Method, device, equipment and storage medium for detecting fruit deformity

Abstract

This application discloses a method, apparatus, equipment, and storage medium for detecting fruit deformities. The method includes: identifying a preset posture image of a fruit in a preset posture from multiple acquired fruit images; performing image segmentation processing on the preset posture image to obtain a contour image containing the contour lines of the fruit in the preset posture image; when the preset posture corresponding to the fruit contour image is a first preset posture, extracting feature values ​​from the fruit contour image and inputting them into a deformity detection model for that preset posture to output a deformity detection result; when the preset posture corresponding to the fruit contour image is a second preset posture, outputting a deformity detection result based on the straight line fitting result of the fruit contour lines in the fruit contour image. The advantage of this application is that it provides a method, apparatus, equipment, and storage medium for efficient and intelligent fruit deformity detection that can be applied to fruit production lines.

Images