Skip to main content
ARS Home » Northeast Area » Ithaca, New York » Robert W. Holley Center for Agriculture & Health » Plant, Soil and Nutrition Research » Research » Publications at this Location » Publication #397841

Research Project: Advancing the Nutritional Quality of Staple Food Crops for Improved Intestinal Function and Health

Location: Plant, Soil and Nutrition Research

Title: Optical sensing technologies for nondestructive quality assessment in dry beans

item MENDOZA, FERNANDO - Cornell University
item Wiesinger, Jason
item Cichy, Karen

Submitted to: Book Chapter
Publication Type: Book / Chapter
Publication Acceptance Date: 5/2/2021
Publication Date: 12/17/2021
Citation: Mendoza, F.A., Wiesinger, J.A., Cichy, K.A. 2021. Optical sensing technologies for nondestructive quality assessment in dry beans. in: Siddiq, M., Uebersax, M. Dry Beans and Pulses Production, Processing and Nutrition. 2nd edition. John Wiley & Sons Ltd. p. 277-306.

Interpretive Summary:

Technical Abstract: Phenotyping techniques capable of rapidly and nondestructively predicting end-use properties on beans are necessary to meet the 21st-century challenge of breeding programs. To optimize the selection process in a breeding program, a great number of phenotypes must be simultaneously evaluated to decide which progenies will be advanced into the next generation. Common dry beans (Phaseolus vulgaris L.) represent an excellent species for developing rapid (ultra-high throughput) phenotyping approaches. To date, several physical, processing, biochemical, nutritional and sensorial traits on beans have been successfully quantified using phenotyping spectroscopy. Machine vision overcomes the deficiencies of visual and instrumental techniques and provides an objective, non-destructive, low-cost, reproducible and faster measure for color and appearance among other physical factors of cooked or canned bean seeds from a single digital image. On the other hand, Vis-NIR spectroscopy and hyperspectral imaging techniques have been increasingly applied for examining the quality of dry beans in breeding programs. Visual and internal traits of common beans can be modeled as a function of the spectra using multivariate methods, such as partial least-squares regression among other machine learning approaches. Best practices suggest that these models should be validated using independent samples, after which models can be used to predict the variable of interest in unknown samples on the basis of their spectral reflectance alone. Importantly, optical sensing technologies are rapid, taking only seconds; are nondestructive; and relatively inexpensive. Although the purchase of a spectrometer can range from hundreds to tens of thousands of U.S. dollars, the expenses to run such instruments are minimal compared with the cost and maintenance of other analytical instrumentation (e.g. high-performance liquid chromatography). A spectral approach also provides the potential to assess considerably more individual bean traits in situ and in vivo over multiple time periods than standard reference measurements alone (e.g. those performed with wet chemistry). In addition, this approach can help us to predict the end-use quality with high prediction accuracy. The long-term goal of this research is to provide breeding programs and food industries with a simple to use (relatively inexpensive) imaging platform that can be tailored to predict quality, nutrition and processing traits important to the consumers of beans and bean-based products.