Lightweight tomato ripeness detection algorithm based on the improved RT-DETR.

Tomatoes, widely cherished for their high nutritional value, necessitate precise ripeness identification and selective harvesting of mature fruits to significantly enhance the efficiency and economic benefits of tomato harvesting management. Previous studies on intelligent harvesting often focused solely on identifying tomatoes as the target, lacking fine-grained detection of tomato ripeness. This deficiency leads to the inadvertent harvesting of immature and rotten fruits, resulting in economic losses. Moreover, in natural settings, uneven illumination, occlusion by leaves, and fruit overlap hinder the precise assessment of tomato ripeness by robotic systems. Simultaneously, the demand for high accuracy and rapid response in tomato ripeness detection is compounded by the need for making the model lightweight to mitigate hardware costs. This study proposes a lightweight model named PDSI-RTDETR to address these challenges. Initially, the PConv_Block module, integrating partial convolution with residual blocks, replaces the Basic_Block structure in the legacy backbone to alleviate computing load and enhance feature extraction efficiency. Subsequently, a deformable attention module is amalgamated with intra-scale feature interaction structure, bolstering the capability to extract detailed features for fine-grained classification. Additionally, the proposed slimneck-SSFF feature fusion structure, merging the Scale Sequence Feature Fusion framework with a slim-neck design utilizing GSConv and VoVGSCSP modules, aims to reduce volume of computation and inference latency. Lastly, by amalgamating Inner-IoU with EIoU to formulate Inner-EIoU, replacing the original GIoU to expedite convergence while utilizing auxiliary frames enhances small object detection capabilities. Comprehensive assessments validate that the PDSI-RTDETR model achieves an average precision mAP50 of 86.8%, marking a 3.9% enhancement over the original RT-DETR model, and a 38.7% increase in FPS. Furthermore, the GFLOPs of PDSI-RTDETR have been diminished by 17.6%. Surpassing the baseline RT-DETR and other prevalent methods regarding precision and speed, it unveils its considerable potential for detecting tomato ripeness. When applied to intelligent harvesting robots in the future, this approach can improve the quality of tomato harvesting by reducing the collection of immature and spoiled fruits.

Hawthorn (Crataegus pinnatifida) berries ripeness induced pectin diversity: A comparative study in physicochemical properties, structure, function and fresh-keeping potential.

The effect of hawthorn berries ripeness on the physicochemical, structural and functional properties of hawthorn pectin (HP) and its potential in sweet cherry preservation were investigated. With the advanced ripeness of hawthorn berries, the galacturonic acid (GalA) content decreased from 59.70 mol% to 52.16 mol%, the molecular weight (Mw) reduced from 368.6 kDa to 284.3 kDa, the microstructure exhibited variable appearance from thick lamella towards porous cross-linked fragment, emulsifying activity and emulsions stability, antioxidant activities, α-amylase and pancreatic lipid inhibitory capacities significantly increased. The heated emulsion stored for 30 d presented higher creaming index and more ordered oil droplets compared to the unheated emulsion. With the extended berries ripeness, the firmness of HP gels remarkably decreased from 225.69 g to 73.39 g, while the springiness increased from 0.78 to 1.16, HP exhibited a superior inhibitory effect in water loss, browning, softening, and bacterial infection in sweet cherries preservation.

Fusion of fruit image processing and deep learning: a study on identification of citrus ripeness based on R-LBP algorithm and YOLO-CIT model.

Citrus fruits are extensively cultivated fruits with high nutritional value. The identification of distinct ripeness stages in citrus fruits plays a crucial role in guiding the planning of harvesting paths for citrus-picking robots and facilitating yield estimations in orchards. However, challenges arise in the identification of citrus fruit ripeness due to the similarity in color between green unripe citrus fruits and tree leaves, leading to an omission in identification. Additionally, the resemblance between partially ripe, orange-green interspersed fruits and fully ripe fruits poses a risk of misidentification, further complicating the identification of citrus fruit ripeness. This study proposed the YOLO-CIT (You Only Look Once-Citrus) model and integrated an innovative R-LBP (Roughness-Local Binary Pattern) method to accurately identify citrus fruits at distinct ripeness stages. The R-LBP algorithm, an extension of the LBP algorithm, enhances the texture features of citrus fruits at distinct ripeness stages by calculating the coefficient of variation in grayscale values of pixels within a certain range in different directions around the target pixel. The C3 model embedded by the CBAM (Convolutional Block Attention Module) replaced the original backbone network of the YOLOv5s model to form the backbone of the YOLO-CIT model. Instead of traditional convolution, Ghostconv is utilized by the neck network of the YOLO-CIT model. The fruit segment of citrus in the original citrus images processed by the R-LBP algorithm is combined with the background segment of the citrus images after grayscale processing to construct synthetic images, which are subsequently added to the training dataset. The experiment showed that the R-LBP algorithm is capable of amplifying the texture features among citrus fruits at distinct ripeness stages. The YOLO-CIT model combined with the R-LBP algorithm has a Precision of 88.13%, a Recall of 93.16%, an F1 score of 90.89, a mAP@0.5 of 85.88%, and 6.1ms of average detection speed for citrus fruit ripeness identification in complex environments. The model demonstrates the capability to accurately and swiftly identify citrus fruits at distinct ripeness stages in real-world environments, effectively guiding the determination of picking targets and path planning for harvesting robots.

Integrating deep learning with non-destructive thermal imaging for precision guava ripeness determination.

BACKGROUND: To mitigate post-harvest losses and inform harvesting decisions at the same time as ensuring fruit quality, precise ripeness determination is essential. The complexity arises in assessing guava ripeness as a result of subtle alterations in some varieties during the ripening process, making visual assessment less reliable. The present study proposes a non-destructive method employing thermal imaging for guava ripeness assessment, involving obtaining thermal images of guava samples at different ripeness stages, followed by data pre-processing. Five deep learning models (AlexNet, Inception-v3, GoogLeNet, ResNet-50 and VGGNet-16) were applied, and their performances were systematically evaluated and compared. RESULTS: VGGNet-16 demonstrated outstanding performance, achieving average precision of 0.92, average sensitivity of 0.93, average specificity of 0.96, average F1-score of 0.92 and accuracy of 0.92 within a training duration of 484 s. CONCLUSION: The present study presents a scalable and non-destructive approach for guava ripeness determination, contributing to waste reduction and enhancing efficiency in supply chains and fruit production. These initiatives align with environmentally friendly practices in agriculture. © 2024 Society of Chemical Industry.

Multiple metabolite profiles uncover remarkable bioactive compounds and metabolic characteristics of noni fruit (Morinda citrifolia L.) at various stages of ripeness.

This study aimed to investigate the changes in physicochemical properties, bioactive compounds, and metabolic characteristics of noni fruit at different ripeness levels. The results showed that there were significant differences in physicochemical properties. HPLC analysis was conducted, revealing succinic acid, scopoletin, deacetylasperulosidic acid, and asperulosidic acid were key bioactive compounds as the fruit ripened. Additionally, 4 differentbiomarkers (isocitric acid, 4,4-thiodiphenol, lobaric acid, and octocrylene), identified using 1HNMR and LC-IT-TOF-MS, were found to have a VIP value over 1. The results from HS-GC-IMS demonstrated noteworthy that 14 volatile compounds were identified as highly discriminative features during fruit ripening. Furthermore, correlation analysis showed that different ripeness had significant effects on bioactive components and functional activities, e.g., the inhibition rate of enzyme and E. coli of noni fruit with different ripeness exceeded 90% at the last stage. This study contributes new insights into the effective utilization of bioactive ingredients in noni fruit.

Physicochemical changes and in vitro digestibility of three banana starches at different maturity stages.

This study aimed to compare the changes in physicochemical properties of the starch isolated from three banana cultivars (Musa AAA group, Cavendish subgroup; Musa ABB group, Pisang Awak subgroup; Musa AA group, Huangdijiao subgroup) at five different maturity stages. The results revealed both similarities and significant differences in micromorphology and physicochemical characteristics of the three banana varieties during different growth stages. Apparent amylose content and particle size of the three starches increased with the ripeness of banana. Light microscopy and scanning electron microscopy revealed that starch particles of the three starches had different microscopic characteristics, and that banana starch morphology was basically unchanged at various growth stages. Moreover, the pasting and thermal properties of the banana starches were significantly different at various growth stages. The resistant starch content of the three banana cultivars was about 80% at all growth stages. Musa AAA group, Cavendish subgroup had the highest resistant starch content at stage Ⅴ. This study provides insights into the starch changes of three banana cultivars during ripening.

Integrated Fruit Ripeness Assessment System Based on an Artificial Olfactory Sensor and Deep Learning.

Artificial scent screening systems, inspired by the mammalian olfactory system, hold promise for fruit ripeness detection, but their commercialization is limited by low sensitivity or pattern recognition inaccuracy. This study presents a portable fruit ripeness prediction system based on colorimetric sensing combinatorics and deep convolutional neural networks (DCNN) to accurately identify fruit ripeness. Using the gas chromatography-mass spectrometry (GC-MS) method, the study discerned the distinctive gases emitted by mango, peach, and banana across various ripening stages. The colorimetric sensing combinatorics utilized 25 dyes sensitive to fruit volatile gases, generating a distinct scent fingerprint through cross-reactivity to diverse concentrations and varieties of gases. The unique scent fingerprints can be identified using DCNN. After capturing colorimetric sensor image data, the densely connected convolutional network (DenseNet) was employed, achieving an impressive accuracy rate of 97.39% on the validation set and 82.20% on the test set in assessing fruit ripeness. This fruit ripeness prediction system, coupled with a DCNN, successfully addresses the issues of complex pattern recognition and low identification accuracy. Overall, this innovative tool exhibits high accuracy, non-destructiveness, practical applicability, convenience, and low cost, making it worth considering and developing for fruit ripeness detection.

Bioactivity and influence on colonic microbiota of polyphenols from noni (Morinda citrifolia L.) fruit under simulated gastrointestinal digestion.

Noni (Morinda citrifolia L.) is a tropical fruit rich in bioactive compounds. Little is known about its polyphenol composition at different ripeness levels and digestive characteristics. Here, we studied changes in polyphenols and antioxidant activity as noni ripened. Rutin and kaempferol-3-O-rutinoside were found in high amounts in noni, with antioxidant capacity increasing as it ripened. Under simulated digestion, polyphenols were gradually released from the oral to gastrointestinal phases, partially decomposing in the small intestine due to their instability. Conversely, fiber-bound phenols were released during colonic fermentation, leading to high bioaccessible antioxidant activity. Additionally, noni consumption affected the intestinal microbiome by reducing the Firmicutes/Bacteroidetes ratio and increasing bacteria with prebiotic properties like Prevotella and Ruminococcus. These findings demonstrate that polyphenols significantly contribute to the health benefits of noni fruit by providing absorbable antioxidants and improving the structure of the intestinal microbiome.

Influence of maturation and roasting on the quality and chemical composition of new conilon coffee cultivar by chemometrics.

Coffee is one of the most consumed beverages worldwide. Espírito Santo is the largest Brazilian producer of conilon coffee, and invested in the creation of new cultivars, such as "Conquista ES8152", launched in 2019. Therefore, the present study aimed to evaluate the effects of maturation and roasting on the chemical and sensorial composition of the new conilon coffee cultivar "Conquista ES8152". The coffee was harvested containing 3 different percentages of ripe fruits: 60%, 80%, and 100%, and roasted at 3 different degrees of roasting: light, medium, and dark, to evaluate the moisture and ash content, yield of soluble extract, volatile compound profile, chlorogenic acid and caffeine content, and sensory profile. "Conquista ES8152" coffee has a moisture content between 1.38 and 2.62%; ash between 4.34 and 4.72%; and yield between 30.7 and 35.8%. Sensory scores ranged between 75 and 80 and the majority of volatile compounds belong to the pyrazine, phenol, furan, and pyrrole groups. The content of total chlorogenic acids was drastically reduced by roasting, with values between 2.40 and 9.33%, with 3-caffeoylquinic acid being the majority. Caffeine was not influenced by either maturation or roasting, with values between 2.16 and 2.41%. The volatile compounds furfural, 5-methylfurfural, and 2-ethyl-5-methylpyrazine were positively correlated with the evaluated sensory attributes and 5-methylfurfural was the only one significantly correlated with all attributes. Ethylpyrazine, furfuryl acetate, 1-furfurylpyrrole, 4-ethyl-2-methoxyphenol, and difurfuryl ether were negatively correlated. The stripping did not affect the quality and composition of this new cultivar, however, the roasting caused changes in both the chemical and sensorial profiles, appropriately indicated by the principal component analysis.

Aromatic profiles and enantiomeric distributions of volatile compounds during the ripening of Dendropanax dentiger honey.

Dendropanax dentiger honey (DDH) is a specialty herbal honey from China. Previous research on DDH has mostly focused on its composition and potential chemical markers, no studies have been conducted on the changes in aroma characteristics and chiral odorants during its maturation. Therefore, the present study aims to address the missing parts. The proportions and total concentrations of 185 volatile compounds identified in different classes varied with DDHs ripening. Fourteen common odor-active compounds were identified by odor activity values (OAVs) and GC-olfactometry (GC-O) analysis. The aroma profiles of DDHs were observed to vary at different ripening stages, although the dominant aroma characteristic was "fruity" aroma, which became more pronounced with increasing maturity. The enantiomeric contents and distributions of 7 volatile enantiomers were related to specific physicochemical indicators and the maturity of DDHs, among which the enantiomers of linalool oxide A may be a potential indicator to identify its maturity. Furthermore, precise quantification and OAVs calculation showed that the enantiomer (2S, 5S)-linalool oxide A presented the highest concentration (8.83-27.39 ng/mL) and only the enantiomer R-linalool (OAVs: 5.56-6.14) was an important contributor to the aroma profiles of DDHs at different stages of maturity. These results provided a new research idea for quality control and identification of DDHs at different maturity stages.

Influence of Date Ripeness on Glycemic Index, Glycemic Load, and Glycemic Response in Various Saudi Arabian Date Varieties.

Background Dates have a special position in Middle Eastern countries, especially Saudi Arabia, and are essential to Arabic and Muslim diets. They are eaten in different forms according to their stage of maturation. In this study, we aimed to estimate the glycemic index (GI), glycemic load (GL), and glycemic response of different stages of date fruit maturation. Materials and methods This prospective clinical trial was conducted at King Abdul-Aziz Medical City, Jeddah, Saudi Arabia. Thirteen healthy participants, seven males and six females, received 50 g of glucose as reference food and 50 g of equivalent carbohydrates from three samples of Khalas dates and three samples of Barhi dates at different maturation stages (Khalal, Rutab, and Tamer). The GI, GL, and glycemic response for each type was calculated. Results The calculated means±SD of GI of the different stages of date maturation were 60.57±25.93, which raged from 53±16.49 to 71.06±32.97. The Khalal stage had the highest GI value, while the Tamer stage had a low GI value of 69.14 and 53.09, respectively. The GL ranged from 7.81 to 18.81. The Rutab stage had the highest GL, whereas the Khalal stage had the lowest GL values of 17.66±6.94 and 9.64±4.72, respectively. There was no significant difference in GI between different date maturation stages (p = 0.48). However, the GL presented a significant difference (p = 0.001) between different maturation stages. Conclusion The present study demonstrated that the stage of date maturation can affect the GI, GL, and glycemic response results. Therefore, healthcare providers and dietitians should address the lower GI and GL stages of date maturation in choosing a suitable carbohydrate source for healthy and diabetic individuals.

Blackberry Fruit Classification in Underexposed Images Combining Deep Learning and Image Fusion Methods.

Berry production is increasing worldwide each year; however, high production leads to labor shortages and an increase in wasted fruit during harvest seasons. This problem opened new research opportunities in computer vision as one main challenge to address is the uncontrolled light conditions in greenhouses and open fields. The high light variations between zones can lead to underexposure of the regions of interest, making it difficult to classify between vegetation, ripe, and unripe blackberries due to their black color. Therefore, the aim of this work is to automate the process of classifying the ripeness stages of blackberries in normal and low-light conditions by exploring the use of image fusion methods to improve the quality of the input image before the inference process. The proposed algorithm adds information from three sources: visible, an improved version of the visible, and a sensor that captures images in the near-infrared spectra, obtaining a mean F1 score of 0.909±0.074 and 0.962±0.028 in underexposed images, without and with model fine-tuning, respectively, which in some cases is an increase of up to 12% in the classification rates. Furthermore, the analysis of the fusion metrics showed that the method could be used in outdoor images to enhance their quality; the weighted fusion helps to improve only underexposed vegetation, improving the contrast of objects in the image without significant changes in saturation and colorfulness.

Antioxidant Edible Films Based on Pear Juice and Pregelatinized Cassava Starch: Effect of the Carbohydrate Profile at Different Degrees of Pear Ripeness.

Edible films based on fruit and vegetable purees combined with different food-grade biopolymeric binding agents (e.g., pectin, gelatin, starch, sodium alginate) are recognized as interesting packaging materials that benefit from the physical, mechanical, and barrier properties of biopolymers as well as the sensory and nutritional properties of purees. In the current contribution, edible antioxidant films based on pear juice and pregelatinized cassava starch were developed. In particular, the suitability of using pregelatinized cassava starch for the non-thermal production of these novel edible films was evaluated. In addition, the effects on the films' properties derived from the use of pear juice instead of the complete puree, from the content of juice used, and from the carbohydrate composition associated with the ripening of pears were all studied. The produced films were characterized in terms of their total polyphenol content, water sensitivity, and water barrier, optical, mechanical and antioxidant properties. Results showed that the use of pear juice leads to films with enhanced transparency compared with puree-based films, and that juice concentration and carbohydrate composition associated with the degree of fruit ripeness strongly govern the films' properties. Furthermore, the addition of pregelatinized cassava starch at room temperature discloses a significant and favorable impact on the cohesiveness, lightness, water resistance, and adhesiveness of the pear-juice-based films, which is mainly attributed to the effective interactions established between the starch macromolecules and the juice components.

Vineyard soil heterogeneity and harvest date affect volatolomics and sensory attributes of Cabernet Sauvignon wines on a meso-terroir scale.

To produce premium wines in a specific region is the goal of local oenologists. This study aimed to investigate the influence of soil properties and harvest date on the volatolomics of wine to provide a better insight into single-vineyard wines. Six Cabernet Sauvignon vineyards were selected in a semi-arid region to produce their wines at three harvest ripeness levels ranging from 23°Brix-28°Brix in three seasons (2019-2021). Results showed that among all six vineyards, the vineyard with the highest soil pH produced wines with lower C6 alcohols and herbaceous aroma. Moderate nutrition in soils was beneficial for the accumulation of ß-damascenone and enhanced fruity and floral aroma in wines while over-fertile soil produced wines with the lowest sensory score. As the harvest ripeness elevated, the wine's fruity and floral aroma intensity decreased. Through advanced network analysis, the key volatiles such as ß-damascenone, ethy1 lactate, and isoamyl octanoate, and their interaction in affecting wine sensory scores were evaluated. Our study provided a concept for producing premium single-vineyard wines.

Influence of ripeness stage on the bioactive compounds' contents and antioxidant activities of Solanum anguivi Lam. fruits accessions.

Solanum anguivi Lam. fruits (SALF) possess bioactive compounds, such as phenolics, alkaloids, saponins, flavonoids, and vitamin C, that are beneficial for preventing oxidative stress-related diseases. It has been documented that ripeness stage influences the nutritional quality of fruits. However, there is limited information on the effect of the ripeness stages (unripe, yellow, orange and red) on the bioactive compounds' contents (BCC) and antioxidant activity (AA) of SALF. We investigated the effect of ripening on the BCC and AA of different SALF accessions. Spectrophotometry was used to determine SALF's total contents of phenolics, flavonoids, saponins, vitamin C, and AA and gravimetry for total alkaloids. The AA was determined as free radical scavenging activity (FRSC) and total antioxidant capacity (TAC). The total phenolics (7.6-22.6 mg gallic acid equivalent/g DW), flavonoids (1.3-4.1 mg quercetin equivalent (QE)/g DW), saponins (44.8-152.5 mg diosgenin equivalent/g DW), vitamin C (2.2-6.4 mg ascorbic acid equivalent/g DW), alkaloids (141.2-296.9 mg/g DW), FRSC (1.5-66.2 %) and TAC (0.1-14.2 mg QE/g DW) significantly differed among the ripeness stages. Fruits in the unripe stage were rich in phenolics, flavonoids, and AA; in the red stage in alkaloids and vitamin C; and in the orange stage, in saponins and flavonoids. The AA had strong positive correlations with total flavonoids and phenolics (r = 0.72 and 0.81, respectively) and a moderate negative correlation with total alkaloids (r = -0.67). Overall, unripe stage fruits had the highest AA and total phenolics and thus may have the highest health-promoting properties. Botanists and farmers may, therefore, focus on harvesting and trading SALF to markets/consumers while still unripe.

The key role of vineyard parcel in shaping flavonoid profiles and color characteristics of Cabernet Sauvignon wines combined with the influence of harvest ripeness, vintage and bottle aging.

Recently, revealing the terroir influence on wine chemical features has drawn increasing interest. This study aimed to explain how wine flavonoid signatures were altered by vineyard parcel, harvest ripeness, vintage and bottle aging. Six commercial Cabernet Sauvignon vineyards were selected in the Manas region to produce wines at three harvest ripeness in three seasons (2019-2021) and aged for three years. The six vineyards had little difference in mesoclimate conditions while varying greatly in soil composition. Results showed high vineyard pH (> 8.5) could accelerate grape ripening rate and increase wine flavonol concentration. Vineyards with moderate nutrition produced wines with abundant anthocyanin derivatives and maintained color characteristics during aging. The role of detailed anthocyanin derivatives in regulating wine color was clarified. As the harvest ripeness elevated, wine's flavonoid profiles were altered and gained a higher red color intensity. This work provides chemical mechanisms underlying single-vineyard wines and a theoretical basis for targeted wine production.

Fully Integrated Ultrathin Solid Immersion Grating Microspectrometer for Handheld Visible and Near-Infrared Spectroscopic Applications.

Despite advances in microfabrication, compact spectrometers still face challenges in shrinking their size without sacrificing optical performance. Here,  the solid immersion grating microspectrometer (SIG-µSPEC) for high spectral resolution in a broad operational wavelength range is reported. The spectroscopic module incorporates a silicon microslit, index-matched lens, plane mirrors, solid immersion grating (SIG), and a CMOS line sensor within a small form factor. The SIG facilitates high angular dispersion of light on a planar focal plane, resulting in an average spectral resolution of 5.8 nm, with over 76% maximum sensitivity from 400 to 800 nm. SIG-µSPEC measures the spectral reflectance of fruits at different ripening stages, clearly revealing changes in the chlorophyll absorption band. The measured spectrum is further utilized for the precise prediction of the soluble solid content (SSC) levels, achieving a high correlation (R2 = 0.91) and a ratio of prediction-to-deviation of 2.36. This compact microspectrometer holds the potential for precise and non-invasive spectral analysis across point-of-care fields.

Real-Time Detection of Strawberry Ripeness Using Augmented Reality and Deep Learning.

Currently, strawberry harvesting relies heavily on human labour and subjective assessments of ripeness, resulting in inconsistent post-harvest quality. Therefore, the aim of this work is to automate this process and provide a more accurate and efficient way of assessing ripeness. We explored a unique combination of YOLOv7 object detection and augmented reality technology to detect and visualise the ripeness of strawberries. Our results showed that the proposed YOLOv7 object detection model, which employed transfer learning, fine-tuning and multi-scale training, accurately identified the level of ripeness of each strawberry with an mAP of 0.89 and an F1 score of 0.92. The tiny models have an average detection time of 18 ms per frame at a resolution of 1280 × 720 using a high-performance computer, thereby enabling real-time detection in the field. Our findings distinctly establish the superior performance of YOLOv7 when compared to other cutting-edge methodologies. We also suggest using Microsoft HoloLens 2 to overlay predicted ripeness labels onto each strawberry in the real world, providing a visual representation of the ripeness level. Despite some challenges, this work highlights the potential of augmented reality to assist farmers in harvesting support, which could have significant implications for current agricultural practices.

Development of Indicator Film Based on Cassava Starch-Chitosan Incorporated with Red Dragon Fruit Peel Anthocyanins-Gambier Catechins to Detect Banana Ripeness.

Banana ripeness is generally determined based on physical attributes, such as skin color; however, it is considered subjective because it depends on individual factors and lighting conditions. In addition, improper handling can cause mechanical damage to the fruit. Intelligent packaging in the form of indicator film incorporated with anthocyanins from red dragon fruit peel has been applied for shrimp freshness detection; however, this film has low color stability during storage, necessitating the addition of gambier catechins as a co-pigment to increase anthocyanin stability. Nevertheless, the characteristics of films that contain gambier catechins and their applications to bananas have not been studied yet; therefore, this study aims to develop and characterize indicator films that were incorporated with red dragon fruit peel anthocyanins and gambier catechins to detect banana ripeness. In this study, the indicator films were made via solvent casting. The films were characterized for their structural, mechanical, and physicochemical properties, and then applied to banana packaging. The results show that the film incorporated with anthocyanins and catechins in a ratio of 1:40 (w/w) resulted in better color stability, mechanical properties, light and water vapor barrier ability, and antioxidant activity. The application of the indicator films to banana packaging resulted in a change in color on the third day of storage. It can be concluded that these films could potentially be used as an indicator to monitor banana ripeness.

A fine recognition method of strawberry ripeness combining Mask R-CNN and region segmentation.

As a fruit with high economic value, strawberry has a short ripeness period, and harvesting at an incorrect time will seriously affect the quality of strawberries, thereby reducing economic benefits. Therefore, the timing of its harvesting is very demanding. A fine ripeness recognition can provide more accurate crop information, and guide strawberry harvest management more timely and effectively. This study proposes a fine recognition method for field strawberry ripeness that combines deep learning and image processing. The method is divided into three stages: In the first stage, self-calibrated convolutions are added to the Mask R-CNN backbone network to improve the model performance, and then the model is used to extract the strawberry target in the image. In the second stage, the strawberry target is divided into four sub-regions by region segmentation method, and the color feature values of B, G, L, a and S channels are extracted for each sub-region. In the third stage, the strawberry ripeness is classified according to the color feature values and the results are visualized. Experimental results show that with the incorporation of self-calibrated convolutions into the Mask R-CNN, the model's performance has been substantially enhanced, leading to increased robustness against diverse occlusion interferences. As a result, the final average precision (AP) has improved to 0.937, representing a significant increase of 0.039 compared to the previous version. The strawberry ripeness classification effect is the best on the SVM classifier, and the accuracy under the combined channel BGLaS reaches 0.866. The classification results are better than common manual feature extraction methods and AlexNet, ResNet18 models. In order to clarify the role of the region segmentation method, the contribution of different sub-regions to each ripeness is also explored. The comprehensive results demonstrate that the proposed method enables the evaluation of six distinct ripeness levels of strawberries in the complex field environment. This method can provide accurate decision support for strawberry refined planting management.