Image matching algorithm of defects on navel orange surface based on compressed sensing

Xie, Xin; Ge, Songlin; Xie, Mingye; Hu, Fengping; Jiang, Nan; Li, Bo

doi:10.1007/s12652-018-0833-0

Cited by 5 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Surface injuries include fruit blemishes, burns, and wrong structures. [18,30,32,38,40,43,49,55,61,71,77,79,82,83,85,87] Chilling/freezing disorders This post-harvest disorder occurs due to the chilling effect, and it is a catastrophic disorder that evolves with the storage of fruits at low temperatures that notably demotes the quality of citrus fruits in the market or disqualifies them from the market. The impact of the chilling disorder depends upon the temperature at which fruits are to be stored or the duration of the time spent by the fruit in cold storage.…”

Section: Wind Scarmentioning

confidence: 99%

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Dhiman¹,

Kaur

Balasaraswathi

et al. 2023

Sustainability

View full text Add to dashboard Cite

Different kinds of techniques are evaluated and analyzed for various classification models for the detection of diseases of citrus fruits. This paper aims to systematically review the papers that focus on the prediction, detection, and classification of citrus fruit diseases that have employed machine learning, deep learning, and statistical techniques. Additionally, this paper explores the present state of the art of the concept of image acquisition, digital image processing, feature extraction, and classification approaches, and each one is discussed separately. A total of 78 papers are selected after applying primary selection criteria, inclusion/exclusion criteria, and quality assessment criteria. We observe that the following are widely used in the selected studies: hyperspectral imaging systems for the image acquisition process, thresholding for image processing, support vector machine (SVM) models as machine learning (ML) models, convolutional neural network (CNN) architectures as deep learning models, principal component analysis (PCA) as a statistical model, and classification accuracy as evaluation parameters. Moreover, the color feature is the most popularly used feature for the RGB color space. From the review studies that performed comparative analyses, we find that the best techniques that outperformed other techniques in their respective categories are as follows: SVM among the ML methods, ANN among the neural network networks, CNN among the deep learning methods, and linear discriminant analysis (LDA) among the statistical techniques.This study concludes with meta-analysis, limitations, and future research directions.

show abstract

Section: Wind Scarmentioning

confidence: 99%

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Dhiman¹,

Kaur

Balasaraswathi

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…A comparison between the extracted features from an axial and transversal radiograph of endoxerated lemon fruit is conducted [17]. Different shape features are derived using binary images in the study [51]. Using multiple linear regression, size features like length and width of the principal axis are measured with the employed algorithm while polar and equatorial diameters were determined manually.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Center-finding routine, eight radii, perimeter tracing, shape factor ratio, area normalized values for delta and delta2values, (diameter.ˆ,./diameterequator) [43] Orange Major and minor axis length, perimeter, the image area [46] Orange Major and minor axis length, perimeter, area [69] Navel Orange Surface area and coloring area [51] Orange Length, width, elongation, circularity, major axis length and minor axis length, width, length, area, perimeter [53] Orange Area, fractal dimension, box-counting dimension, [55] Lemon Area, Major axis, and Minor axis [60] Apple, litchi, mosambi, pomegranate, and pears…”

Section: Papermentioning

confidence: 99%

“…[47] Tangerine varieties Florida grapefruit and orange 98.5% for grapefruit and orange and 98.3% for tangerine [48] 47 citrus fruits(Satsuma mandarins) Absolute error 2.48 [49] Images of immature (green) fruits and tangerine sugar belle leaves were taken from an experiment orchard at Immokalee, Florida, USA 96% [50] 320 oranges image (salustiana) Maturity index=0.31 [51] 303 images Kinnow mandarin fruits from Punjab Agriculture University, Ludhiana (India) 98.66% [52] 32 images of healthy oranges, 30 samples of medium-quality oranges, and 31 images of low-quality or faulty MLP-84.9%,RBF network-83.9%,SMO-86.0% [53] Orange samples of 100 healthy and damaged were hand-picked across orange farms over Nilgiri hills, Tamil Nadu, India 94.50% [54] 104 CBS positive citrus fruits and 30 CBS negative samples 93.40% [56] A total of 180 grapefruits were harvested with healthy and five infected peels 96.00% [57] For the maturity trial, 100 'Unshiu' citrus fruits were assigned and the remaining 200 fruits were used for the fault experiment. 97% [58] 2000 samples of different fruits including the litchi, pears apple, pomegranate, and mosambi were generated 99% [60] 5632 Table 12 shows the name of the dominant journal, including its impact factor and H-index.…”

Section: Papermentioning

confidence: 99%

See 1 more Smart Citation

Citrus Fruit Disease Detection Techniques: A Survey and Comparative Analysis of Relevant Approaches

Dhiman,

Kaur,

Kukreja

2023

IJCDS

View full text Add to dashboard Cite

The incorporation of computer vision in contemporary agriculture has witnessed significant advancements, particularly in detecting diseases and deficiencies affecting citrus fruit production. This study provides an in-depth comparative analysis of several limitations of the citrus fruit detection system and the cutting-edge machine vision algorithms used for classification. Traditional diagnostic methods are initially reviewed, followed by an elaborate discussion on various image acquisition techniques such as remote sensing, hyperspectral imaging, bio speckle laser imaging, and color imaging. These techniques focus on extracting features like color, texture, and size for diagnosing citrus fruit diseases. Despite their effectiveness, the images obtained might contain noise and distortions. The study details two crucial steps-image preprocessing and segmentation-to minimize these anomalies. It further explores a range of classification techniques and their efficacy in different research contexts. The paper is structured around five key components: diverse image capture methods, preprocessing and segmentation techniques, various extracted features, classification techniques for citrus fruit detection, and a comparison among classification methods like machine learning, deep learning, and statistical techniques. The study concludes by discussing current challenges and limitations in detecting citrus fruit diseases. It emphasizes the use of thresholding in hyperspectral imaging and identifies RGB color space as a frequently used feature. Among the compared techniques, Support Vector Machine (SVM) in machine learning, Artificial Neural Network (ANN) in neural networks, Convolutional Neural Network (CNN) in deep learning, and Linear Discriminant Analysis in statistical approaches emerge as the most effective.

show abstract

“…24 had suggested a model to group the Intermittent Leather Images using Linear Discriminant Model as per the category of normal leather and defective leather based on surface level features such as base color, other than base color, share of regions, share of cutting area, share of cutting value, position wise length and position wise breadth. Xie, X., et al 25 has proposed an improved image matching algorithm of defects by describing spatial signals on navel orange surface based on compressed sensing by combining of wavelet transform (WT) and speeded up robust features (SURF). Aslam, Y., et al 26 has proposed an automatic segmentation and quantification approach for inspecting defects on Metal from digital images consisting of input image and ground truth using convolutional neural network (CNN) approach.…”

Section: Introductionmentioning

confidence: 99%

Region Wise Surface Level Defect Detection and Ranking of Crust Leather Images Based on Image Processing Techniques

Vasagam,

Sornam

2023

JALCA

View full text Add to dashboard Cite

Sorting and aligning of crust leather for grading on position wise defect distribution is one of the methods adopted in the tanning industry. This method is generally carried out manually by a veteran on official sampling position and their input is critical because it is directly linked to sales of the crust leather. The opinion of the experts is believed to be stable and consumes a good amount of time too. Hence, in the current research a robust defect detection method and ranking of crust leather images based on image processing techniques is proposed to give a stable solution in a short span of time. A custom-made dataset of crust leather images consisting of 5640 images were used in this study. The pixel intensity has been extracted on demarcated position of various regions including neck, belly left, belly right, center and butt instead of official sampling position through horizontal and vertical mapping of coordinates with a new method Grading Score on Image Position wise (GSIP) on the actual images. The image processing techniques using Canny Edge Detection and filters such as Laplacian, Median, Prewitt, Roberts, Sobel and Scharr were implemented to get the pixel intensity grouped and classified based on parameters within acceptable range using a Naïve Bayes Classifier. The classifier confirms that the accuracy of Set I - Actual Images and Set II - Defects with implementation of canny edge detection over other image processing techniques at 99.50%. Therefore, the current research confirms that the proposed GSIP method would give an additional tool to inspectors while ranking the crust leather based on region wise surface level defect detection of crust leather images based on image processing techniques.

show abstract

Image matching algorithm of defects on navel orange surface based on compressed sensing

Cited by 5 publications

References 14 publications

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Image Acquisition, Preprocessing and Classification of Citrus Fruit Diseases: A Systematic Literature Review

Citrus Fruit Disease Detection Techniques: A Survey and Comparative Analysis of Relevant Approaches

Region Wise Surface Level Defect Detection and Ranking of Crust Leather Images Based on Image Processing Techniques

Contact Info

Product

Resources

About