Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379987740> ?p ?o ?g. }
Showing items 1 to 49 of
49
with 100 items per page.
- W4379987740 abstract "<p>Document authentication is a critical part of forensic analysis, which ensures the veracity of a document’s origins. A significant challenge in this field is the detection of ink mismatches, especially in instances of disproportionate ink distribution. This issue is effectively handled with hyperspectral images of documents, whereas traditional imaging techniques struggle to distinguish between visually similar inks. To address this problem, we introduce a new approach that leverages hyperspectral unmixing for ink mismatch detection in unbalanced clusters. The proposed method identifies unique spectral characteristics of different inks and their respective proportions, thus facilitating significant ink distinction. The proposed approach utilizes Elbow estimation and Silhouette coefficient for number of inks estimation and performs color segmentation for all unique ink types by employing k-means clustering and Gaussian mixture models (GMMs), outperforming existing methods in this regard which rely on prior knowledge about the number of inks used in the document. For abundance estimation, a unique method of dimensional reduction of HSI and channel wise analysis is proposed. We evaluate our approach on the iVision Handwritten Hyperspectral Images Data set (iVision HHID), a comprehensive and rich dataset that surpasses the commonlyused UWA Writing Inks Hyperspectral Images (WIHSI) database in size and diversity. Our results, in comparison with state-of-theart methods, demonstrate the effectiveness of our approach in hyperspectral ink mismatch detection. This paper thus promotes the application of hyperspectral imaging for document analysis and encourages further exploration toward automated questioned document examination.</p>" @default.
- W4379987740 created "2023-06-10" @default.
- W4379987740 creator A5092123674 @default.
- W4379987740 date "2023-06-09" @default.
- W4379987740 modified "2023-09-27" @default.
- W4379987740 title "Automated Forensic Analysis for Ink Mismatch Detection in Hyperspectral Document Images" @default.
- W4379987740 doi "https://doi.org/10.36227/techrxiv.23353271.v1" @default.
- W4379987740 hasPublicationYear "2023" @default.
- W4379987740 type Work @default.
- W4379987740 citedByCount "0" @default.
- W4379987740 crossrefType "posted-content" @default.
- W4379987740 hasAuthorship W4379987740A5092123674 @default.
- W4379987740 hasBestOaLocation W43799877401 @default.
- W4379987740 hasConcept C109693293 @default.
- W4379987740 hasConcept C153180895 @default.
- W4379987740 hasConcept C154945302 @default.
- W4379987740 hasConcept C159078339 @default.
- W4379987740 hasConcept C28490314 @default.
- W4379987740 hasConcept C41008148 @default.
- W4379987740 hasConcept C58103923 @default.
- W4379987740 hasConcept C61224824 @default.
- W4379987740 hasConcept C73555534 @default.
- W4379987740 hasConcept C89600930 @default.
- W4379987740 hasConceptScore W4379987740C109693293 @default.
- W4379987740 hasConceptScore W4379987740C153180895 @default.
- W4379987740 hasConceptScore W4379987740C154945302 @default.
- W4379987740 hasConceptScore W4379987740C159078339 @default.
- W4379987740 hasConceptScore W4379987740C28490314 @default.
- W4379987740 hasConceptScore W4379987740C41008148 @default.
- W4379987740 hasConceptScore W4379987740C58103923 @default.
- W4379987740 hasConceptScore W4379987740C61224824 @default.
- W4379987740 hasConceptScore W4379987740C73555534 @default.
- W4379987740 hasConceptScore W4379987740C89600930 @default.
- W4379987740 hasLocation W43799877401 @default.
- W4379987740 hasOpenAccess W4379987740 @default.
- W4379987740 hasPrimaryLocation W43799877401 @default.
- W4379987740 hasRelatedWork W1562793155 @default.
- W4379987740 hasRelatedWork W2028628118 @default.
- W4379987740 hasRelatedWork W2777646793 @default.
- W4379987740 hasRelatedWork W2954309397 @default.
- W4379987740 hasRelatedWork W3173596272 @default.
- W4379987740 hasRelatedWork W4213434694 @default.
- W4379987740 hasRelatedWork W4253950112 @default.
- W4379987740 hasRelatedWork W4308073684 @default.
- W4379987740 hasRelatedWork W4379987740 @default.
- W4379987740 hasRelatedWork W4380081001 @default.
- W4379987740 isParatext "false" @default.
- W4379987740 isRetracted "false" @default.
- W4379987740 workType "article" @default.