Apple grading identification method based on deep learning

Abstract

The invention discloses an apple grading identification method based on deep learning. The method comprises the following steps: step 1, constructing an apple training data set: 1, crawling apple image data; 2, preprocessing images; step 2, detecting apple targets: 1, selecting an apple graph in the apple data set constructed in the step 1 as test data, and performing data training by using a Darknet framework; step 2, after training is completed, shooting apple photos by using a mobile phone, detecting apple positions of images, and labeling the positions step 3, detecting apple surface defects: taking single apple photos after screenshot as input images, independently extracting each positioned apple, and positioning the four surface defects; and step 4, grading and identifying apples. Compared with the prior art, the invention has the following advantages: 1, the weight is lighter; 2, the expansibility is high; and 3, the life requirements are better met.

Description

technical field [0001] The invention relates to a method for grading and identifying apples. Background technique [0002] Such as figure 1 As shown, the defect forms of apples mainly include insect eyes, apple skin scratches, apple skin cracks, and rot, among which: insect eyes are small defect points on apples, with relatively dark colors, distributed on the surface of apples in the form of discrete points; Scratches are elongated defect areas that are relatively light in color and have little difference from the color texture of the apple surface; cracks in the apple skin are large areas of damage on the apple surface, and the color may be relatively dark or relatively light, which is manifested as Large-area damage on the surface of the apple; rot is a large-area surface damage, and due to corruption, the rotten area on the apple surface is also a deep and large-area damage. [0003] Because Apple’s sales method is stacked sales, the various targets will be relatively ...

AI Technical Summary

Problems solved by technology

[0007] (1) The font color of the target labeling scheme is lighter, and the difference with the target background is small, and it is not easy for the human eye to observe directly

[0008] (2) In the two apples below the figure, the labeling positions of the two targets are too close to effectively distinguish the relationship between the target and the labeling

[0009] (3) If the label font is too large, it will block the useful information of the target itself, making it more confusing visually

Images