Nondestructive Classification of Potatoes Based on HSI and Clustering

A rapid classification method of potatoes based on the combination of hyperspectral imaging(HSI) technology and integrated learning algorithm was proposed in this paper. Here, potatoes were divided into six types: intact ones, green skin, germination, dry rot, wormhole and damage. Firstly, visible-near infrared (VNIR) hyperspectral imaging system with the band range of 400-1000nm was used to collect the potato hyperspectral image information in the experiment. Further, after the image masked, K-means clustering method was used to segmentate images. Extract the average spectrum of the defect areas and the intact areas as the classification data set. Based on the traditional machine learning algorithm (support vector machine, decision tree) and the integrated learning algorithm (random forest, gradient promotion decision tree), the classification model of potato defects was established and compared. The results show that among all classification algorithms, the classification accuracy of potato defects can be significantly improved by using the decision tree of gradient lifting. By comparing the feature importance of each band, the model accuracy was maintained above 80%. Furthermore, in order to improve the discrimination ability of data and reduce the dimension of data, linear discrimination analysis method was used to process spectral data, and the accuracy of the established model was finally improved to 84.62%.

[1]  Vikram Chalana,et al.  PC‐based machine vision system for real‐time computer‐aided potato inspection , 1998 .

[2]  Xiaoming Huang,et al.  Combustion mechanism of asphalt binder with TG–MS technique based on components separation , 2015 .

[3]  Arno Formella,et al.  Common Scab Detection on Potatoes Using an Infrared Hyperspectral Imaging System , 2011, ICIAP.

[4]  Arno Formella,et al.  Non-destructive Detection of Hollow Heart in Potatoes Using Hyperspectral Imaging , 2011, CAIP.

[5]  C. G. Haugh,et al.  Detecting Hollow Heart in Potatoes Using Ultrasound , 1994 .

[6]  Sushma Panigrahy,et al.  Utility of Hyperspectral Data for Potato Late Blight Disease Detection , 2011 .

[7]  Bart Nicolai,et al.  Prediction of optimal cooking time for boiled potatoes by hyperspectral imaging , 2011 .

[8]  Kurt C. Lawrence,et al.  Textural analysis of hyperspectral images for improving contaminant detection accuracy , 2008 .

[9]  Laura Hoch Computer Analysis of Images and Patterns , 1993, Lecture Notes in Computer Science.

[10]  Moon S. Kim,et al.  Correlation analysis of hyperspectral imagery for multispectral wavelength selection for detection of defects on apples , 2008 .

[11]  Angel Blanch,et al.  Top hundred chess experts: A cross-domain analysis of change over time , 2018, Intelligence.

[12]  H. Gonzalez-Jorge,et al.  A genetic algorithm approach for feature selection in potatoes classification by computer vision , 2009, 2009 35th Annual Conference of IEEE Industrial Electronics.

[13]  Moon S. Kim,et al.  Detection of Fecal Contamination on Cantaloupes Using Hyperspectral Fluorescence Imagery , 2005 .

[14]  Wenyi Tan,et al.  Detecting and classifying minor bruised potato based on hyperspectral imaging , 2018, Chemometrics and Intelligent Laboratory Systems.

[15]  Da-Wen Sun,et al.  Potential of hyperspectral imaging for visual authentication of sliced organic potatoes from potato and sweet potato tubers and rapid grading of the tubers according to moisture proportion , 2016, Comput. Electron. Agric..

[16]  Jianwei Qin,et al.  Citrus canker detection using hyperspectral reflectance imaging and PCA-based image classification method , 2008 .

[17]  Moon S. Kim,et al.  Development of hyperspectral imaging technique for the detection of apple surface defects and contaminations , 2004 .

[18]  Ismael Lopez-Juarez,et al.  Ann Analysis in a Vision Approach for Potato Inspection , 2008 .

[19]  Ning Wang,et al.  Early detection of apple bruises on different background colors using hyperspectral imaging , 2008 .

[20]  Hiroshi Okamoto,et al.  Discrimination between potato tubers and clods by detecting the significant wavebands , 2008 .

[21]  Xueying Zhang,et al.  Evaluation of a set of new ORF kernel functions of SVM for speech recognition , 2013, Eng. Appl. Artif. Intell..

[22]  Navid Razmjooy,et al.  A real-time mathematical computer method for potato inspection using machine vision , 2012, Comput. Math. Appl..

[23]  Jacco C. Noordam,et al.  High-speed potato grading and quality inspection based on a color vision system , 2000, Electronic Imaging.