Traditional Chinese medicinal material stir-frying process monitoring device and traditional Chinese medicinal material stir-frying judgment method
A technology of process monitoring and traditional Chinese medicinal materials, applied in neural learning methods, television, biological neural network models, etc., can solve the problems of difficult, inaccurate, time-consuming and labor-intensive judgments of fried medicinal materials, achieve real-time monitoring of the degree of frying, and improve The effect of production efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0021] Embodiment 1: the following combination figure 1 with figure 2 To illustrate this embodiment, this embodiment relates to a monitoring device for the frying process of Chinese herbal medicines, including a camera 1, a computer and a bracket 2;
[0022] The camera 1 is connected to the USB interface on the host computer through a data cable, and the camera 1 is set on the bracket 2 .
[0023] In order to be able to adjust the shooting position of the camera 1, a guide rail 3 is horizontally arranged on the support 2, a slide block is slidably arranged on the guide rail 3, and a connecting part 4 is rotated on the slide block, and the connecting part 4 rotates in the vertical direction, and the connecting part 4 is provided with video camera 1. The position of the camera 1 is adjusted through the lateral adjustment of the connecting part 4, so that the camera lens corresponds to the traditional Chinese medicinal material frying machine.
[0024] Optionally, the camera ...
Embodiment 2
[0028] Embodiment 2: This embodiment relates to a method for judging the frying of Chinese herbal medicines, comprising the following steps:
[0029] S1. Obtain several images of roasted Chinese medicinal materials through the camera 1: from the beginning of the roasting of the medicinal materials to the end of the roasting, images of different degrees of roasting are obtained to train the machine so that it can accurately detect the medicinal materials of different roasting degrees. Identification; optionally, at least 10,000 images of Chinese herbal medicines;
[0030] S2, use the labelme open source software to label the image;
[0031] S3. Input the marked images into the cascade maskrcnn network architecture for training to generate a regression model; optionally, the marked images are grouped in groups of 100;
[0032] S4. Input multiple images to the regression model during the frying process, set the value of the cooked Chinese medicinal materials, and judge the degre...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More