Computer vision model for estimating the mass and volume of freshly harvested Thai apple ber (Ziziphus mauritiana L.) and its variation with storage days

Mansuri, Shekh Mukhtar; Gautam, Prem Veer; Jain, Dilip; Nickhil, C.; Pramendra,

doi:10.1016/j.scienta.2022.111436

Cited by 16 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple sensors have been used for image acquisition in on-farm sorting and transportation, including a red-green-blue (RGB) camera, a charge-coupled device (CCD) camera, a hyperspectral camera, a near-infrared (NIR) sensor, visible and near-infrared spectroscopy, and a thermal camera. According to previous studies, the RGB camera is currently the most widely employed for on-farm sorting, especially for surface damage detection, color grading, mass and volume estimation of apples, and ripeness of avocados ( Jaramillo-Acevedo et al., 2020 ; Lu et al., 2022 ; Mansuri et al., 2022 ). A CCD camera was utilized for the size and color grading of apples and mass grading of mangoes ( Momin et al., 2017 ; Zhang et al., 2021 ).…”

Section: Data Acquisition Sensors and Techniques For On-farm Sorting ...mentioning

confidence: 99%

“…Various image processing methods and deep learning models have been introduced to achieve automated on-farm sorting. Artificial neural network (ANN) and support vector machine (SVM) models have been developed to estimate the mass and volume of apples and mangoes ( Utai et al., 2019 ; Mansuri et al., 2022 ). Classification of bruises in blueberries was performed using linear discriminant analysis, SVM, random forest (RF), K-nearest-neighbors, and logistic regression classifiers ( Kuzy et al., 2018 ).…”

Section: Ai Models For On-farm Sorting and Transportationmentioning

confidence: 99%

“…In previous studies, datasets were mostly built for individual research using limited varieties and cultivars. Fruit samples were randomly selected to ensure the diversity of the dataset, and the fruit quality used as a reference for the AI models was manually checked and classified by experts ( Caladcad et al., 2020 ; Mansuri et al., 2022 ; Wang et al., 2022 ). These data collections to build datasets were conducted for individual research, which could lead to tendencies of model overfitting and reduce the accuracy of the AI model.…”

Section: Challenges and Future Directions For Ai In On-farm Sorting A...mentioning

confidence: 99%

See 2 more Smart Citations

Advancement in artificial intelligence for on-farm fruit sorting and transportation

Zhou

Zahid

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

On-farm sorting and transportation of postharvest fruit include sorting out defective products, grading them into categories based on quality, distributing them into bins, and carrying bins to field collecting stations. Advances in artificial intelligence (AI) can speed up on-farm sorting and transportation with high accuracy and robustness and significantly reduce postharvest losses. The primary objective of this literature review is to provide an overview to present a critical analysis and identify the challenges and opportunities of AI applications for on-farm sorting and transportation, with a focus on fruit. The challenges of on-farm sorting and transportation were discussed to specify the role of AI. Sensors and techniques for data acquisition were investigated to illustrate the tasks that AI models have addressed for on-farm sorting and transportation. AI models proposed in previous studies were compared to investigate the adequate approaches for on-farm sorting and transportation. Finally, the advantages and limitations of utilizing AI have been discussed, and in-depth analysis has been provided to identify future research directions. We anticipate that this survey will pave the way for further studies on the implementation of automated systems for on-farm fruit sorting and transportation.

show abstract

Section: Data Acquisition Sensors and Techniques For On-farm Sorting ...mentioning

confidence: 99%

Section: Ai Models For On-farm Sorting and Transportationmentioning

confidence: 99%

Section: Challenges and Future Directions For Ai In On-farm Sorting A...mentioning

confidence: 99%

See 1 more Smart Citation

Advancement in artificial intelligence for on-farm fruit sorting and transportation

Zhou

Zahid

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…The relationships between geometric properties and mass have been used by different researchers to develop models for predicting fruits' mass, ranging from single variable linear and non‐linear regressions to more complex multi‐variable machine learning models. For regular or uniform‐shaped fruits such as pomegranate, mandarin, apples, and limes, single variable models are often optimal for modeling mass (Khoshnam et al, 2007; Mahawar et al, 2019; Mansuri et al, 2022). However, for nonuniform‐shaped fruits, the mass may be better predicted with multiple variables (Schulze et al, 2015; Spreer & Müller, 2011; Utai et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

The influence of papaya shape on its mass model and mechanical properties

Aina,

Harith,

Hashim

et al. 2024

J Food Process Engineering

View full text Add to dashboard Cite

Postharvest handling tasks include fruit grading and minimizing loss. Fruits are often packaged into grades based on size and mass for uniformity and proper handling. Losses caused by mechanical damage can be reduced by understanding the fruit's response to loads. Papaya's (cv. Exotica) irregular shape and short shelf‐life are important factors for proper handling. This study aimed to develop a model for papaya mass based on geometric properties and to characterize its mechanical behavior when compressed along its major axis. For mass prediction, single‐ and multiple‐variable regression models using papaya's geometrical variables were developed. Despite its irregular shape, similar performance was observed in the best single‐ and multiple‐variable mass models (R2 ≈ 0.95, RMSE ≈ 82 g). However, the single‐variable model is likely more practical because only two axial lengths are needed and can be extracted from 2D images. For papaya's mechanical behavior, the results for elastic properties indicate some variations (p > 0.05) in elastic modulus, and failure stress and strain along the major axis, while results for viscoelastic properties indicate significant variation (p < 0.05) in the relaxation moduli. Overall, the bottom section is less resistant to deformation compared to the top. Therefore, reducing compression in the section could potentially reduce damage. Using the mechanical properties described here in computer simulation studies may provide more detailed load distribution. Mass modeling can aid the automation of papaya grading, while mechanical response characterization provides valuable information for designing postharvest handling systems.Practical ApplicationsPostharvest handling tasks include fruit grading and minimizing loss. Fruits are often packaged into grades based on size and mass for uniformity and proper handling. Losses caused by mechanical damage may be reduced by understanding the fruit's response to loads. Papaya's irregular shape and short shelf‐life are important factors for proper postharvest handling. Mass modeling can assist the automation of papaya sorting, while characterizing its mechanical response can assist the design of postharvest handling systems. The mass model result indicates that papaya's mass (cv. Exotica) can be predicted using two axial lengths, which can be easily obtained using 2D images. The advantage is that this task can be combined with other tasks using imaging data. While the mechanical properties of papaya indicate that its bottom section is more susceptible to deformation compared to the top when they are stored in an environment with minimal movements over an extended period. Therefore, in this setup, applying the compression load at the top section while minimizing compression load at the bottom may be more effective in preventing and minimizing mechanical damage.

show abstract

“…CVS is capable of producing consistent, objective, and rapid results on a real‐time basis. It has been extensively used to assess the color, texture, volume, and mass of fruits and vegetables (Chacon et al, 2022; Mansuri et al, 2022; Rafiq et al, 2016). It also helps to study the dynamic and complex nature of the drying process, meet stringent product quality characteristics and attain a better understanding of the process for further optimization of the standard operating methods (Zang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Long short‐term memory based real‐time monitoring of potato slice drying using image chromatic features

Sabat

Kotwaliwale

Chakraborty

et al. 2022

Food Processing Preservation

View full text Add to dashboard Cite

Potato is the fourth most important crop in the world after rice, wheat, and corn. Considered a healthy, low-fat, economical food, it is the only noncereal crop that has the potential to eliminate malnutrition and hunger while ensuring food security. In most of the unorganized sectors of India, potatoes are sliced, blanched, dried, stored, and consumed as a snack food throughout the year. Hot air drying is the most popular method after open sun drying. During drying, the dynamics of moisture and temperature gradient have opposite effects. The strength of these gradients determine the product quality. A stronger moisture gradient produces a good quality product; otherwise, there can be issues like case-hardening and crusting of the surface and the edges (Zhao & Gao, 2016), leading to poor product quality and early spoilage.The product moisture is the indicator of the drying condition of the product. Conventionally, the weight measurement method determines the sample moisture content during drying. This method is very accurate but requires human intervention, which poses a higher chance of contamination of the product and is not very practicable in the case of continuous dryers. Additionally, in hot air drying, using a continuous weight-measuring system like a load cell is not feasible, as the incoming hot air creates vibrations that interfere with the performance of a sensor-based weight measurement system. Change in chromatic properties of the products is one of the primary visual

show abstract

Computer vision model for estimating the mass and volume of freshly harvested Thai apple ber (Ziziphus mauritiana L.) and its variation with storage days

Cited by 16 publications

References 31 publications

Advancement in artificial intelligence for on-farm fruit sorting and transportation

Advancement in artificial intelligence for on-farm fruit sorting and transportation

The influence of papaya shape on its mass model and mechanical properties

Long short‐term memory based real‐time monitoring of potato slice drying using image chromatic features

Contact Info

Product

Resources

About