Image Analysis Techniques for Automated Hazelnut Peeling Determination

被引：48

作者：

Pallottino, Federico ^{[1
]}

Menesatti, Paolo ^{[1
]}

Costa, Corrado ^{[1
]}

Paglia, Graziella ^{[1
]}

De Salvador, Flavio R. ^{[2
]}

Lolletti, Daniele ^{[2
]}

机构：

[1] Agr Res Council, CRA, ING, Agr Engn Res Unit, I-00016 Monterotondo, Rome, Italy

[2] FRU Tree Fruit Res Ctr, CRA, I-00134 Rome, Italy

来源：

FOOD AND BIOPROCESS TECHNOLOGY | 2010年 / 3卷 / 01期

关键词：

Hazelnut peeling; Image analysis; KNN; Non-destructive testing; QUALITY;

D O I：

10.1007/s11947-009-0211-1

中图分类号：

TS2 [食品工业];

学科分类号：

0832 ;

摘要：

According to FAO statistics, in 2000, Italy was the second largest hazelnut (Corylus avellana, L. 1753) producer in the world. The price of the stock depends on the nut quality (kernel/nut ratio, nut and seed defect, percentage of peeling, and taste panel scores). The evaluation of peeling efficiency after toasting is generally conducted by trained operators in sight on 100 kernels. This work tests two alternative objective methods of after toasting peeling evaluation based on image analysis. Eleven hazelnut cultivars were analyzed and results were compared with the ones assessed by trained operators. Images were analyzed with two statistical approaches: fixed values of RGB thresholding and trained K Nearest Neighbors (KNN). Root mean squared error (RMSE), estimating the comparison between operators and the two image analysis-based techniques, shows better results for KNN (6.6) with respect to fixed threshold (15.9).

引用

页码：155 / 159

页数：5

共 15 条

[1]

[Anonymous], 1990, Two-Dimensional Signal and Image Processing

[2] Estimation of Dielectric Properties of Cakes Based on Porosity, Moisture Content, and Formulations Using Statistical Methods and Artificial Neural Networks [J].

Boyaci, Ismail Hakki ;

Sumnu, Gulum ;

Sakiyan, Ozge .

FOOD AND BIOPROCESS TECHNOLOGY, 2009, 2 (04) :353-360

[3]

Bruce V., 1996, Visual Perception, physiology, psychology and ecology

[4]

Clarkson K.L., 2005, Nearest-Neighbor Methods in Learning and Vision, V1st, P15

[5]

Kaleoglu M, 2004, FOOD BIOPROD PROCESS, V82, P201, DOI [10.1205/fbio.82.3.201.44184, 10.1205/096030897531577]

[6]

Leardi R, 2008, MODERN TECHNIQUES FO

[7]

Martens H., 1989, Multivariate Calibration, P97

[8] Shape-based methodology for multivariate discrimination among Italian hazelnut cultivars [J].

Menesatti, Paolo ;

Costa, Corrado ;

Paglia, Graziella ;

Pallottino, Federico ;

D'Andrea, Stefano ;

Rimatori, Valentina ;

Aguzzi, Jacopo .

BIOSYSTEMS ENGINEERING, 2008, 101 (04) :417-424

[9] Supervised Multivariate Analysis of Hyper-spectral NIR Images to Evaluate the Starch Index of Apples [J].

Menesatti, Paolo ;

Zanella, Angelo ;

D'Andrea, Stefano ;

Costa, Corrado ;

Paglia, Graziella ;

Pallottino, Federico .

FOOD AND BIOPROCESS TECHNOLOGY, 2009, 2 (03) :308-314

[10] Uncertainty analysis and modelling of the starch index during apple fruit maturation [J].

Peirs, A ;

Scheerlinck, N ;

Perez, AB ;

Jancsók, P ;

Nicolaï, BM .

POSTHARVEST BIOLOGY AND TECHNOLOGY, 2002, 26 (02) :199-207

← 1 2 →