corn lifting and conveying pipeline, and regularly extracts the corn from the conveying pipeline to analyze the quality of the corn. Different kinds of buds, grass seeds, worm-eaten grains, Gibberella grains, damaged grains, black germs, impurities, etc. are tested and analyzed, and statistical reports are formed from time to time to improve product safety and traceability.

When it is detected that the quality of the sampled corn is not good, the operators of the production line can adjust the parameters of the corn sorting machine on the production line in time to ensure the quality of the flour produced. The tested corn can be automatically sent back to the flour processing line through the pipeline, and the grains are returned to the warehouse without wasting a grain of grain.

Equipment advantages&details

1)AI algorithm:Accurately locate grain attributes, classify and weigh grains;

2)Easy to operate:Complete the test within 3 minutes, and meet the requirements of the number of samples in the national standard, which is simple and easy to operate

Core technology

1. Automatic binarization: use deep neural network to segment the foreground and background of the image, smoothly segment the grain edge, and accurately locate the grain to be analyzed.

2. Adhesion material segmentation algorithm: deep neural network segments the adhering grains to form independent and complete grains, which are analyzed and classified.

3. Multi-attribute recognition: It adopts a lightweight neural network and integrates a semi-supervised multi-attribute learning method. The user can label a small number of samples of the grain to be analyzed, and then the data model can be updated to perform fast and high-precision analysis of the grain.

Our advantages