Automated visual inspection system for the classification of preserved vegetables

Fernández, Carlos; Muro, Juan Suardíaz; Jimenez, C.; Navarro, Pedro J.; Toledo, A.; Iborra, Andrés

doi:10.1109/isie.2002.1026076

Cited by 7 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is due to the fact that inspectors are prone to suffer fatigue, boredom or simply fail to pay sufficient attention because of the repetitive nature of their tasks [ 1 ]. To deal with these problems, human inspectors are being substituted by automatic visual inspection systems [ 2 , 3 , 4 ].…”

Section: Introductionmentioning

confidence: 99%

Defect Detection in Textures through the Use of Entropy as a Means for Automatically Selecting the Wavelet Decomposition Level

Navarro

Fernández-Isla

Alcover

et al. 2016

Sensors

View full text Add to dashboard Cite

This paper presents a robust method for defect detection in textures, entropy-based automatic selection of the wavelet decomposition level (EADL), based on a wavelet reconstruction scheme, for detecting defects in a wide variety of structural and statistical textures. Two main features are presented. One of the new features is an original use of the normalized absolute function value (NABS) calculated from the wavelet coefficients derived at various different decomposition levels in order to identify textures where the defect can be isolated by eliminating the texture pattern in the first decomposition level. The second is the use of Shannon’s entropy, calculated over detail subimages, for automatic selection of the band for image reconstruction, which, unlike other techniques, such as those based on the co-occurrence matrix or on energy calculation, provides a lower decomposition level, thus avoiding excessive degradation of the image, allowing a more accurate defect segmentation. A metric analysis of the results of the proposed method with nine different thresholding algorithms determined that selecting the appropriate thresholding method is important to achieve optimum performance in defect detection. As a consequence, several different thresholding algorithms depending on the type of texture are proposed.

show abstract

Section: Introductionmentioning

confidence: 99%

Defect Detection in Textures through the Use of Entropy as a Means for Automatically Selecting the Wavelet Decomposition Level

Navarro

Fernández-Isla

Alcover

et al. 2016

Sensors

View full text Add to dashboard Cite

show abstract

“…The feature vector is usually composed by a wide variety of different types of features. The most utilized features are related to: intensity of image pixels [ 28 ], geometries [ 29 ] and textures (first and second-order statistical features) [ 30 , 31 ]. In addition the feature vector is computed over image transformations such as Fourier, Gabor, and Wavelet [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

Machine Learning and Computer Vision System for Phenotype Data Acquisition and Analysis in Plants

Navarro

Pérez

Weiß

et al. 2016

Sensors

View full text Add to dashboard Cite

Phenomics is a technology-driven approach with promising future to obtain unbiased data of biological systems. Image acquisition is relatively simple. However data handling and analysis are not as developed compared to the sampling capacities. We present a system based on machine learning (ML) algorithms and computer vision intended to solve the automatic phenotype data analysis in plant material. We developed a growth-chamber able to accommodate species of various sizes. Night image acquisition requires near infrared lightning. For the ML process, we tested three different algorithms: k-nearest neighbour (kNN), Naive Bayes Classifier (NBC), and Support Vector Machine. Each ML algorithm was executed with different kernel functions and they were trained with raw data and two types of data normalisation. Different metrics were computed to determine the optimal configuration of the machine learning algorithms. We obtained a performance of 99.31% in kNN for RGB images and a 99.34% in SVM for NIR. Our results show that ML techniques can speed up phenomic data analysis. Furthermore, both RGB and NIR images can be segmented successfully but may require different ML algorithms for segmentation.

show abstract

“…Many AVI developments have been using CCD-based camera [5]- [7]. This is because it has clear advantage such as low noise and fast shuttering speed.…”

Section: Previous Workmentioning

confidence: 99%

Surface Defect Detection and Classification Based on Statistical Filter and Decision Tree

Akbar¹,

Suryana²,

Akbar³

2013

IJCTE

View full text Add to dashboard Cite

Abstract-Industrial quality inspection is a major issue due to the growing of market competitiveness which requires the product to be checked in terms of online defect detection. Meanwhile, labor inspection has been eliminated due to its limitation that restricts the speed of manufacturing process. Hence, automated inspection process is inevitable to preserve the industrial health and lift human function into management tasks. There are huge efforts on Automated Visual Inspection (AVI) research area, particularly in plain surfaces such as ceramics and fabrics. The inspection modeling includes statistical-based, model-based and color analysis. Most systems are well studied and tested on Charge-Coupled Device (CCD) image sensor. However, only few approaches are carried out for Complementary Metal Oxide Semiconductor (CMOS) imaging modality. This study presents an inspection scheme to detect defect in plain fabric based on statistical filter and geometrical features on CMOS-based image input. The advantage of this technology is obvious regarding to its affordable development especially for small and medium industries. We showed that it is suitable for defect inspection applications that does not require specialized lighting environment. In addition, a classification approach is developed based on decision tree framework. The result for static image shows the classification achieve 99% accuracy.

show abstract

Automated visual inspection system for the classification of preserved vegetables

Cited by 7 publications

References 1 publication

Defect Detection in Textures through the Use of Entropy as a Means for Automatically Selecting the Wavelet Decomposition Level

Defect Detection in Textures through the Use of Entropy as a Means for Automatically Selecting the Wavelet Decomposition Level

Machine Learning and Computer Vision System for Phenotype Data Acquisition and Analysis in Plants

Surface Defect Detection and Classification Based on Statistical Filter and Decision Tree

Contact Info

Product

Resources

About