&lt;title&gt;New feature extraction method for classification of agricultural products from x-ray images&lt;/title&gt;

Talukder, Ashit; Casasent, David P.; Lee, Ha-Woon; Keagy, Pamela M.; Schatzki, Thomas F.

doi:10.1117/12.336874

Cited by 13 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bottom images were acquired on a high speed X-ray imaging system. Comparing to the scanned film images, it is clear that with existing equipment the earliest larval stages cannot be detected at high speed due to lower resolution and higher noise levels [75][76][77][78] as well as separation of touching samples in X-ray images [21,79]. Algorithm strategies include: neural networks that achieve 98% recognition with less than 1% false positives (good product classified as bad) on scanned film images, discriminant analysis routines achieving 89% accuracy in linescan images, and multiple feature extraction strategies.…”

Section: Applesmentioning

confidence: 98%

“…It is not practical to attempt to describe each method that has been presented in the literature. The majority of detection algorithms for X-ray images of food products use a variation of discriminant analysis [18], neural networks [19][20][21], or simple/adaptive thresholding [22]. Spectral filtering of the X-ray image has also been shown to be an effective tool [23,24].…”

Section: Detection and Imagingmentioning

confidence: 99%

See 1 more Smart Citation

X-ray detection of defects and contaminants in the food industry

Haff

Toyofuku

2008

Sens. & Instrumen. Food Qual.

193

View full text Add to dashboard Cite

The ability of X-rays to traverse through matter and reveal hidden contaminants or defects has led to their extensive use in manufacturing industries for quality control inspection. The difficulties inherent in the detection of defects and contaminants in food products have kept the use of X-ray in that industry limited mainly to the packaged foods sector. Nevertheless, the need for non-destructive internal product inspection has motivated a considerable research effort in this field spanning many decades. Improvements in technology, especially more compact and affordable high voltage power sources, high speed computing, and high resolution detector arrays, have made many X-ray detection tasks possible today that were previously unfeasible. These improvements can be expected to continue into the future. The purpose of this article is to give a review of research activity related to the use of X-ray imaging for the detection of defects and contaminants in agricultural commodities and discuss improvements in technology required to improve these detection capabilities.

show abstract

Section: Applesmentioning

confidence: 98%

Section: Detection and Imagingmentioning

confidence: 99%

X-ray detection of defects and contaminants in the food industry

Haff

Toyofuku

2008

Sens. & Instrumen. Food Qual.

193

View full text Add to dashboard Cite

show abstract

“…We applied edge detection on every pixel by adding the absolute difference of pixel intensities from its eight neighbors [11]. An x-ray image sample before and after edge detection is shown in Fig.…”

Section: ) Global Statistical Texture Featuresmentioning

confidence: 99%

“…For nuts, the key task is to detect the unhealthy ones and separate them from the healthy ones before entering the production assembly. For detection of bad items, several kinds of meaningful features have been extracted from the x-ray images, projecting geometric, statistical, and texture properties [4], [5]. Spectral imaging was used for quality assessment of cherries [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial neural network classifier for quality inspection of nuts

Khosa

Pasero

2014

2014 International Conference on Robotics and Emerging Allied Technologies in Engineering (iCREATE)

View full text Add to dashboard Cite

In the food industry, automatic inspection of key ingredients as well as end products is gaining attention. Automatic detection of unhealthy ingredients on early stage of food production is becoming a vital task. In this paper, feature extraction of raw food ingredient's x-ray images and their classification is presented. X-ray images of pine and pistachio nuts are used as samples for this purpose. Statistical and texture features are extracted from each of original image samples as well as after applying edge detection on them. Texture features are calculated on global level and from co-occurrence matrices. Original features are used for classification independently, and in combination with edge features also. Artificial neural network is used as classifier. Texture features independently turned out better results with the classifier producing 0% and 6.8% false negative rate for pine and pistachio nuts respectively.

show abstract

Defects Detection in Pistachio Nuts Using Artificial Neural Networks

Ros

Pasero

2013

Neural Nets and Surroundings

View full text Add to dashboard Cite

<title>New feature extraction method for classification of agricultural products from x-ray images</title>

Cited by 13 publications

References 0 publications

X-ray detection of defects and contaminants in the food industry

X-ray detection of defects and contaminants in the food industry

Artificial neural network classifier for quality inspection of nuts

Defects Detection in Pistachio Nuts Using Artificial Neural Networks

Contact Info

Product

Resources

About