Abstract
Grading of table grapes depends on reliable berry-level phenotyping, yet manual inspection is subjective and slow. A wavelet-guided instance segmentation network named WGMG-Net is introduced for automated assessment of post-harvest grape clusters. A multi-scale feature merging module based on discrete wavelet transform is used to preserve edges under dense occlusion, and a bivariate fusion enhanced attention mechanism is used to strengthen channel and spatial cues. Instance masks are produced for all berries, a regression head estimates the total berry count, and a mask-derived compactness index assigns clusters to three tightness grades. On a Shine Muscat dataset with 252 cluster images acquired on a simulated sorting line, the WGMG-Net variant attains a mean average precision at Intersection over Union (IoU) 0.5 of 98.98 percent and at IoU 0.5 to 0.95 of 87.76 percent, outperforming Mask R-CNN, PointRend and YOLO models with fewer parameters. For berry counting, a mean absolute error of 1.10 berries, root mean square error of 1.48 berries, mean absolute percentage error of 2.82 percent, accuracy within two berries of 92.86 percent and Pearson correlation of 0.986 are achieved. Compactness grading reaches Top-1 accuracy of 98.04 percent and Top-2 accuracy of 100 percent, supporting the use of WGMG-Net for grape quality evaluation.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 10
Claim · model-written summary
WGMG-Net attained mean average precision of 98.98 percent at IoU 0.5.
Verbatim
e0“the WGMG-Net variant attains a mean average precision at Intersection over Union (IoU) 0.5 of 98.98 percent and at IoU 0.5 to 0.95 of 87.76 percent, outperforming Mask R-CNN, PointRend and YOLO models with fewer parameters”
t0“Grape”
Claim · model-written summary
WGMG-Net attained mean average precision of 87.76 percent across IoU 0.5 to 0.95.
Verbatim
e0“the WGMG-Net variant attains a mean average precision at Intersection over Union (IoU) 0.5 of 98.98 percent and at IoU 0.5 to 0.95 of 87.76 percent, outperforming Mask R-CNN, PointRend and YOLO models with fewer parameters”
t0“Grape”
Claim · model-written summary
WGMG-Net used fewer parameters than the compared models.
Verbatim
e0“outperforming Mask R-CNN, PointRend and YOLO models with fewer parameters”
t0“Grape”
Claim · model-written summary
Berry counting had mean absolute error of 1.10 berries.
Verbatim
e0“For berry counting, a mean absolute error of 1.10 berries, root mean square error of 1.48 berries, mean absolute percentage error of 2.82 percent, accuracy within two berries of 92.86 percent and Pearson correlation of 0.986 are achieved.”
t0“Grape”
Claim · model-written summary
Berry counting had root mean square error of 1.48 berries.
Verbatim
e0“root mean square error of 1.48 berries”
t0“Grape”
Claim · model-written summary
Berry counting had mean absolute percentage error of 2.82 percent.
Verbatim
e0“mean absolute percentage error of 2.82 percent”
t0“Grape”
Claim · model-written summary
Berry counting was accurate within two berries for 92.86 percent.
Verbatim
e0“accuracy within two berries of 92.86 percent”
t0“Grape”
Claim · model-written summary
Berry counting achieved Pearson correlation of 0.986.
Verbatim
e0“Pearson correlation of 0.986”
t0“Grape”
Claim · model-written summary
Compactness grading reached Top-1 accuracy of 98.04 percent.
Verbatim
e0“Compactness grading reaches Top-1 accuracy of 98.04 percent and Top-2 accuracy of 100 percent”
t0“Grape”
Claim · model-written summary
Compactness grading reached Top-2 accuracy of 100 percent.
Verbatim
e0“Top-2 accuracy of 100 percent”
t0“Grape”