SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION
Written information on the surface of cultural relics can record important historical events. Due to the influence of natural and human factors, the surface of cultural relics fades and the words are difficult to identify. Take advantage of the hyperspectral data image and spectral unity and wide sp...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2022-05-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2022/917/2022/isprs-archives-XLIII-B2-2022-917-2022.pdf |
_version_ | 1811254814347100160 |
---|---|
author | S. H. Wang S. H. Wang S. Q. Lyu S. Q. Lyu M. L. Hou M. L. Hou Z. H. Gao Z. H. Gao M. Huang M. Huang |
author_facet | S. H. Wang S. H. Wang S. Q. Lyu S. Q. Lyu M. L. Hou M. L. Hou Z. H. Gao Z. H. Gao M. Huang M. Huang |
author_sort | S. H. Wang |
collection | DOAJ |
description | Written information on the surface of cultural relics can record important historical events. Due to the influence of natural and human factors, the surface of cultural relics fades and the words are difficult to identify. Take advantage of the hyperspectral data image and spectral unity and wide spectral range, a cultural relics surface handwriting enhancement method based on manifold learning and mixed pixel decomposition was proposed. First, the minimum noise fraction (MNF) transformation was carried out on the hyperspectral image, and then the top 10 bands were selected for inverse MNF transformation to reduce noise of the hyperspectral image. Then, the reconstructed image was dimensionally reduced by locally linear embedding (LLE) to obtain a gray image with the maximum amount of information. At the same time, the spectral features of the handwriting and background area in the reconstructed image were analysed. The automatic target generation process (ATGP) was adopted for endmember extraction on the reconstructed image to identify the endmember of handwriting. The abundance map of handwriting area was obtained by the fully constrained least squares (FCLS). Finally, the gray image and the abundance map of the handwriting region were weighted together to obtain the handwriting enhanced image. The true color image was synthesized from the reconstructed image, Then the true color image and the handwriting enhancement image were fused to obtain the handwritting fusion image. The hyperspectral image of a faded text in Shuozhou City, Shanxi Province, China, was used as an example for verification, and the results showed that the method can effectively enhance the text on the surface of the artifacts. |
first_indexed | 2024-04-12T17:13:18Z |
format | Article |
id | doaj.art-a4c91f8626da4f2bab5b44c6ccc5b6d1 |
institution | Directory Open Access Journal |
issn | 1682-1750 2194-9034 |
language | English |
last_indexed | 2024-04-12T17:13:18Z |
publishDate | 2022-05-01 |
publisher | Copernicus Publications |
record_format | Article |
series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
spelling | doaj.art-a4c91f8626da4f2bab5b44c6ccc5b6d12022-12-22T03:23:44ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342022-05-01XLIII-B2-202291792210.5194/isprs-archives-XLIII-B2-2022-917-2022SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITIONS. H. Wang0S. H. Wang1S. Q. Lyu2S. Q. Lyu3M. L. Hou4M. L. Hou5Z. H. Gao6Z. H. Gao7M. Huang8M. Huang9School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, ChinaBeijing Key Laboratory for Architectural Heritage Fine Reconstruction & Health Monitoring, No.15 Yongyuan Road, Daxing District, Beijing, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, ChinaBeijing Key Laboratory for Architectural Heritage Fine Reconstruction & Health Monitoring, No.15 Yongyuan Road, Daxing District, Beijing, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, ChinaBeijing Key Laboratory for Architectural Heritage Fine Reconstruction & Health Monitoring, No.15 Yongyuan Road, Daxing District, Beijing, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, ChinaShanxi Provincial Institute of Archeology, Taiyuan, Shanxi Province, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, No.15 Yongyuan Road, Daxing District, Beijing, ChinaBeijing Key Laboratory for Architectural Heritage Fine Reconstruction & Health Monitoring, No.15 Yongyuan Road, Daxing District, Beijing, ChinaWritten information on the surface of cultural relics can record important historical events. Due to the influence of natural and human factors, the surface of cultural relics fades and the words are difficult to identify. Take advantage of the hyperspectral data image and spectral unity and wide spectral range, a cultural relics surface handwriting enhancement method based on manifold learning and mixed pixel decomposition was proposed. First, the minimum noise fraction (MNF) transformation was carried out on the hyperspectral image, and then the top 10 bands were selected for inverse MNF transformation to reduce noise of the hyperspectral image. Then, the reconstructed image was dimensionally reduced by locally linear embedding (LLE) to obtain a gray image with the maximum amount of information. At the same time, the spectral features of the handwriting and background area in the reconstructed image were analysed. The automatic target generation process (ATGP) was adopted for endmember extraction on the reconstructed image to identify the endmember of handwriting. The abundance map of handwriting area was obtained by the fully constrained least squares (FCLS). Finally, the gray image and the abundance map of the handwriting region were weighted together to obtain the handwriting enhanced image. The true color image was synthesized from the reconstructed image, Then the true color image and the handwriting enhancement image were fused to obtain the handwritting fusion image. The hyperspectral image of a faded text in Shuozhou City, Shanxi Province, China, was used as an example for verification, and the results showed that the method can effectively enhance the text on the surface of the artifacts.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2022/917/2022/isprs-archives-XLIII-B2-2022-917-2022.pdf |
spellingShingle | S. H. Wang S. H. Wang S. Q. Lyu S. Q. Lyu M. L. Hou M. L. Hou Z. H. Gao Z. H. Gao M. Huang M. Huang SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
title | SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION |
title_full | SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION |
title_fullStr | SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION |
title_full_unstemmed | SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION |
title_short | SURFACE HANDWRITING ENHANCEMENT OF ARTIFACTS BASED ON MANIFOLD LEARNING AND MIXED PIXEL DECOMPOSITION |
title_sort | surface handwriting enhancement of artifacts based on manifold learning and mixed pixel decomposition |
url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2022/917/2022/isprs-archives-XLIII-B2-2022-917-2022.pdf |
work_keys_str_mv | AT shwang surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT shwang surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT sqlyu surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT sqlyu surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT mlhou surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT mlhou surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT zhgao surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT zhgao surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT mhuang surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition AT mhuang surfacehandwritingenhancementofartifactsbasedonmanifoldlearningandmixedpixeldecomposition |