|
|
|
![](https://webarchive.library.unt.edu/eot2008/20081111131053im_/http://www.ars.usda.gov/incme/images/Research_head.gif) |
Research Project:
TECHNOLOGIES FOR ASSESSING AND GRADING QUALITY AND CONDITION OF CUCUMBERS AND TREE FRUITS
Location: Sugarbeet and Bean Research
Title: Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging ¿ Part 1. Development of a prototype
Authors
Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type:
Peer Reviewed Journal
Publication Acceptance Date: June 3, 2008
Publication Date: June 27, 2008
Reprint URL: http://www.springerlink.com/content/w44j431683101493/?p=82e616197cf946048666ff6a7a981782&pi=0
Citation: Ariana, D., Lu, R. 2008. Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging. Part 1. Development of a prototype. Sensing and Instrumentation for Food Quality and Safety. DOI 10.1007/s11694-008-9057-x. Available: www.springerlink.com/content/w44j431683101493/?.
Interpretive Summary: Automated sorting and grading of fruits and vegetables can lessen industry dependence on human inspectors, reduce production cost, and improve product consistency and quality. Machine vision inspection systems currently are being used in many pickle processing facilities for inspecting external characteristics (size, shape, color and/or surface blemishes) of pickling cucumbers, but they are not suitable for detecting internal defect (such as bruises and soft or hollow center). To ensure high quality, consistent pickled products, fresh pickling cucumbers need to be inspected for both external and internal quality attributes. Hence, an effective and efficient internal defect inspection system would be valuable to the pickling industry. In this research, we developed a laboratory prototype using hyperspectral imaging, a technique that acquires both spectral and spatial information from the product item over the visible and near-infrared (longer than visible light in wavelength) region. With the integration of reflectance and transmittance sensing modes, the prototype is capable of inspecting both external characteristics (color and size) and internal defect (hollow center) at a speed of up to two fruits per second. The prototype also had a novel feature of performing inline, real-time calibrations to correct the effect of light source variations on the images acquired from each cucumber. Algorithms were developed for pre-processing hyperspectral images and for estimating the size of cucumbers. This research demonstrated that the hyperspectral imaging technique, coupled with both reflectance and transmittance modes, can achieve the goal of online inspection of both external and internal quality of pickling cucumbers, which otherwise cannot be achieved with other existing technologies. The prototype provides a basis for further development of a commercially viable hyperspectral imaging system for rapid inspection of pickling cucumbers and pickled products. The technology can also be used for quality inspection of other horticultural products.
Technical Abstract: This paper reports on the development of a hyperspectral imaging prototype for real-time evaluation of external and internal quality of pickling cucumbers. The prototype consisted of a two-lane round belt conveyor, two illumination sources (one for reflectance and one for transmittance), and a line-scan hyperspectral imaging unit. It had a novel feature of simultaneous imaging under reflectance mode in the visible region (500-680 nm) and transmittance mode in the short-wavelength near infrared (SW-NIR) region (680-1000 nm). Reflectance information from the visible region was intended for evaluating the external characteristics of cucumbers such as skin color, whereas transmittance information from the SW-NIR region was used for internal defect detection (i.e., hollow center). Additional features of the prototype included simultaneous acquisition of reflectance and transmittance from calibration references that were installed in the system, to provide real-time, continuous corrections of individual hyperspectral images from each sample. Methods and algorithms were developed for system calibrations, image acquisition and pre-processing, and estimation of cucumber fruit size. The prototype was calibrated and tested for image acquisition and segregation and fruit size estimation of pickling cucumbers.
|
|
|
|
|
|
Last Modified: 11/10/2008
|
|