Product background

As people's living quality is improving day by day, the quality of rice is more and more concerned by consumers. At present, the traditional methods of sensory evaluation and manual detection are mostly used to evaluate the quality of rice. However, with the development of science and technology, digital image processing technology can be widely used in the agricultural field. The rice appearance quality detector can automatically analyze and measure the appearance quality indicators such as grain shape, whole grain number, broken rice grain number, chalkiness, transparency and so on with the help of machine vision technology, which makes the detection of rice quality faster and more accurate.

Machine vision technology uses image acquisition equipment such as cameras or cameras and image processing software to work together to replace the human eye for image recognition, size measurement, shape matching, etc. Its advantage is that the measurement equipment does not have subjective factors, No fatigue, consistent and fast measurements every time. The rice appearance quality detector can automatically detect the appearance quality indicators of rice and rice after obtaining the image through the scanner. Testing units, grain distribution enterprises, processing enterprises, etc.

Inspection principle&system parameters

Using the KEYE Rice Appearance Quality Tester, each analysis image, distribution map and result data can be saved, and the analysis results can be output to an Excel sheet. The measurement error of the length and width of the equipment is ≤±0.05mm, the error of the whole milled rice rate is ≤±1.0%, and the precision is high; and the system can manually delete abnormal rice, the data can be automatically updated, and the inspection is more accurate. It can be used for the quality inspection of imported rice In the evaluation, control the rice quality.

Detection method

1. Automatic binarization: Use deep neural network to segment the foreground and background of the image. Compared with the traditional binarization method, it can be applied to a variety of lighting conditions, and the edge segmentation of rice is smoother, fast and robust High advantages.

2. Adhesive rice segmentation algorithm: The method based on connected domains cannot segment the adhered rice. The deep neural network is used to segment the adhered rice at an instance level, which can reach a speed of 1000fps and can process the adhered rice in real time.

3. Rice attribute recognition algorithm: adopts a lightweight neural network and integrates a semi-supervised learning method. The model can be iteratively optimized only by marking a small amount of data. It has the advantages of high accuracy, fast speed, and convenient deployment.

Our advantages