A free-fall fruit and vegetable sorting method and system based on deep learning

Abstract

A deep learning-based free-fall fruit and vegetable sorting method and system belong to the field of fruit and vegetable sorting. The electrical control box is installed on the outside of the equipment shell, the display touch device is installed on the front side of the equipment shell, the bucket is installed obliquely below the feed inlet, the straight vibrator is installed at the bottom of the bucket, the chute is connected to the bucket, and the material arrangement curtain The first nozzle array is connected to the high-frequency solenoid valve array, the second nozzle array is connected to the high-frequency electromagnetic valve array, and the second blanking plate is arranged between the first and second nozzle arrays. On the opposite side of the frame, the first and second image acquisition boxes are installed at the front and rear ends of the frame, the two color line scan cameras are installed in the first and second image acquisition boxes, and the first light source box and the first light source background box are at an angle to each other It is located on the right side of the chute, and the second light source box and the second light source background box are located on the left side of the chute at an angle to each other. The invention can greatly improve the detection speed of fruits and vegetables, has a sorting function, has high rejection precision and low maintenance cost.

Description

technical field [0001] The invention belongs to the field of fruit and vegetable sorting, and in particular relates to a deep learning-based free-fall fruit and vegetable sorting method and system. Background technique [0002] At present, the fruit and vegetable sorting industry mainly relies on manual sorting, with low automation level, low efficiency, and high human resource costs. For small particles such as wolfberry, the color sorting technology is used to check for defects by color, which has been mature and widely used. However, for varieties such as dried red dates and tomatoes, it still remains at the stage of manual selection, which involves quality judgment and complex defects rather than simple color and size recognition. [0003] In terms of detection algorithms, conventional image processing algorithms are commonly used in fruit and vegetable sorting at present, mainly through color, edge detection and other technologies to detect the color size and obvious d...

AI Technical Summary

Problems solved by technology

The detection object is small, and the area detection algorithm is used, and the rejection accuracy is poor

Images