Development and assessment of different modeling approaches for size-mass estimation of mango fruits (Mangifera indica L., cv. ‘Nam Dokmai’)

Schulze, Katrin; Nagle, Marcus; Spreer, Wolfram; Mahayothee, Busarakorn; Müller, Joachim

doi:10.1016/j.compag.2015.04.013

Cited by 51 publications

(36 citation statements)

References 24 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A score between zero and unity indicates the model's acceptability while unity indicates the model's optimal performance. The NSE and R 2 have been used as a performance indicator in similar study (Schulze et al, 2015).…”

Section: Rulementioning

confidence: 99%

Clustered ANFIS weighing models for sweet lime (Citrus limetta) using computer vision system

Phate

Ramanathan

Palanisamy

2019

J Food Process Engineering

View full text Add to dashboard Cite

In the present research work, a clustered adaptive neuro‐fuzzy inference system (ANFIS) is used to develop the model of relationship between the weight with 1D and 2D features of the Indian sweet lime fruit extracted through the developed computer vision system. Initially, three clustering methods are used to classify the input data into a homogeneous group. Then, the self‐learning proficiency of an artificial neural network and the ability of fuzzy theory to deal with the uncertainty and nonlinearity are utilized by developing the ANFIS model. Finally, the clustered data is combined with the ANFIS models trained by two different learning methods are analyzed. The goodness‐of‐fit indicators close to unity and the lower values of the error performance metrics implies the adequacy, robustness, and superiority of the proposed method. Moreover, the lower value of Theil's coefficient for uncertainty (UII) signifies the credibility of the model to predict the weight of a sweet lime fruit. Practical applications The presented improved approach of clustered ANFIS modeling for weighing sweet lime fruit will be fruitful to the researchers, farmers, and engineers. In order to, design and develop the real time weight‐based grading, sorting, and packaging machine's knowledge about the fruit weight‐size relation is a basic requirement. Use of this proposed approach (computer vision linked with the clustered ANFIS model) will greatly reduce the handling of the fruit as well as the workload that are responsible for the qualitative and quantitative losses of fruits on bulk industrial scale. Also, this weighing model using 1D and 2D features will be more beneficial, faster, and economically viable substitute to the on‐field manual method used in agriculture specially during the sorting, grading, and packaging of sweet lime.

show abstract

Section: Rulementioning

confidence: 99%

Clustered ANFIS weighing models for sweet lime (Citrus limetta) using computer vision system

Phate

Ramanathan

Palanisamy

2019

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…Thus, the usage of weighing devices can be eliminated from the packaging line. Spreer [28] and Schulze [29] determined the mass of the Chok Anan mangoes and Nam Dokmai mangoes using the physical properties of the mango. Relationships between the physical traits were determined and a high correlation between the mass and the physical traits was found.…”

Section: Resultsmentioning

confidence: 99%

In-Line Sorting of Harumanis Mango Based on External Quality Using Visible Imaging

Ibrahim

Saad

Zakaria

et al. 2016

Sensors

View full text Add to dashboard Cite

The conventional method of grading Harumanis mango is time-consuming, costly and affected by human bias. In this research, an in-line system was developed to classify Harumanis mango using computer vision. The system was able to identify the irregularity of mango shape and its estimated mass. A group of images of mangoes of different size and shape was used as database set. Some important features such as length, height, centroid and parameter were extracted from each image. Fourier descriptor and size-shape parameters were used to describe the mango shape while the disk method was used to estimate the mass of the mango. Four features have been selected by stepwise discriminant analysis which was effective in sorting regular and misshapen mango. The volume from water displacement method was compared with the volume estimated by image processing using paired t-test and Bland-Altman method. The result between both measurements was not significantly different (P > 0.05). The average correct classification for shape classification was 98% for a training set composed of 180 mangoes. The data was validated with another testing set consist of 140 mangoes which have the success rate of 92%. The same set was used for evaluating the performance of mass estimation. The average success rate of the classification for grading based on its mass was 94%. The results indicate that the in-line sorting system using machine vision has a great potential in automatic fruit sorting according to its shape and mass.

show abstract

“…Schulze et al 31 compared three different models for mass estimation of mango fruits, using simple linear regression, multiple linear regression and artificial neural networks; they found that the latter method was the most accurate and robust model for mass estimation. Predictive accuracy of machine learning and linear regression techniques for crop yield in 10 crop datasets was also compared 32 ; the results showed that M5-Prime model trees achieved the largest number of crop yield predictions with the lowest errors (and they are more interpretable than K-Nearest Neighbours, the other system with lowest error).…”

Section: Introductionmentioning

confidence: 99%

Using regression trees to predict citrus load balancing accuracy and costs

Bóbeda¹,

Combarro²,

Mazza³

et al. 2018

IJCIS

View full text Add to dashboard Cite

In order to define management and marketing strategies, farmers need adequate knowledge about future yield with the greatest possible accuracy and anticipation. In citrus orchards, greater variability and non-normality of yield distributions complicate the early estimation of fruit production. This study was conducted with the objective of developing a method to estimate citrus load based on orchard characteristics, morphological information of trees and number of fruits in defined locations of the crow. Field data from 16 citrus orchards obtained from 2005/06 through 2013/14 seasons were used. Machine learning techniques were applied to predict yield; these methods can reduce the estimation error as well as decrease the need for in-field measuring, thus reducing both the cost and time of the process.

show abstract

Development and assessment of different modeling approaches for size-mass estimation of mango fruits (Mangifera indica L., cv. ‘Nam Dokmai’)

Cited by 51 publications

References 24 publications

Clustered ANFIS weighing models for sweet lime (Citrus limetta) using computer vision system

Clustered ANFIS weighing models for sweet lime (Citrus limetta) using computer vision system

In-Line Sorting of Harumanis Mango Based on External Quality Using Visible Imaging

Using regression trees to predict citrus load balancing accuracy and costs

Contact Info

Product

Resources

About