Potato quality grading based on machine vision and 3D shape analysis

Su, Qinghua; Kondo, Naoshi; Li, Minzan; Sun, Hong; Riza, Dimas Firmanda Al; Habaragamuwa, Harshana

doi:10.1016/j.compag.2018.07.012

Cited by 65 publications

(26 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Root growth and its distribution not only affect the absorption of water and nutrients of root, but also directly affect the growth of fruit trees and the quality and yield of apples. At present, machine vision is mainly concentrated in the upper part of the study of plants, such as the measurement of sunflower flower size by image processing [3], the classification of potato quality by machine vision and three-dimensional image [4], the estimation of apple fruit size by 3D technology [5], etc. The physical measurement of root morphological parameters mainly relies on the root scanners currently available in the market.…”

Section: Discussionmentioning

confidence: 99%

“…With the development of machine vision technology and research in the field of plant science, it has been widely used in the identification of plant species, plant growth information detection, quality inspection and classification of agricultural products as well as visual navigation of farmland. For example, Sunoj et al proposed measuring the size of sunflowers by machine vision in 2018 [3], Qinghua et al put forward to classify potato quality by machine vision in 2018 [4], Gongal et al proposed estimating the size of apple fruit by 3D machine vision in 2018 [5], Benoit et al simulated image acquisition in machine vision for seedling elongation, root segmentation algorithm for image processing validation in 2014 [6]. The application of machine vision-assisted electronic image analysis systems increases the precision and efficiency of plant production and avoids the subjective effects of human observation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Study on measurement method for apple root morphological parameters based on Labview

et al. 2019

View full text Add to dashboard Cite

BackgroundTraditional measurements of apple seedling roots often rely on manual measurements and existing root scanners on the market. Manual measurement requires a lot of labor and time, and subjective reasons may cause the uncertainty of data; root scanners have limited scanning size and expensive. In case of fruit roots, coverage and occlusion issues will occur, resulting in inaccurate results, but our research solved this problem.ResultsThe background plate was selected according to the color of the seedling roots; the image of the roots of the collected apple seedlings was preprocessed with Vision Development Module by combining image and Labview. The root surface area, average root diameter, root length and root volume of apple seedlings were measured by combining root characteristic parameters algorithm. In order to verify the effectiveness of the proposed method, a set of measurement system for root morphology of apple seedlings was designed, and the measurement result was compared with the Canadian root system WinRHIZO 2016 (Canada). With application of SPSS v22.0 analysis, the significance P > 0.01 indicated that the difference was not significant. The relative error of surface area was less than 0.5%. The relative error of the average diameter and length of the root system was less than 0.1%, and the relative error of the root volume was less than 0.2%.ConclusionsIt not only proved that the root surface area, average root diameter, root length and root volume of apple seedlings could be accurately measured by the method described herein, which was handy in operation, but also reduced the cost by 80–90% compared with the conventional scanner.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Study on measurement method for apple root morphological parameters based on Labview

et al. 2019

View full text Add to dashboard Cite

show abstract

“…This technology combined with image processing, pattern recognition, and artificial intelligence technology can detect samples in a noncontact manner [2]. The color [3], size [4], shape [5], and other apparent features of the sample can be analyzed and processed from collected images for detection. However, some characteristics are difficult to detect because traditional machine vision is conducted at visible wavelengths [6].…”

Section: Introductionmentioning

confidence: 99%

Integration of Partial Least Squares Regression and Hyperspectral Data Processing for the Nondestructive Detection of the Scaling Rate of Carp (Cyprinus carpio)

Wang

Zhu

Zhang

et al. 2020

Foods

View full text Add to dashboard Cite

The scaling rate of carp is one of the most important factors restricting the automation and intelligence level of carp processing. In order to solve the shortcomings of the commonly-used manual detection, this paper aimed to study the potential of hyperspectral technology (400–1024.7 nm) in detecting the scaling rate of carp. The whole fish body was divided into three regions (belly, back, and tail) for analysis because spectral responses are different for different regions. Different preprocessing methods, including Savitzky–Golay (SG), first derivative (FD), multivariate scattering correction (MSC), and standard normal variate (SNV) were applied for spectrum pretreatment. Then, the successive projections algorithm (SPA), regression coefficient (RC), and two-dimensional correlation spectroscopy (2D-COS) were applied for selecting characteristic wavelengths (CWs), respectively. The partial least square regression (PLSR) models for scaling rate detection using full wavelengths (FWs) and CWs were established. According to the modeling results, FD-RC-PLSR, SNV-SPA-PLSR, and SNV-RC-PLSR were determined to be the optimal models for predicting the scaling rate in the back (the coefficient of determination in calibration set (RC2) = 96.23%, the coefficient of determination in prediction set (RP2) = 95.55%, root mean square error by calibration (RMSEC) = 6.20%, the root mean square error by prediction (RMSEP)= 7.54%, and the relative percent deviation (RPD) = 3.98), belly (RC2 = 93.44%, RP2 = 90.81%, RMSEC = 8.05%, RMSEP = 9.13%, and RPD = 3.07) and tail (RC2 = 95.34%, RP2 = 93.71%, RMSEC = 6.66%, RMSEP = 8.37%, and RPD = 3.42) regions, respectively. It can be seen that PLSR integrated with specific pretreatment and dimension reduction methods had great potential for scaling rate detection in different carp regions. These results confirmed the possibility of using hyperspectral technology in nondestructive and convenient detection of the scaling rate of carp.

show abstract

“…This technique has been widely used to evaluate the quality of fruits and vegetables [6,7]. As reported by many authors, computer vision systems have been used for potato quality grading [4,8], strawberry industrial classification [9], soybean quality evaluation [10], papaya disease recognition [11], apple sorting and quality inspection [12], classification of pepper seeds [13], quality evaluation in fresh-cut lettuce [14], grading of fried figs [5] and many other food products as discussed in [15]. In [16], the authors present an automatic leaf image classification system for sunflower crops using neural networks with selected features.…”

Section: Introductionmentioning

confidence: 99%

Quality and Defect Inspection of Green Coffee Beans Using a Computer Vision System

García

Candelo-Becerra²,

Hoyos

2019

Applied Sciences

View full text Add to dashboard Cite

There is an increased industry demand for efficient and safe methods to select the best-quality coffee beans for a demanding market. Color, morphology, shape and size are important factors that help identify the best quality beans; however, conventional techniques based on visual and/or mechanical inspection are not sufficient to meet the requirements. Therefore, this paper presents an image processing and machine learning technique integrated with an Arduino Mega board, to evaluate those four important factors when selecting best-quality green coffee beans. For this purpose, the k-nearest neighbor algorithm is used to determine the quality of coffee beans and their corresponding defect types. The system consists of logical processes, image processing and the supervised learning algorithms that were programmed with MATLAB and then burned into the Arduino board. The results showed this method has a high effectiveness in classifying each single green coffee bean by identifying its main visual characteristics, and the system can handle several coffee beans present in a single image. Statistical analysis shows the process can identify defects and quality with high accuracy. The artificial vision method was helpful for the selection of quality coffee beans and may be useful to increase production, reduce production time and improve quality control.

show abstract

Potato quality grading based on machine vision and 3D shape analysis

Cited by 65 publications

References 7 publications

Study on measurement method for apple root morphological parameters based on Labview

Study on measurement method for apple root morphological parameters based on Labview

Integration of Partial Least Squares Regression and Hyperspectral Data Processing for the Nondestructive Detection of the Scaling Rate of Carp (Cyprinus carpio)

Quality and Defect Inspection of Green Coffee Beans Using a Computer Vision System

Contact Info

Product

Resources

About