Merino, IbonAzpiazu, JonRemazeilles, AnthonySierra, Basilio2020-06-01Merino , I , Azpiazu , J , Remazeilles , A & Sierra , B 2020 , ' Histogram-Based Descriptor Subset Selection for Visual Recognition of Industrial Parts ' , Applied Sciences , vol. 10 , no. 11 , 3701 , pp. 3701 . https://doi.org/10.3390/app101137012076-3417researchoutputwizard: 11556/934Publisher Copyright: © 2020 by the authors.This article deals with the 2D image-based recognition of industrial parts. Methods based on histograms are well known and widely used, but it is hard to find the best combination of histograms, most distinctive for instance, for each situation and without a high user expertise. We proposed a descriptor subset selection technique that automatically selects the most appropriate descriptor combination, and that outperforms approach involving single descriptors. We have considered both backward and forward mechanisms. Furthermore, to recognize the industrial parts a supervised classification is used with the global descriptors as predictors. Several class approaches are compared. Given our application, the best results are obtained with the Support Vector Machine with a combination of descriptors increasing the F1 by 0.031 with respect to the best descriptor alone.11436087enginfo:eu-repo/semantics/openAccessjournal article10.3390/app10113701Computer visionFeature descriptorHistogramFeature subset selectionIndustrial objectsComputer visionFeature descriptorHistogramFeature subset selectionIndustrial objectsGeneral Materials ScienceInstrumentationGeneral EngineeringProcess Chemistry and TechnologyComputer Science ApplicationsFluid Flow and Transfer ProcessesProject IDinfo:eu-repo/grantAgreement/EC/H2020/820689/EU/Seamless and safe human - centred robotic applications for novel collaborative workplaces/SHERLOCKinfo:eu-repo/grantAgreement/EC/H2020/820689/EU/Seamless and safe human - centred robotic applications for novel collaborative workplaces/SHERLOCKFunding InfoThis paper has been supported by the project SHERLOCK under the European Union’s Horizon 2020 Research & Innovation programme, grant agreement No. 820689.This paper has been supported by the project SHERLOCK under the European Union’s Horizon 2020 Research & Innovation programme, grant agreement No. 820689.http://www.scopus.com/inward/record.url?scp=85086082672&partnerID=8YFLogxK