LAUSR

BACKGROUND Fast identification of damaged soybean seeds has undeniable importance in seed sorting and food quality. Mechanical vibration is generally used in soybean seed sorting, which will seriously damage soybean seeds. Convolutional Neural Network (CNN) has been considered to be an effective method for location and segmentation tasks. However, CNN requires a large amount of ground truth data and high computational cost. RESULTS First, we propose a self-supervision manner to automatically generate ground truths, which can theoretically create an almost unlimited number of labeled images. Second, instead of using popular CNNs, a novel invertible convolution (involution) enabled scheme is proposed by using the bottleneck block of the residual networks. Third, a Feature Selection Feature Pyramid Network (FS-FPN) based on involution is designed, which selects features more flexible and adaptive. We further merge involution-based backbones and FS-FPN into a unified network, achieving an end-to-end seed location and segmentation model, the best mean average precision (mAP) of location and segmentation achieve 85.1% and 81%. CONCLUSION Experimental results demonstrate that the proposed method greatly improves the performance of the baseline network with faster speed and fewer parameters, making it available to detect the soybean seeds more effectively. This article is protected by copyright. All rights reserved.