Hyperspectrum-based seed germination rate online-detection apparatus and method thereof

A detection method and germination rate technology, which is applied in the field of hyperspectral technology and agricultural breeding, can solve the problems of not being able to screen out non-germinating seeds, not visually displaying the quality of seeds, failing to detect non-germinating seeds, etc., to improve the level of automation , reliability and reproducible results

CN103636315BActive Publication Date: 2015-03-11SOUTH CHINA UNIV OF TECH
4 Cites 3 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2015-03-11

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a hyperspectrum-based seed germination rate online-detection method. The method comprises the following steps: 1, carrying out hyperspectral image acquisition of seed training samples, and extracting the characteristic parameters of the hyperspectral images of the seed training samples under a characteristic wave band; 2, testing the seed training samples by utilizing a traditional process to obtain a germination result of the seed training samples; 3, establishing a hyperspectrum-based seed germination rate predication model with the characteristic parameters and spectral reflection values of the hyperspectral images of the seed training samples under the characteristic wave band as input and the seed germination result as output; and 4, carrying out hyperspectral image acquisition of seeds for detection, and utilizing the seed germination rate predication model to detect in order to obtain the germination rate of the seeds for detection. The invention also discloses a hyperspectrum-based seed germination rate online-detection apparatus. The simple, rapid, lossless and real time detection of the germination rate of seeds is realized in the invention.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the fields of hyperspectral technology and agricultural breeding, in particular to a hyperspectral-based on-line detection device and method for seed germination rate. Background technique

[0002] Seeds, as the most basic means of production in agricultural production, are an important factor to ensure a good harvest in agriculture. At present, China's annual seed demand is 12.5 billion kg, the actual seed supply is 4.5 billion kg, and the seed commodity rate is only 36%. The seed industry market has a lot of room for development. Seed inspection is the key to ensure the quality of seeds, and the seed germination rate is the most important index in seed inspection. The loss of production due to the problem of seed germination rate is very serious every year. Therefore, it is very important to do a good job in the detection of seed germination rate.

[0003] The seed germination rate refers to the percentage of the number of ...

Examples

Embodiment

[0034] Such as figure 1 As shown, a hyperspectral-based online detection device for seed germination rate includes a loader 1, a hyperspectral imaging recognition system and automatic seed grading components;

[0035] Described seed automatic grading part comprises conveyor chain 10, a plurality of grading hoppers 9, a grading actuator 13, a cylinder 12, a seed slideway 11, the germinateable seed collection box 14 that is positioned at the delivery chain output end and can't germinate seed collection Box 15; the conveyor chain 10 is connected with a sprocket, a hopper shaft, a gear and a motor, and the grading hopper 9 is evenly mounted on the conveyor chain 10 through the hopper shaft, and the sprocket rotates, and the grading hopper 9 can follow the conveyor chain 10 to Front movement; the seed slideway 11 is a circular groove, supported by a bearing and a cylinder 12, and is located at the output end of the conveyor chain. When the seeds can germinate, the slideway 11 is in...