Recognising blueberry fruit of different maturity using histogram oriented gradients and colour features in outdoor scenes

Tan, Kun; Lee, Won Suk; Gan, Hao; Wang, Shuwen

doi:10.1016/j.biosystemseng.2018.08.011

Cited by 99 publications

(43 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous fruit maturity classification research resulted in similar classification accuracies (melon with 85.7% [ 62 ], banana with 87.1% [ 30 ], passion fruit with 91.5% [ 27 ], blueberry with 94% [ 36 ], papaya with 94.3% [ 40 ], date with 96.9% [ 39 ], and tomato with 99.31% [ 34 ]). However, this comparison is very limited due to several reasons; most of these fruits have uniform maturity patterns; all research were based on a single and usually random viewpoint of the fruit, and each research used a different classification method that varies in the amount of data needed and its computational complexity.…”

Section: Resultsmentioning

confidence: 88%

“…Image processing and machine vision for the maturity level classification of fruits have been intensively investigated [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 ]. Most work to date has focused on maturity analysis of fruit that ripen in a uniform fashion, such as tomato [ 32 , 33 , 34 ], passion fruit [ 27 ], apricot [ 24 ], persimmon [ 35 ], blueberry [ 36 , 37 ], cherry [ 38 ], and date [ 39 ]. Different methods were used for classification (e.g., support vector machines [ 27 , 36 ], convolutional neural networks [ 34 , 39 ], random forest [ 40 ], K-nearest neighbor [ 33 ], and linear discriminant analysis [ 35 ]) based on different sensors (e.g., RGB—Red Green Blue [ 29 , 33 , 35 , 36 ], RGB-D—Red Green Blue-Depth [ 27 ], and NIR—Near Infra-Red [ 38 ]).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Viewpoint Analysis for Maturity Classification of Sweet Peppers

Harel

Essen

Parmet

et al. 2020

Sensors

View full text Add to dashboard Cite

The effect of camera viewpoint and fruit orientation on the performance of a sweet pepper maturity level classification algorithm was evaluated. Image datasets of sweet peppers harvested from a commercial greenhouse were collected using two different methods, resulting in 789 RGB—Red Green Blue (images acquired in a photocell) and 417 RGB-D—Red Green Blue-Depth (images acquired by a robotic arm in the laboratory), which are published as part of this paper. Maturity level classification was performed using a random forest algorithm. Classifications of maturity level from different camera viewpoints, using a combination of viewpoints, and different fruit orientations on the plant were evaluated and compared to manual classification. Results revealed that: (1) the bottom viewpoint is the best single viewpoint for maturity level classification accuracy; (2) information from two viewpoints increases the classification by 25 and 15 percent compared to a single viewpoint for red and yellow peppers, respectively, and (3) classification performance is highly dependent on the fruit’s orientation on the plant.

show abstract

Section: Resultsmentioning

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Viewpoint Analysis for Maturity Classification of Sweet Peppers

Harel

Essen

Parmet

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The United States is the world’s largest producer of blueberries [ 39 ]. More recently, Andalusia, Spain, has become an important producer and is at present the largest producer in Europe (51.569 tonnes in 2019) [ 40 ].…”

Section: Introductionmentioning

confidence: 99%

Anthocyanins in Blueberries Grown in Hot Climate Exert Strong Antioxidant Activity and May Be Effective against Urinary Tract Bacteria

et al. 2020

View full text Add to dashboard Cite

Anthocyanins are extensively studied for their health-related properties, including antibacterial activity against urinary tract infections (UTI). Among common fruits, blueberries, with their remarkable antioxidant capacity, are one of the richest sources. Anthocyanin-rich extracts were obtained from four varieties: Snowchaser, Star, Stella Blue and Cristina Blue, grown in the hot climate of Southern Spain. Their total anthocyanins contents (TAC) were determined spectrophotometrically, and the anthocyanin profile by ultra high performance liquid chromatography—tandem mass spectrometer (UHPLC-MS/MS). Their antioxidant activity was assessed by oxygen radical absorbance capacity (ORAC) assay, while antibacterial activity against strains isolated from UTI patients was assessed in vitro, helping to select the varieties with the highest bioactive potential. Star showed the highest TAC and antioxidant activity (1663 ± 159 mg of cyanidin-3-O-glucoside (cy-3-O-glu) equivalents/100 g fresh weight (FW), 6345 ± 601 μmol Trolox equivalents (TE)/100 g FW, respectively), followed by Cristina Blue, Stella Blue and Snowchaser. As far as we know, this is the first time that cyanidin-3-rutinoside has been identified in blueberries. The extracts inhibited all the tested strains, MICs ranging from 0.4 mg/mL (for Stella Blue extract against UTI P. aeruginosa) to 9.5 mg/mL (for all extracts against UTI K. pneumoniae ssp. pneumoniae). This is the first study that assessed in vitro the antibacterial activity of blueberries against Klebsiella pneumoniae, Providencia stuartii and Micrococcus spp. strains isolated from UTI.

show abstract

“…Based on image processing techniques, three fresh tomato maturity levels (green, orange and red) were identified by Wan et al [21], where the average blue-channel intensity and the hues of pixels in the maximum inscribed circle within each tomato’s surface were extracted and then classified with a backpropagation neural network; the average accuracy of the three maturity levels reached 99.31%. Tan et al [22] proposed a stepwise, computer vision-based algorithm to recognize the maturity stages of blueberries (mature, intermediate and young), and the recognition pipeline attained an average accuracy of 92.07%; specifically, the fruit regions were first located using histogram-oriented gradients and feature attributes in the International Commission on Illumination (CIE) L*a*b* color space, and then the maturity of a located blueberry was determined using template matching with a weighted Euclidean distance. Marimuthu et al [23] formulated a particle swarm optimized fuzzy model to grade banana fruits into unripe, ripe and overripe stages using peel color attributes extracted from the hue channel and opponent colors in CIE L*a*b* space, achieving an average classification accuracy of 93.11%.…”

Section: Introductionmentioning

confidence: 99%

Assessment of External Properties for Identifying Banana Fruit Maturity Stages Using Optical Imaging Techniques

Zhuang

Hou

Tang

et al. 2019

Sensors

View full text Add to dashboard Cite

The maturity stage of bananas has a considerable influence on the fruit postharvest quality and the shelf life. In this study, an optical imaging based method was formulated to assess the importance of different external properties on the identification of four successive banana maturity stages. External optical properties, including the peel color and the local textural and local shape information, were extracted from the stalk, middle and tip of the bananas. Specifically, the peel color attributes were calculated from individual channels in the hue-saturation-value (HSV), the International Commission on Illumination (CIE) L*a*b* and the CIE L*ch color spaces; the textural information was encoded using a local binary pattern with uniform patterns (UP-LBP); and the local shape features were described by histogram of oriented gradients (HOG). Three classifiers based on the naïve Bayes (NB), linear discriminant analysis (LDA) and support vector machine (SVM) algorithms were adopted to evaluate the performance of identifying banana fruit maturity stages using the different optical appearance features. The experimental results demonstrate that overall identification accuracies of 99.2%, 100% and 99.2% were achieved using color appearance features with the NB, LDA and SVM classifiers, respectively; overall accuracies of 92.6%, 86.8% and 93.4% were obtained using local textural features for the three classifiers, respectively; and overall accuracies of only 84.3%, 83.5% and 82.6% were obtained using local shape features with the three classifiers, respectively. Compared to the complicated calculation of both the local textural and local shape properties, the simplicity and high accuracy of the peel color property make it more appropriate for identifying banana fruit maturity stages using optical imaging techniques.

show abstract

Recognising blueberry fruit of different maturity using histogram oriented gradients and colour features in outdoor scenes

Cited by 99 publications

References 23 publications

Viewpoint Analysis for Maturity Classification of Sweet Peppers

Viewpoint Analysis for Maturity Classification of Sweet Peppers

Anthocyanins in Blueberries Grown in Hot Climate Exert Strong Antioxidant Activity and May Be Effective against Urinary Tract Bacteria

Assessment of External Properties for Identifying Banana Fruit Maturity Stages Using Optical Imaging Techniques

Contact Info

Product

Resources

About