Multispectral Wavebands Selection for the Detection of Potential Foreign Materials in Fresh-Cut Vegetables

Abstract

Ensuring the quality of fresh-cut vegetables is the greatest challenge for the food industry and is equally as important to consumers (and their health). Several investigations have proven the necessity of advanced technology for detecting foreign materials (FMs) in fresh-cut vegetables. In this study, the possibility of using near infrared spectral analysis as a potential technique was investigated to identify various types of FMs in seven common fresh-cut vegetables by selecting important wavebands. Various waveband selection methods, such as the weighted regression coefficient (WRC), variable importance in projection (VIP), sequential feature selection (SFS), successive projection algorithm (SPA), and interval PLS (iPLS), were used to investigate the optimal multispectral wavebands to classify the FMs and vegetables. The application of selected wavebands was further tested using NIR imaging, and the results showed good potentiality by identifying 99 out of 107 FMs. The results indicate the high applicability of the multispectral NIR imaging technique to detect FMs in fresh-cut vegetables for industrial application.

Intelligent detection for fresh‐cut fruit and vegetable processing: Imaging technology

“…Compared with other foods, there are few reports about the application of imaging technology for foreign body detection in fresh cutting processing, only focusing on HSI and FI. Tunny et al (2022) evaluated the feasibility of multispectral NIR imaging for the detection of various foreign bodies (including paper, plastic, rubber, wood, stone, insects, nail, etc.; Figure 4a) in seven fresh-cut vegetables (zucchini, potato, onion, green onion, radish, carrot, and cabbage). The results showed that the foreign body detection accuracy of 7 fresh-cut vegetables using 6 different band combinations (1150, 1400, 1450, 1731, 1880, and 1920 nm) was 92.5%.…”

“…Foreign body diagram (Tunny et al., 2022) (a); Schematic diagram of fluorescence imaging instrument (b); Fluorescence classification image of foreign body mixed with cabbage and green onion (Lohumi et al., 2021) (c); Fluorescence imaging results of foreign body detection in zucchini and green onion, as well as the reflectance imaging results of foreign body detection in garlic, carrot and onion (Cho, 2021) (d)…”

“…Tunny et al. (2022) evaluated the feasibility of multispectral NIR imaging for the detection of various foreign bodies (including paper, plastic, rubber, wood, stone, insects, nail, etc. ; Figure 4a) in seven fresh‐cut vegetables (zucchini, potato, onion, green onion, radish, carrot, and cabbage).…”

Non-destructive testing of mechanical properties of solid wood panel based on partial least squares structural equation modeling transfer method

“…Consequently, using this stack of wavelength images or spectral cube, the average intensity and local changes of the intensity pixels at each spectral image may be analyzed and used for pattern identification. However, expensive and specialized hardware is required to capture hyperspectral images (Nakawajana et al 2021;Tunny et al 2022). In general, hyperspectrometers with somewhat higher resolution cost over a million dollars.…”

Spectroscopy Imaging Techniques as In Vivo Analytical Tools to Detect Plant Traits

“…Further, food safety deals with the safety of the food production line, ranging from on-farm to off-farm practices [7,8]. Hazards commonly occur due to chemical contamination [9], physical contamination [10,11], food adulteration [12,13], genetic modification [14], and other processes. Chemical contamination and food adulteration in agricultural products are present as the side effects of food unavailability.…”