Development of a Methodological Framework for the Self Reconfiguration of Automated Visual Inspection Systems

Garcia, H.C.; Villalobos, J. René

doi:10.1109/indin.2007.4384757

Cited by 6 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method seeks to estimate the MER based on the stochastic representation for the exact distributions of the misclassification probabilities. These misclassification probabilities are obtained through the use of a "plug-in" Quadratic Discriminant Function (QDF) originally proposed by [3], later expanded by [4] and modified to fit our needs in this paper and [17]. A brief explanation of these works is presented next.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Two shortcomings of this work was that the results presented assumed that all the features had normal distributions with identical parameters and that the sample sizes were of the same size (n 1 = n 2 ). These two shortcomings were addressed by [17] and reported in [21] which considered the case of features that have different parameters and unequal sample. The results of that work are the basis for the feature selection methodology presented next.…”

Section: A Stochastic Representation Of the "Plug-in" Quadraticmentioning

confidence: 99%

“…The computational details of the previous equations presented in [17] are based on the works of [3] and [4]. Although McFarland & Richards [3] showed that the stochastic representation of random variable 2 Q can be estimated in a similar way to that of 1 Q , Hua [4] proposed a more efficient Additionally, given that in almost all practical situations, the population parameters of the discriminant functions, 1 , 2 , 1 and 2 are unknown, it is necessary to replace the population parameters by their sample estimates [18].…”

Section: B Mean and Variance Estimationsmentioning

confidence: 99%

“…One of the main motivations of the proposed feature selection methodology is to produce the tools needed for the development of self reconfigurable automated inspection systems [5]. One of the conditions for the emergence of these systems is the automation of decisions that traditionally are performed by human developers such as feature generation, feature selection, inspection algorithm testing and refinement.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A feature selection method for Automated Visual Inspection systems

Garcia¹,

Villalobos

2008

2008 6th IEEE International Conference on Industrial Informatics

Self Cite

View full text Add to dashboard Cite

Automated Visual Inspection (AVI) systems are nowadays considered essential in the assembly of Surface Mounted Devices (SMD). The general goal of this research centers on developing self-training AVI systems for the inspection of SMD components. In this paper, it is proposed a new feature selection methodology based on a stepwise variable selection. The procedure uses an estimation of the marginal Misclassification Error Rate (MER) as the figure of merit to introduce new features in the quadratic classifier used by the inspection system. This marginal error rate is estimated by using the densities of the conditional stochastic representations of the underlying quadratic discriminant function. In this paper we show that the application of the proposed methodology to the inspecting of SMD components results in significant savings of computational time in the estimation of classification error over the traditional simulation and crossvalidation methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: A Stochastic Representation Of the "Plug-in" Quadraticmentioning

confidence: 99%

Section: B Mean and Variance Estimationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A feature selection method for Automated Visual Inspection systems

Garcia¹,

Villalobos

2008

2008 6th IEEE International Conference on Industrial Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, Garcia and Villalobos introduced a reconfigurable framework for AVI Systems [11]. Although it is good to design a reconfigurable system, it is still costly to implement, especially for small industries.…”

Section: Introductionmentioning

confidence: 99%

Cost-efficient Automated Visual Inspection system for small manufacturing industries based on SIFT

Bohlool

Taghanaki

2008

2008 23rd International Conference Image and Vision Computing New Zealand

View full text Add to dashboard Cite

This paper presents a cost efficient Automated Visual Inspection (AVI) system for small industries' quality control system. The complex hardware and software make current AVI systems too expensive to afford for smallsize manufacturing industries. Proposed approach to AVI systems is based on an ordinary PC with a medium resolution camera without any other extra hardware. The Scale Invariant Feature Transform (SIFT) is used to acquire good accuracy and make it applicable for different situations with different sample sizes, positions, and illuminations. Proposed method can detect three different defect types as well as locating and measuring defect percentage for more specialized utilization. To evaluate the performance of this system different samples with different sizes, shapes, and complexities are used and the results show that proposed system is highly applicable to different applications and is Invariant to noise, illumination changes, rotation, and transformation.

show abstract

Automated Feature Selection Methodology for Reconfigurable Automated Visual Inspection Systems

Garcia

Villalobos

2007

2007 IEEE International Conference on Automation Science and Engineering

View full text Add to dashboard Cite

Development of a Methodological Framework for the Self Reconfiguration of Automated Visual Inspection Systems

Cited by 6 publications

References 19 publications

A feature selection method for Automated Visual Inspection systems

A feature selection method for Automated Visual Inspection systems

Cost-efficient Automated Visual Inspection system for small manufacturing industries based on SIFT

Automated Feature Selection Methodology for Reconfigurable Automated Visual Inspection Systems

Contact Info

Product

Resources

About