Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201901129> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3201901129 endingPage "561" @default.
- W3201901129 startingPage "550" @default.
- W3201901129 abstract "In the questioned document, the examination of stamp-pad ink is crucial scientific evidence to discern the difference between genuine and forged documents. In this study, a new method for rapid and non-destructive identification of types of stamp-pad inks by combining hyperspectral imaging (HSI) technology and deep learning was developed. Twenty stamp-pad inks of different brands and models were collected and numbered in turn, and then, each of them was sealed six times repeatedly on the A4 printing paper for the test. After that, the hyperspectral imager was used to collect the hyperspectral images and the reflectance spectral data were obtained after pixel fusion. Principal component analysis (PCA) and non-negative matrix factorization (NMF) were used to deal with the dataset, but visual results were not good. Then, back propagation neural network (BPNN) and one-dimensional convolutional neural network (1D-CNN) were constructed and their merits and drawbacks were compared. The final loss function of the BPNN of training set and validation set was stable at 0.27 and 0.42, and the classification accuracy of the training set and validation set reached 90.02% and 83.99%, respectively. Compared with the BPNN, the 1D-CNN had better stability and efficiency for the classification. The loss function of the training set and validation set was as low as 0.068 and 0.075, and the final classification accuracy reached 98.30% and 97.94%, respectively. Therefore, the combination of hyperspectral imaging technology and 1D-CNN represents a potentially simple, non-destructive, and rapid method for stamp-pad inks detection and classification." @default.
- W3201901129 created "2021-10-11" @default.
- W3201901129 creator A5012402194 @default.
- W3201901129 creator A5013444655 @default.
- W3201901129 creator A5014775484 @default.
- W3201901129 creator A5028688827 @default.
- W3201901129 creator A5037269917 @default.
- W3201901129 creator A5047691642 @default.
- W3201901129 date "2021-10-07" @default.
- W3201901129 modified "2023-09-25" @default.
- W3201901129 title "Classification modeling method for hyperspectral stamp‐pad ink data based on one‐dimensional convolutional neural network" @default.
- W3201901129 cites W1521436688 @default.
- W3201901129 cites W1976457287 @default.
- W3201901129 cites W1984692344 @default.
- W3201901129 cites W2085774580 @default.
- W3201901129 cites W2598551616 @default.
- W3201901129 cites W2783401215 @default.
- W3201901129 cites W2901211777 @default.
- W3201901129 cites W2909669418 @default.
- W3201901129 cites W2911361065 @default.
- W3201901129 cites W3006505613 @default.
- W3201901129 cites W3006667532 @default.
- W3201901129 cites W3012931284 @default.
- W3201901129 cites W3037303831 @default.
- W3201901129 doi "https://doi.org/10.1111/1556-4029.14909" @default.
- W3201901129 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34617278" @default.
- W3201901129 hasPublicationYear "2021" @default.
- W3201901129 type Work @default.
- W3201901129 sameAs 3201901129 @default.
- W3201901129 citedByCount "7" @default.
- W3201901129 countsByYear W32019011292022 @default.
- W3201901129 countsByYear W32019011292023 @default.
- W3201901129 crossrefType "journal-article" @default.
- W3201901129 hasAuthorship W3201901129A5012402194 @default.
- W3201901129 hasAuthorship W3201901129A5013444655 @default.
- W3201901129 hasAuthorship W3201901129A5014775484 @default.
- W3201901129 hasAuthorship W3201901129A5028688827 @default.
- W3201901129 hasAuthorship W3201901129A5037269917 @default.
- W3201901129 hasAuthorship W3201901129A5047691642 @default.
- W3201901129 hasConcept C108583219 @default.
- W3201901129 hasConcept C153180895 @default.
- W3201901129 hasConcept C154945302 @default.
- W3201901129 hasConcept C159078339 @default.
- W3201901129 hasConcept C160633673 @default.
- W3201901129 hasConcept C169903167 @default.
- W3201901129 hasConcept C177264268 @default.
- W3201901129 hasConcept C199360897 @default.
- W3201901129 hasConcept C27438332 @default.
- W3201901129 hasConcept C41008148 @default.
- W3201901129 hasConcept C50644808 @default.
- W3201901129 hasConcept C58489278 @default.
- W3201901129 hasConcept C81363708 @default.
- W3201901129 hasConceptScore W3201901129C108583219 @default.
- W3201901129 hasConceptScore W3201901129C153180895 @default.
- W3201901129 hasConceptScore W3201901129C154945302 @default.
- W3201901129 hasConceptScore W3201901129C159078339 @default.
- W3201901129 hasConceptScore W3201901129C160633673 @default.
- W3201901129 hasConceptScore W3201901129C169903167 @default.
- W3201901129 hasConceptScore W3201901129C177264268 @default.
- W3201901129 hasConceptScore W3201901129C199360897 @default.
- W3201901129 hasConceptScore W3201901129C27438332 @default.
- W3201901129 hasConceptScore W3201901129C41008148 @default.
- W3201901129 hasConceptScore W3201901129C50644808 @default.
- W3201901129 hasConceptScore W3201901129C58489278 @default.
- W3201901129 hasConceptScore W3201901129C81363708 @default.
- W3201901129 hasIssue "2" @default.
- W3201901129 hasLocation W32019011291 @default.
- W3201901129 hasLocation W32019011292 @default.
- W3201901129 hasOpenAccess W3201901129 @default.
- W3201901129 hasPrimaryLocation W32019011291 @default.
- W3201901129 hasRelatedWork W1585144779 @default.
- W3201901129 hasRelatedWork W1993683021 @default.
- W3201901129 hasRelatedWork W2142308737 @default.
- W3201901129 hasRelatedWork W2731899572 @default.
- W3201901129 hasRelatedWork W2921350538 @default.
- W3201901129 hasRelatedWork W2997155179 @default.
- W3201901129 hasRelatedWork W3133861977 @default.
- W3201901129 hasRelatedWork W4312417841 @default.
- W3201901129 hasRelatedWork W4321369474 @default.
- W3201901129 hasRelatedWork W4366351422 @default.
- W3201901129 hasVolume "67" @default.
- W3201901129 isParatext "false" @default.
- W3201901129 isRetracted "false" @default.
- W3201901129 magId "3201901129" @default.
- W3201901129 workType "article" @default.