Evaluation and comparison of NIR multi-product calibration methods for Brix prediction
-
Michael Kopf
Michael Kopf is a student at the Karlsruhe Institute of Technology KIT and a research assistant at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Karlsruhe. His research interests include computer vision and machine learning.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
Robin Gruna is research group manager at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Karlsruhe. His research interests include hyperspectral imaging, machine vision, computational imaging and machine learning.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
,
Thomas Längle
Thomas Längle is adjunct professor at the Karlsruhe Institute of Technology KIT, Karlsruhe, and the head of the business unit “Vision Based Inspection Systems” at the Fraunhofer IOSB in Karlsruhe, Germany. His research interests include different aspects of image processing and real-time algorithms for inspection systems.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
Jürgen Beyerer is full professor for informatics at the Institute for Anthropomatics and Robotics at the Karlsruhe Institute of Technology KIT since March 2004 and director of the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Ettlingen, Karlsruhe, Ilmenau and Lemgo. Research interests include automated visual inspection, signal and image processing, variable image acquisition and processing, active vision, metrology, information theory, fusion of data and information from heterogeneous sources, system theory, autonomous systems and automation.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
Abstract
Near-infrared (NIR) spectroscopy is a widespread technology for fruit and vegetable quality assessment. New fields of application of this technology, like mobile food analysis with handheld low-cost spectrometers, increase the demand for chemometric calibration models that are able to deal with multiple products and varieties thereof at once (so-called multi-product calibration models). While there are well studied methods for single-product calibration as partial least squares regression (PLSR), multi-product calibration is still challenging. Conventional approaches that work well for single-product calibration can lead to high errors for multi-product calibration. However, nonlinear methods as local regression and artificial neural networks were found to be suitable[1][2]. Preliminary studies in multi-product calibration for quantitative analysis of food with near-infrared spectroscopy showed good results for memory-based learning (MBL) and a classification prediction hierarchy (CPH)[3]. In this study, three varieties of apples, pears and tomatoes with known sugar content (in ○Brix) are analysed with NIR hyperspectral imaging spectroscopy in the range from 900 nm to 2400 nm. Predictive performance of a linear PLSR model, two nonlinear models (CPH and MBL) and different pre-processing techniques are tested and evaluated. For error estimation, leave-one-product-out and leave-one-out cross-validation are used.
Zusammenfassung
Nahinfrarotspektroskopie ist eine etablierte Methode zur Qualitätsbestimmung von Obst und Gemüse. Neue Anwendungsgebiete, wie z. B. die mobile Lebensmittelanalyse mittels handgetragener und preisgünstiger Mikrospektrometer, verlangen nach neuen Ansätzen zur Multiprodukt-Kalibrierung. Zur produktspezifischen Kalibrierung existieren bereits geeignete Methoden wie partial least squares regression (PLSR). Der Versuch von Micklander et al. zeigt jedoch auf, dass die Multiprodukt-Kalibrierung noch eine ungelöste Herausforderung darstellt. Nichtlineare Ansätze wie neuronale Netze und lokale Regression erzielten hier bessere Ergebnisse als konventionelle Methoden wie PLSR. Vorläufige Untersuchungen zur Multiprodukt-Kalibrierung zur quantitativen Analyse von Lebensmitteln mittels NIR Spektroskopie lieferten vielversprechende Ergebnisse durch Memory-Based Learning (MBL) und Classification-Prediction-Hierarchy (CPH). In dieser Arbeit werden drei Ansätze zur Multiprodukt-Kalibrierung untersucht. Hierzu werden drei unterschiedliche Apfelsorten, Birnen und Tomaten mit bekanntem Zuckergehalt (in ○Brix) mittels bildgebender NIR Spektroskopie im Bereich von 900 nm bis 2400 nm analysiert. Die Genauigkeit eines linearen PLSR-Modells und zweier nichtlinearer Modelle (CPH und MBL) sowie unterschiedliche Vorverarbeitungsmethoden werden untersucht und evaluiert. Zur Bestimmung von Fehlermaßen dienen Leave-One-Out- und Leave-One-Product-Out-Kreuzvalidierungen.
About the authors
Michael Kopf is a student at the Karlsruhe Institute of Technology KIT and a research assistant at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Karlsruhe. His research interests include computer vision and machine learning.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
Robin Gruna is research group manager at the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Karlsruhe. His research interests include hyperspectral imaging, machine vision, computational imaging and machine learning.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
Thomas Längle is adjunct professor at the Karlsruhe Institute of Technology KIT, Karlsruhe, and the head of the business unit “Vision Based Inspection Systems” at the Fraunhofer IOSB in Karlsruhe, Germany. His research interests include different aspects of image processing and real-time algorithms for inspection systems.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
Jürgen Beyerer is full professor for informatics at the Institute for Anthropomatics and Robotics at the Karlsruhe Institute of Technology KIT since March 2004 and director of the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB in Ettlingen, Karlsruhe, Ilmenau and Lemgo. Research interests include automated visual inspection, signal and image processing, variable image acquisition and processing, active vision, metrology, information theory, fusion of data and information from heterogeneous sources, system theory, autonomous systems and automation.
Fraunhofer Institute of Optronics, System Technologies and Image Exploitation, Karlsruhe, Germany
©2018 Walter de Gruyter Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- Optical characterization of materials 2017
- Beiträge
- Considering spectral variability for optical material abundance estimation
- Automatic detection of fused tungsten carbides for the characterization of welding process
- Durchführbarkeitsstudie zur Inline-Überwachung der Wärmeleitfähigkeit und der strukturellen Qualität von Kunststoffen im Heißextrusionsprozess mittels Infrarot-Thermographie
- Non-invasive assessment of the bioburden of minced pork using a hand-held fluorescence device
- Evaluation and comparison of NIR multi-product calibration methods for Brix prediction
- THz imaging for recycling of black plastics
- Motion-based material characterization in sensor-based sorting
Articles in the same Issue
- Frontmatter
- Editorial
- Optical characterization of materials 2017
- Beiträge
- Considering spectral variability for optical material abundance estimation
- Automatic detection of fused tungsten carbides for the characterization of welding process
- Durchführbarkeitsstudie zur Inline-Überwachung der Wärmeleitfähigkeit und der strukturellen Qualität von Kunststoffen im Heißextrusionsprozess mittels Infrarot-Thermographie
- Non-invasive assessment of the bioburden of minced pork using a hand-held fluorescence device
- Evaluation and comparison of NIR multi-product calibration methods for Brix prediction
- THz imaging for recycling of black plastics
- Motion-based material characterization in sensor-based sorting
