TY - GEN
T1 - Calyx and stem discrimination for apple quality control using hyperspectral imaging
AU - Pineda, Israel
AU - Alam MD, Nur
AU - Gwun, Oubong
N1 - Publisher Copyright:
© Springer Nature Switzerland AG 2019.
PY - 2019
Y1 - 2019
N2 - The production of high-quality food products needs an efficient method to detect defects in food, this is particularly true in the production of apples. Hyperspectral image processing is a popular technique to carry out this detection. However, the stem and calyx of the apple provoke frequent detection errors. We analyze the spectrum of our apple data set, propose an algorithm that uses the average of the principal components of two regions of the spectrum to identify the defects, and couple this detection routine with a two-band ratio that discriminates the calyx and stem. Our study considers the spectral range between 403 nm and 998 nm. Our results include the detection of scab, bruise, crack, and cut with and without stem and calyx. We describe all the necessary parameters provided by our spectral analysis. Our algorithm has an overall accuracy of 95%. We conclude that our algorithm effectively detects defects in the presence of stem and calyx.
AB - The production of high-quality food products needs an efficient method to detect defects in food, this is particularly true in the production of apples. Hyperspectral image processing is a popular technique to carry out this detection. However, the stem and calyx of the apple provoke frequent detection errors. We analyze the spectrum of our apple data set, propose an algorithm that uses the average of the principal components of two regions of the spectrum to identify the defects, and couple this detection routine with a two-band ratio that discriminates the calyx and stem. Our study considers the spectral range between 403 nm and 998 nm. Our results include the detection of scab, bruise, crack, and cut with and without stem and calyx. We describe all the necessary parameters provided by our spectral analysis. Our algorithm has an overall accuracy of 95%. We conclude that our algorithm effectively detects defects in the presence of stem and calyx.
KW - Defect detection
KW - Hyperspectral imaging
KW - Two-band ratio
UR - http://www.scopus.com/inward/record.url?scp=85059775643&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-05532-5_20
DO - 10.1007/978-3-030-05532-5_20
M3 - Contribución a la conferencia
AN - SCOPUS:85059775643
SN - 9783030055318
T3 - Communications in Computer and Information Science
SP - 274
EP - 287
BT - Technology Trends - 4th International Conference, CITT 2018, Revised Selected Papers
A2 - Botto-Tobar, Miguel
A2 - D’Armas, Mayra
A2 - Zúñiga Sánchez, Miguel
A2 - Zúñiga-Prieto, Miguel
A2 - Pizarro, Guillermo
PB - Springer Verlag
T2 - 4th International Conference on Technology Trends, CITT 2018
Y2 - 29 August 2018 through 31 August 2018
ER -