Ripeness Categories Research Articles

Development of fig fruit ripeness classification using convolutional neural network

This study presents the design and evaluation of a deep convolutional neural network (CNN) model for accurately classifying fig ripeness stages. Traditionally, fruit ripeness classification has been conducted manually, which presents several drawbacks, including heavy reliance on human labor and inconsistencies in determining fruit ripeness. By leveraging advanced deep learning techniques, specifically CNNs, this research aims to automate the fig ripeness classification process. The CNN architecture was developed and trained using MATLAB software, targeting three ripeness categories: ripe, half-ripe, and unripe. The methodology involved pre-processing the fig images and configuring the CNN model with multiple convolutional, batch normalization, and max pooling layers specifically for fig classification tasks. The final CNN model achieved an impressive accuracy rate of 94.44%, significantly surpassing results from previously reported studies. The developed model is a promising tool for automating fig ripeness classification, contributing to advancements in precision agriculture and smart farming technologies.

Variation in Soluble Sugars in Arabica Coffee Cherry Fruits.

The maturation of Arabica coffee fruits is influenced by both endogenous and external factors. The stage of fruit maturation affects the chemical composition of the beans, which in turn impacts the quality of the coffee beverage. During maturation, the fruit peel changes colour from green to red (cherry), signalling the optimal harvest time and suggesting high fruit quality. However, the degree of redness can vary, indicating different levels of maturity. This study aimed to explore the variation in soluble sugar accumulation in relation to the redness of coffee fruit tissues. We classified ripe fruits into six ripeness categories based on the intensity of the red colour of the epicarp, measured using a colourimeter. We analysed total soluble sugar, sucrose, and starch in three parts: coat (exocarp + mesocarp), coat juice (obtained by squeezing the coat), and beans. Our findings reveal that the variation in sugar in the endosperm does not correspond to changes in the coat, suggesting separate regulation of sugar accumulation, particularly sucrose, which is crucial for coffee quality. Our data indicate that there is no transfer of sucrose and reducing sugars from the red coat to the bean.

Tomato maturity stage prediction based on vision transformer and deep convolution neural networks

Automated assessment of tomato crop maturity is vital for improving agricultural productivity and reducing food waste. Traditionally, farmers have relied on visual inspection and manual assessment to predict tomato maturity, which is prone to human error and time-consuming. Computer vision and deep learning automate this process by analysing visual characteristics, enabling data-driven harvest decisions, optimising quality, and reducing waste for sustainable and efficient agriculture. This research demonstrates deep learning models accurately classifying tomato maturity stages using computer vision techniques, utilising a novel dataset of 4,353 tomato images. The Vision Transformer (ViT) model exhibited superior performance in classifying tomatoes into three ripeness categories (immature, mature, and partially mature), achieving a remarkable testing accuracy of 98.67% and the Convolution neural network (CNN) models, including EfficientNetB1, EfficientNetB5, EfficientNetB7, InceptionV3, ResNet50, and VGG16, achieved testing accuracies of 88.52%, 89.84%, 91.16%, 90.94%, 93.15%, and 92.27%, respectively, when tested with unseen data. ViT significantly surpassed the performance of CNN models. This research highlights the potential for deploying ViT in agricultural environments to monitor tomato maturity stages and packaging facilities smartly. Transformer-based systems could substantially reduce food waste and improve producer profits and productivity by optimising fruit harvest time and sorting decisions.

A Real-Time Detection Algorithm for Sweet Cherry Fruit Maturity Based on YOLOX in the Natural Environment

Fast, accurate, and non-destructive large-scale detection of sweet cherry ripeness is the key to determining the optimal harvesting period and accurate grading by ripeness. Due to the complexity and variability of the orchard environment and the multi-scale, obscured, and even overlapping fruit, there are still problems of low detection accuracy even using the mainstream algorithm YOLOX in the absence of a large amount of tagging data. In this paper, we proposed an improved YOLOX target detection algorithm to quickly and accurately detect sweet cherry ripeness categories in complex environments. Firstly, we took a total of 2400 high-resolution images of immature, semi-ripe, and ripe sweet cherries in an orchard in Hanyuan County, Sichuan Province, including complex environments such as sunny days, cloudy days, branch and leaf shading, fruit overlapping, distant views, and similar colors of green fruits and leaves, and formed a dataset dedicated to sweet cherry ripeness detection by manually labeling 36068 samples, named SweetCherry. On this basis, an improved YOLOX target detection algorithm YOLOX-EIoU-CBAM was proposed, which embedded the Convolutional Block Attention Module (CBAM) between the backbone and neck of the YOLOX model to improve the model’s attention to different channels, spaces capability, and replaced the original bounding box loss function of the YOLOX model with Efficient IoU (EIoU) loss to make the regression of the prediction box more accurate. Finally, we validated the feasibility and reliability of the YOLOX-EIoU-CBAM network on the SweetCherry dataset. The experimental results showed that the method in this paper significantly outperforms the traditional Faster R-CNN and SSD300 algorithms in terms of mean Average Precision (mAP), recall, model size, and single-image inference time. Compared with the YOLOX model, the mAP of this method is improved by 4.12%, recall is improved by 4.6%, F-score is improved by 2.34%, while model size and single-image inference time remain basically comparable. The method in this paper can cope well with complex backgrounds such as fruit overlap, branch and leaf occlusion, and can provide a data base and technical reference for other similar target detection problems.

APPLICATION FUZZY MAMDANI TO DETERMINE THE RIPENESS LEVEL OF CRYSTAL GUAVA FRUIT

Crystal guava is one of Indonesia's flora diversity. The rind of the unripe crystal guava fruit is green, and the rind of the ripe crystal guava fruit is yellowish green. However, it is difficult to determine the ripeness of crystal guava due to the similar color of the fruit skin. Determining fruit ripeness is uncertain and therefore requires a way to deal with this uncertainty. One of the methods you can use is fuzzy Mamdani. In this study, the ripeness level of crystal guava is determined using fuzzy Mamdani. Crystal guava fruits fall into four ripeness categories: raw, half ripe, ripe, and very ripe. The data used is in the form of an RGB image separated from the background so that only crystal guava fruit objects are captured. The image of the fruit object was then extracted by looking for the median red, green, and blue at each pixel of the image. This value is used as input for the fuzzy Mamdani process. The fuzzy set and fuzzy rules that have been formed can be applied to determine the maturity level of crystal guava fruit by validating the results of 140 image data with an accuracy of 83,5%.

Classification of oil palm fresh fruit maturity based on carotene content from Raman spectra

The oil yield, measured in oil extraction rate per hectare in the palm oil industry, is directly affected by the ripening levels of the oil palm fresh fruit bunches at the point of harvesting. A rapid, non-invasive and reliable method in assessing the maturity level of oil palm harvests will enable harvesting at an optimum time to increase oil yield. This study shows the potential of using Raman spectroscopy to assess the ripeness level of oil palm fruitlets. By characterizing the carotene components as useful ripeness features, an automated ripeness classification model has been created using machine learning. A total of 46 oil palm fruit spectra consisting of 3 ripeness categories; under ripe, ripe, and over ripe, were analyzed in this work. The extracted features were tested with 19 classification techniques to classify the oil palm fruits into the three ripeness categories. The Raman peak averaging at 1515 cm−1 is shown to be a significant molecular fingerprint for carotene levels, which can serve as a ripeness indicator in oil palm fruits. Further signal analysis on the Raman peak reveals 4 significant sub bands found to be lycopene (ν1a), β-carotene (ν1b), lutein (ν1c) and neoxanthin (ν1d) which originate from the C=C stretching vibration of carotenoid molecules found in the peel of the oil palm fruit. The fine KNN classifier is found to provide the highest overall accuracy of 100%. The classifier employs 6 features: peak intensities of bands ν1a to ν1d and peak positions of bands ν1c and ν1d as predictors. In conclusion, the Raman spectroscopy method has the potential to provide an accurate and effective way in determining the ripeness of oil palm fresh fruits.

A study on the oil palm fresh fruit bunch (FFB) ripeness detection by using Hue, Saturation and Intensity (HSI) approach

To increase the quality of palm oil means to accurately grade the oil palm fresh fruit bunches (FFB) for processing. In this paper, HSI color model was used to determine the relationship between FFB ’ s color with the underipe and ripe category so that the grading system could be accurately done. From the analysis manipulation, a formula was generated and applied to the data obtained. The by linear regression in the data shows an average success rate at 45% accuracy for oil palm ripeness detection. Artificial Neural Network (ANN) however return a better accuracy result for both underipe and ripe categories which are 60% and 80% respectively. This yield an overall accuracy of 70%. This can be increased more by improving the grading system.

Oil palm fruit grading using a hyperspectral device and machine learning algorithm

In this paper, a hyperspectral-based system was introduced to detect the ripeness of oil palm fresh fruit bunches (FFB). The FFBs were scanned using a hyperspectral device, and reflectance was recorded at different wavelengths. A total of 469 fruits from oil palm FFBs (nigrescens, virescens, oleifera) were categorized as overripe, ripe, and underripe. Fruit attributes in the visible and nearinfrared (400 nm to1000 nm) wavelength range regions were measured. Artificial neural network (ANN), classified the different wavelength regions on oil palm fruit through pixel-wise processing. The developed ANN model successfully classified oil palm fruits into the three ripeness categories (ripe, underripe, and overripe). The accuracy achieved by our approach was compared against that of the conventional system employing manual classification based on the observations of a human grader. Our classification approach had an accuracy of more than 95% for all three types of oil palm fruits. The research findings will help increase the quality harvesting and grading efficiency of FFBs.

Determination of oil palm fresh fruit bunch ripeness—Based on flavonoids and anthocyanin content

Non-destructive and real-time oil palm fresh fruit bunch (FFB) grading systems are of major exploratory concern for researchers in the oil palm industry. The objective is to reduce time, labour, costs, and most importantly, to increase the oil extraction rate, in order to achieve a good quality of palm oil at a more acceptable price. This research investigates the potential of flavonoids and anthocyanins as a predictor to classify the degree of oil palm FFB ripeness. This paper also discusses the relationship between these predictors and the ripeness categories period. One hundred and eighty oil palm FFB samples were collected from a private plantation in Malaysia, according to three maturity categories i.e., ripe, under-ripe, and over-ripe. Each sample was randomly scanned 10 times, both front and back using a hand-held Multiplex®3 multi-parameter fluorescence sensor. The results show that flavonoid and anthocyanin content decreased from immature to over mature oil palm FFBs. Overall, the relationship using Pearson's correlation between flavonoids and anthocyanins was r2=0.84 and the most outstanding relationship accuracy was at the over-ripe stage, at 90%. Statistical analysis using analysis of variance (ANOVA) and pair-wise testing proved that both predictors gave significance difference between under-ripe, ripe, and over-ripe maturity categories. This shows that both predictors can be good indicators to classify oil palm FFB. Classification analysis was performed by using both predictors together and separately through several methods. The highest overall classification accuracy was 87.7% using a Stochastic Gradient Boosting Trees model and with both predictors. The other classification methods used either independent or both predictors together and gave various results ranging from 50 to 85% accuracy. This research proves that flavonoids and anthocyanins can be used as predictors of oil palm maturity classification.

The Effects of Ethephon on Saskatoon (Amelanchier alnifolia Nutt.) Fruit Ripening

Field experiments were conducted on two cultivars of saskatoon to test the effectiveness of ethephon in stimulating uniform fruit ripening without compromising fruit quality. Shrubs of cultivars Northline and Smoky were sprayed to runoff with ethephon (0, 250, 500, and 1000 mg·L-1 for `Northline'; 0, 500, and 1000 mg·L-1 for `Smoky') prior to fruit maturity. Fruit were harvested 4 to 8 days after treatment and sorted into ripeness categories by size, and the fully ripe fruit were evaluated for quality (surface color, firmness, mean fruit weight, soluble solids, and titratable acids). Ethephon significantly increased the percent ripe fruit per shrub (by up to 9.7%) in both cultivars, without a significant effect on fruit quality. At concentrations up to 1000 mg·L-1, ethephon may be an effective ripening agent for saskatoon fruit without reducing fruit quality. Although there were significant differences in yield from year to year for both cultivars because of their biennial-bearing habit, ethephon treatments did not significantly affect total yields.

Classification of apple fruits according to their maturity state by the pattern recognition analysis of their polyphenolic compositions

Polyphenolic profiles of cider apple cultivars were studied in order to differentiate fruits according to their maturity state (ripe or unripe). Thiolysis and direct solvent extracts of freeze-dried apple pulps and peels were analysed by HPLC-DAD. Univariate data treatment did not achieve the mentioned target; thus a multivariate approach was considered. For each apple tissue data set, several chemometric techniques were applied to the most discriminant variables. Cluster analysis allowed a preliminary study of the data structure. Then, supervised pattern recognition procedures, namely linear discriminant analysis, K-nearest neighbours, soft independent modelling of class analogy, and multilayer feed-forward artificial neural networks (MLF-ANN), were used to develop decision rules to classify samples in the established categories. Excellent results were afforded by MLF-ANN applied to the concentrations of total procyanidins and (+)-catechin and the average degree of polymerisation of procyanidins in apple pulp, with success in the prediction ability of 97% and 99% for unripe and ripe categories, respectively.

175 Comparison of Suitability of Nonmelting and Melting Flesh Peach Cultivars for Fresh-cut

Two nonmelting flesh (`GUFprince' and `UF2000') and two melting flesh (`Tropic Beauty' and `Rayon') peach cultivars were segregated into ripeness categories at harvest according to initial flesh firmness and prepared as fresh-cut slices as described in Gorny et al. (HortScience 33:110–113), except that there were no “overripe” (0-13 N flesh firmness) stage nonmelting flesh fruit. Slices were stored at 1, 5, or 10 °C for 8 days and were evaluated for visual and taste quality, flesh firmness and color, and respiration and ethylene production rates every other day during storage. The optimal ripeness for preparing fresh-cut slices from the melting flesh cultivars was the “ripe” (13-27 N flesh firmness) stage; less-ripe melting flesh slices did not ripen at 1 or 5 °C and riper melting flesh slices and those held at 10 °C softened excessively, became discolored, and decayed. The optimal ripeness stage for the nonmelting flesh cultivars was 40-53 N flesh firmness, which corresponded to physiologically ripe (climacteric rise) for nonmelting flesh fruit, but melting flesh fruit at that firmenss were physiologically only mature-green (preclimacteric). Storage of nonmelting flesh slices was limited by surface desiccation at 1 °C, and by flesh discoloration at 5 and 10 °C, which was more severe in riper slices. The best storage temperature for both fruit genotypes was 1 °C, which prevented discoloration and decay over the 8-day storage period. Nonmelting flesh peach cultivars are better suited for fresh-cut processing than melting flesh cultivars because their firmer texture allows the use of riper fruit with better flavor than the less ripe fruit that must be used for fresh-cut melting flesh peaches.

Fruit Ripeness Determination by Electronic Sensing of Aromatic Volatiles

A sniffer for determining fruit ripeness nondestructively, based on electronic sensing of gas emissions, was developed. The sensing head consists of a semiconductor gas sensor located within a small cup that is placed on the fruit surface, in this study, for a period of up to 30 seconds. Natural gases emitted by the ripening fruit accumulate in the cup and cause a change in the sensor’s conductivity. The sensor was tested on three muskmelon cultivars over two growing seasons. The overall Bayesian maximum likelihood classification accuracy was 90.2% when separating unripe from ripe fruit (two-way classification), and 83.0% for sorting into three ripeness categories (unripe, half-ripe, and ripe). Comparison of sniffer performance with traditional methods of ripeness determination, including flesh firmness, stem detachment force, percent soluble solids, and ethylene emissions, demonstrated that performance of the electronic sniffer had a higher degree of accuracy than all other destructive and nondestructive methods evaluated. Classification accuracy of fruit growing in the field under ambient conditions were comparable to fruit measured in the laboratory: 88.0% and 78.3% for two-way and three-way classification, respectively.

Spring defoliation of white clover seed crops. 1. Inflorescence production of contrasting white clover cultivars

AbstractThree white clover cultivars, S184 (small‐leaved), Menna (medium‐leaved) and Olwen (large‐leaved), were sown at a seed rate of 3 kg ha‐1 under spring wheat cv. Tonic. In the spring of the two following years, there were three pre‐bud emergence mechanical defoliation treatments on which were superimposed four post‐bud emergence treatments giving a total of twelve cutting treatments. Pre‐bud emergence, plots were either cut twice (at approximately two weeks before bud emergence and at bud emergence), cut once at bud emergence or not cut. To each treatment were applied four post‐bud emergence treatments: plots were not cut or cut once (one, two or three weeks after bud emergence). Counts of the total number of inflorescences and of the proportions in various ripeness categories were made throughout the period of seed crop development to determine the pattern of inflorescence development and optimum harvest date. Overall, inflorescence numbers were greatest in cv. S184and least in cv. Olwen. Defoliation before bud emergence had no effect on inflorescence production; however, it was significantly influenced by defoliation after bud emergence. Although delaying the initial development of the crop, inflorescence numbers of all cultivars were highest in both years following cuts two and three weeks after bud emergence. Optimum harvest date was not affected by defoliation or cultivar, numbers of ripe inflorescences in both years reaching a peak at the end of August. The number of brown inflorescences, which may also contribute to seed yield, reached a peak in both years in late July. Seasonal differences in inflorescence production were again observed, emphasizing the difference between first and second year crops and importance of climate in while clover seed production. The implications of these differences in numbers and proportions of inflorescences in various ripeness categories under different defoliation regimes are discussed in relation to seed crop management in the UK.

Firmness Measurement of Stored `Delicious' Apples by Sensory Methods, Magness-Taylor, and Sonic Transmission

`Delicious' apples (Malus domestica Borkh.) from five major U.S. production areas were tested after ≈3 months of commercial storage. Soluble solids concentration (SSC), titratable acidity (TA), Magness-Taylor (MT) firmness, and sonic transmission spectra were compared with ripeness (maturity in trade terminology) scores assigned by six U.S. Dept. of Agriculture (USDA)-licensed apple inspectors according to USDA Grades and Standards inspection procedures. USDA ripeness categories are defined by textural and flavor terms. Inspectors in this test used visual, manual, oral, and auditory sensations to make their judgments, but firmness was the paramount characteristic judged. SSC and TA did not correlate with inspectors' scores, MT, or sonic measurements and thus are not satisfactory indices of ripeness for stored apples. Sonic resonance functions correlated significantly with mean inspectors' scores and with MT firmness. Inspectors' scores correlated slightly better with MT firmness than with sonic terms. MT is destructive and site-specific; in contrast, sonic measurements are nondestructive and representative of the entire fruit.

Defining fruit losses in machine-harvested raspberries

Abstract Machine harvesting raspberries often produces lower yields than hand picking. Total yield loss is not completely accounted for by adding individual yield component losses to saleable yields. Conversion of fruit weights to fruit numbers using weighted mean berry weights specific to each yield loss component reduces this discrepancy. Suggestions for refining this technique are made. Continual use of machine harvesting further reduces fruit yields compared to those from hand picking. Summation of fruit numbers from each yield loss component cannot account for yield differences between machine and hand picking after machine harvesting is used for more than one season. It may, however, enable a more accurate estimate of the adverse effect of long-term machine harvesting on fruit production. Proportions of fmit in ripe, green, and diseased categories from tagged laterals were dissimilar to those in machine harvested yields. The number of laterals used was inadequate to determine accurately the fate of ...

Effect of seed crop management on the potential seed yield of contrasting white clover varieties.

AbstractThree contrasting white clover varieties, Olwen (large‐leaved), Menna (medium‐leaved) and S184 (small‐leaved) were sown with and without a grass companion in 30 cm drills. Two grazing and one mechanical spring defoliation managements were imposed. Counts of the total number of inflorescences and of the percentage in various ripeness categories were made throughout the period of seed crop development to determine the pattern of inflorescence development and optimum harvest date. Inflorescence numbers were greatest in cv. S184 and least in cv. Olwen and, in general, varieties produced both more inflorescences and a greater proportion of ripe inflorescences when grown under spring defoliation managements similar to those for which they were bred. Thus, cv. Olwen produced more ripe inflorescences, and a lower proportion of brown inflorescences (semi‐ripe), after mechanical defoliation while cv. Menna produced more ripe inflorescences following mechanical defoliation and rotational grazing. However, cv. S184 produced more ripe inflorescences under both grazing managements than under mechanical defoliation. Optimum harvest date was not affected by management or variety, total inflorescence number and maximum ripe inflorescences having reached a peak on 11 September. However, varieties differed in the proportion of ripe and brown (semi‐ripe) inflorescences on this date, with cv. Menna and cv. S184 containing a significantly higher proportion of brown inflorescences than cv. Olwen, The implications of these differences in inflorescence development, the proportions of inflorescences in the various ripeness categories and their contribution to seed yield are discussed in relation to the management of white clover seed crops and harvesting method under UK climatic conditions.

Effe-gi, Magness-Taylor, and Instron Fruit Pressure Testing Devices for Apples, Peaches, and Nectarines1

Abstract Pressure test values obtained on various fruits with 2 manual fruit pressure testers (the Magness-Taylor and the smaller Effe-gi) and the Instron Universal Testing Instrument were compared. Tests were made on 5 apple, 1 nectarine, and 3 peach cultivars on an individual fruit basis. Differences in pressure readings were marked among instruments. Responses to the instruments differed among cultivars. Some apples were classified in different ripeness categories according to different pressure testers. For nectarines and peaches, high correlations, but not complete agreement, were obtained among instruments. For all 3 fruits, differences were sufficient to require specification of instrument and method of measurement when fruit pressure test values are reported and to necessitate compensation when measurements made with different types of instruments are compared. Regression equations such as we report should be used to permit accurate comparisons.