Apple Sorting Using Artificial Neural Networks and Spectral Imaging

Kavdır, İsmail; Guyer, Daniel E.

doi:10.13031/2013.11411

Cited by 48 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[4] However, the signatures of the healthy and bruised regions in the visible range (400-700 nm) are very similar, so fresh bruises are usually difficult to detect when oxidative browning is limited. [5] In recent decades, hyperspectral imaging (HSI) technology, which can simultaneously acquire spatial and spectral information, has been used as a powerful technique for food quality detection. [6] ElMasry et al [7] investigated a hyperspectral imaging system based on a spectral region between 400 and 1000 nm for early detection of bruises on 'McIntosh' apples, which could detect apple bruises on different background colors (green, red, and green reddish).…”

Section: Introductionmentioning

confidence: 99%

Visual detection of apple bruises using AdaBoost algorithm and hyperspectral imaging

Zhang

2018

International Journal of Food Properties

View full text Add to dashboard Cite

Hyperspectral imaging technique (400-1000 nm) was used for rapid and nondestructive recognition of bruises of apples. A total of 324 hyperspectral images were collected from 108 Fuji apples and the average spectral reflectance was extracted from the region of interest (ROI) of each image. The classification results of AdaBoost for the data pretreated by various existing methods were compared. Then, the correlation-based feature selection (CFS) algorithm was used to obtain characteristic wavelengths for reducing data redundancy. After pretreating with multiplicative scatter correction (MSC) and CFS, the average accuracy of the selected wavelengths was 97.63%. Then, an image processing algorithm based on the characteristic wavelengths selected before was proposed for the visual discrimination of bruises. This algorithm performed independent component analysis (ICA) transformation of the selected wavelengths, and chose the third component image of the ICA transform, then used adaptive threshold segmentation to obtain the bruise region of apples. The results showed that hyperspectral imaging technology could discriminate apple bruise, and this study can help to develop an online apple bruises detection system. ARTICLE HISTORY

show abstract

Section: Introductionmentioning

confidence: 99%

Visual detection of apple bruises using AdaBoost algorithm and hyperspectral imaging

Zhang

2018

International Journal of Food Properties

View full text Add to dashboard Cite

show abstract

“…Kavdir and Guyer (2002) sorted Empire and Golden Delicious apples using back-propagation (BP) ANNs and spectral imaging. A 2-class and a 5-class classification were performed and the classification success rates in the 2-class classification were between 89.2% and 100%.…”

Section: Cereal Grainsmentioning

confidence: 99%

“…It lacks a profound theoretical basis for designing an ANN to choose the best topological structure, such as the number of hidden layers, and the number of nodes in each hidden layer. Therefore, to find the right ANN structure for a specific problem, one should try different settings such as neurons in hidden layer(s), the number of hidden layers, and the type of transfer function in the neurons of hidden and output layers (Kavdir & Guyer, 2002). Furthermore, ANNs are essentially black boxed: given any input a corresponding output is produced, but it is represented as just a matrix of parameters, and the relationship between the inputs and outputs is not well understood or is difficult to translate into a mathematical function.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Learning techniques used in computer vision for food quality evaluation: a review

Sun

2006

Journal of Food Engineering

323

125

View full text Add to dashboard Cite

“…The former that has been proposed by Haralick et al [16], is the widely applied statistical texture analysis method, in which texture features such as entropy, homogeneity, correlation and contrast are extracted by some statistical approaches from the cooccurrence matrix of gray scale image histogram. GLCM has been used for classification of cereal grain and dockage [17], and apple [18].…”

Section: Introductionmentioning

confidence: 99%

Effect of Different Processing Parameters on Quality Factors and Image Texture Features of Bread

Karimi¹

2012

J Bioproces Biotechniq

View full text Add to dashboard Cite

In this research, image texture analysis as a nondestructive and rapid method was applied for estimation of mechanical texture property of bread. Bread samples were formulated using different emulsifiers (i.e. SSL, DATEM and E471) in three concentrations (0.2, 0.4 and 0.6%) at three proofing times (25, 35 and 45min) and sensory properties, specific volume, color components (i.e. L*, a* and b*), porosity, hardness and four image texture features (i.e. contrast, correlation, energy and homogeneity) were determined. The results indicated that emulsifier treated samples showed better (p<0.05) sensory perceptions in compression to control samples. However, the proofing time did not show significant effect. Application of E471 significantly increased the specific volume of bread. Emulsifier treated samples had higher lightness values. Application of higher concentration and longer proofing time led to higher porosity of bread. Emulsifiers, their concentrations and proofing times had positive significant (p<0.05) effects on softness of bread. On the other side of this research, contrast, correlation, energy and homogeneity were calculated from Grey Level CoOccurrence Matrix (GLCM). They showed splendid correlations with hardness of bread (0.958, 0.973, 0.966 and 0.91, respectively). Multiple Linear Regression (MLR) was conducted between hardness and four image texture features and the mathematical equation could predict hardness with high correlation of coefficient of 0.994. These results strongly suggest that image texture analysis can be applied as a nondestructive and rapid method for estimation of hardness of bread.

show abstract

Apple Sorting Using Artificial Neural Networks and Spectral Imaging

Cited by 48 publications

References 0 publications

Visual detection of apple bruises using AdaBoost algorithm and hyperspectral imaging

Visual detection of apple bruises using AdaBoost algorithm and hyperspectral imaging

Learning techniques used in computer vision for food quality evaluation: a review

Effect of Different Processing Parameters on Quality Factors and Image Texture Features of Bread

Contact Info

Product

Resources

About