Oranges are juicy, refreshing, and the most loved winter fruit in Pakistan. Pakistan is the 6th largest producer of citrus in the world [1], and around 0.46 million tons of fruit were exported in the year 2020 [2]. Ripeness is very critical as it directly influences the eating quality of harvested fruits [3]. Oranges are non-climacteric fruits i.e., they don’t ripe further once they are harvested. In Pakistan, quality inspection for fruits to be exported is still carried out subjectively by the packaging industry by visualizing physical features, such as fruit color, size, and sample-based tasting. The method is error-prone and tedious. These factors serve as a motivation for the automation of testing procedures. To automate the visual quality inspection, one can utilize camera sensors for estimating size, surface characteristics, and texture [4]. For gauging taste, sweetness, or other quality measures, one can utilize infrared spectroscopy-based methods [5]. The non-destructive assessment using NIRS can help to correlate dry matter (DM), Brix, titratable acidity (TA), and color [6] with fruit quality. Such assessment can also help in full batch testing and quality-based segregation as opposed to sample-based manual judgment.
Over the past decades, NIR spectroscopy has gained considerable attention for non-destructive maturity index assessment due to its ease, fast detection speed, and precision [7, 8]. Researchers have used NIR spectroscopy with machine learning regression algorithms to develop maturity index prediction models such as DM, Brix, color, chlorophyll, starch and TA (only in high acid fruit like lemon and mandarin) of various fruits including apple [9], pear [10], nectarine [11], mango [12], banana [13], melon [14], mandarin [15], strawberry [16], apricot [17], kiwifruit [18], persimmon [19], grape [20], loquat [21] and pineapple [22]. However, due to the diversity in varieties and growing conditions, it is essential to develop the maturity index prediction model for a particular variety, growing region, and for local or export varieties [23]. Other applications require direct classification by use of some machine learning classification algorithm rather than quantification of quality parameter levels. For example, nectarine cultivars [24, 25], orange cultivars [26], and orange growing regions [27] have been differentiated, maturity classes of durian [28, 29] and mango fruit [30], and sweetness levels of melon [31] and grapes [37] have been classified.
Most of the published research on the measurement of intact fruit internal parameters has used an extended NIR region (> 1000 nm) [7]. The short-wave NIR region (750-1100nm) is used commercially for the assessment of internal quality attributes of intact fruit, in preference to the extended NIR region [7]. Longer wavelength ranges offer narrower and stronger absorption features as compared to short-wave NIR and thus better evaluation of internal parameters however, the short-wave NIR wavelengths have greater effective penetration depth into the fruit, hence, offer robustness across independent populations and given the variation in outer layer attributes. The short-wave Vis-NIR option is preferred for commercial purposes due to (currently) lower hardware costs [7, 8].
The pulp of oranges is covered inside a thick peel, which makes penetration of NIRS challenging. Since ripening and harvest maturity is the same for non-climacteric fruits, there can be two ways to estimate ripeness/maturity. The first method is to estimate the fruit quality parameters like Brix, TA, etc. using a machine learning regression algorithm and based on their values judge the sample quality. The second method is to directly classify the eating quality using a machine learning classification algorithm, as reported by researchers in [31, 32] for the direct sweetness classification of melons and grapes.
Like oranges, melons also have a thick rind. Authors have previously proposed a direct sweetness classifier for melons [31] as opposed to Brix-based thresholding, using the correlation between short-wave NIR spectroscopy and sensory assessment. The proposed direct sweetness classifier tested on a single cultivar of melons i.e., ‘honey’ melons, outperformed the Brix estimation-based indirect classification method [31]. There is a need to evaluate the correlation of short-wave NIRS and sensory assessment in other fruits as well. Moreover, the potential of short-wave NIRS and direct sweetness classification for mixed cultivar datasets need to be analyzed. As an extension of the author’s previous work [31], in this paper, the potential of short-wave NIR spectroscopy and direct sweetness classification is evaluated for Pakistani cultivars of orange i.e., Blood red, Mosambi, and Succari (average peel thickness 6mm). A correlation is developed between quality indices i.e., Brix, TA, Brix: TA, and BrimA (Brix minus acids), the sweetness of the fruit, and NIR spectra which are then classified as sweet, mixed, and acidic using a machine learning classifier based on NIR spectra. We argue that direct classification is more suitable to evaluate orange sweetness as opposed to estimating quality indices.