一种基于图像融合和深度学习的鲜食玉米外观检测方法

By employing image fusion and deep learning methods, the HPM-GELAN detection model was improved, solving the problem of detecting various defects in the appearance inspection of fresh corn. This resulted in efficient and accurate corn appearance inspection, making it suitable for the processing of fresh corn.

CN120997627BActive Publication Date: 2026-07-17JIANGNAN UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
JIANGNAN UNIV
Filing Date
2025-07-15
Publication Date
2026-07-17

Smart Images

  • Figure CN120997627B_ABST
    Figure CN120997627B_ABST
Patent Text Reader

Abstract

本发明公开了一种基于图像融合和深度学习的鲜食玉米外观检测方法，属于图像识别技术领域。所述方法包括：获取鲜食玉米外观的RGB图像和NIR图像并进行融合；利用HPM‑GELAN检测模型对融合后的图像进行检测，得到鲜食玉米外观检测结果。本发明利用融合图像进行特征提取和外观检测，可以有效地提升网络的整体检测性能；此外，本发明将主干网络中的第一个RepNCSPELAN4模块替换为HAM模块，有效提高了微弱目标的检测精度；进一步引入PConv模块和MSSA模块，可以进一步提升检测精度和检测效率。实验证明，本发明基于图像融合和深度学习的鲜食玉米外观检测方法可以在较少参数的前提下，完成鲜食玉米的外观的高精度检测。
Need to check novelty before this filing date? Find Prior Art