Fusion of fruit image processing and deep learning: a study on identification of citrus ripeness based on R-LBP algorithm and YOLO-CIT model

Abstract

Citrus fruits are extensively cultivated fruits with high nutritional value. The identification of distinct ripeness stages in citrus fruits plays a crucial role in guiding the planning of harvesting paths for citrus-picking robots and facilitating yield estimations in orchards. However, challenges arise in the identification of citrus fruit ripeness due to the similarity in color between green unripe citrus fruits and tree leaves, leading to an omission in identification. Additionally, the resemblance between partially ripe, orange-green interspersed fruits and fully ripe fruits poses a risk of misidentification, further complicating the identification of citrus fruit ripeness. This study proposed the YOLO-CIT (You Only Look Once-Citrus) model and integrated an innovative R-LBP (Roughness-Local Binary Pattern) method to accurately identify citrus fruits at distinct ripeness stages. The R-LBP algorithm, an extension of the LBP algorithm, enhances the texture features of citrus fruits at distinct ripeness stages by calculating the coefficient of variation in grayscale values of pixels within a certain range in different directions around the target pixel. The C3 model embedded by the CBAM (Convolutional Block Attention Module) replaced the original backbone network of the YOLOv5s model to form the backbone of the YOLO-CIT model. Instead of traditional convolution, Ghostconv is utilized by the neck network of the YOLO-CIT model. The fruit segment of citrus in the original citrus images processed by the R-LBP algorithm is combined with the background segment of the citrus images after grayscale processing to construct synthetic images, which are subsequently added to the training dataset. The experiment showed that the R-LBP algorithm is capable of amplifying the texture features among citrus fruits at distinct ripeness stages. The YOLO-CIT model combined with the R-LBP algorithm has a Precision of 88.13%, a Recall of 93.16%, an F1 score of 90.89, a mAP@0.5 of 85.88%, and 6.1ms of average detection speed for citrus fruit ripeness identification in complex environments. The model demonstrates the capability to accurately and swiftly identify citrus fruits at distinct ripeness stages in real-world environments, effectively guiding the determination of picking targets and path planning for harvesting robots.

Keywords: LBP feature; citrus; deep learning; image processing; ripeness identification.

Figure 1

Calculation process for peel roughness of citrus fruits.

Figure 2

Peel roughness of citrus fruits with distinct ripeness stages.

Figure 3

R-LBP algorithm process.

Figure 4

Sample image of initial dataset: (A) Medium distance exposure citrus image; (B) Medium range natural light citrus image; (C) Medium distance backlight citrus image; (D) Close range exposure citrus image; (E) Close range natural light citrus image; (F) Close range backlight citrus image.

Figure 5

Image synthesis process.

Figure 6

Sample image of additional dataset: (A) Grayscale citrus image; (B) Synthetic citrus images based on LBP; (C) Synthetic citrus images based on R-LBP.

Figure 7

C3+CBAM module calculation process.

Figure 8

Ghostconv module calculation process.

Figure 9

YOLO-CIT Network Architecture.

Figure 10

(A–D) Different ripening stages of citrus fruits.

Figure 11

Citrus fruit epidermal roughness difference across ripening stages.

Figure 12

Change in YOLO-CIT model’s mAP@0.5 trained on different datasets.

Figure 13

Variation of mAP@0.5 during training across different models.

Figure 14

Detection time and mAP@0.5 across various models.

Figure 15

YOLO-CIT model: citrus ripeness identification in varied environments: (A, B) Backlight environment; (C, D) Exposure environment; (E, F) The situation where leaves cover the fruit; (G, H) The dense distribution of citrus fruits.