Simultaneous detection of surface defects and prediction of internal SSC of kumquats based on hyperspectral imaging technology

Xiong Li

doi:10.1016/j.infrared.2025.106321

Simultaneous detection of surface defects and prediction of internal SSC of kumquats based on hyperspectral imaging technology

2025-12-21

0

PRE

AI

X

Xiong Li *

X

Xinlin Xiong

Y

Yawen Guo

W

Wenwei Wang

B

Bojin Yang

X

Xiangguo He

Y

Yande Liu *

DOI：10.1016/j.infrared.2025.106321

Original

Original request for help

Save

Abstract

En 中文

• This study explores the feasibility of using HSI combined with 2D-COS and image segmentation enables simultaneous defect and internal quality detection in kumquats. • An improved morphological-Canny segmentation (IMS) algorithm is developed for superior defect detection accuracy. • Based on the key wavelengths identified through the integrated CARS-UVE-SPA algorithm, quantitative models (LS-SVM and PLS) were developed for predicting soluble solid content in normal kumquats. • The LS-SVM model optimized with the SG + StandardScaler pre-processing method showed the best predictive performance on the prediction set.

Simultaneous detection of surface defects and prediction of internal SSC of kumquats based on hyperspectral imaging technology

Abstract

Journal

Organization

Cited Papers

Citing Papers