Fiber Estimation From Paper Macro Images via EfficientNet-Based Patch Classification

In the field of paper conservation and archival research, identifying the raw materials of paper is important to elucidate its history and culture. As the most basic element of the raw materials for paper, fibers have not been sufficiently investigated. In this study, we propose a nondestructive met...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.12271-12278
Main Authors: Kamiya, Naoki, Yoshizato, Yu, Zhou, Yexin, Ohyanagi, Yoichi, Shibazaki, Koji
Format: Article
Language:English
Subjects:
Accuracy
Classification
Digital cameras
Digital imaging
EfficientNet
Estimation
Image reconstruction
macro image
nondestructive paper analysis
Nondestructive testing
paper fiber
Pixels
Raw materials
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the field of paper conservation and archival research, identifying the raw materials of paper is important to elucidate its history and culture. As the most basic element of the raw materials for paper, fibers have not been sufficiently investigated. In this study, we propose a nondestructive method for estimating paper fibers from macro photographs ([Formula Omitted] pixels) captured using a digital camera. The proposed method consists of background patch (500 pixels per side) detection (BPD), wherein background regions with no text are identified; patch fiber classification (PFC), wherein background patches obtained after BPD are analyzed for fiber classification; and paper fiber estimation (PFE), wherein macro images obtained after PFC are analyzed for fiber estimation. BPD and PFC are employed to perform patch-based classification on segmented macro images, which are reconstructed during PFE to obtain the final fiber estimation results. We performed experiments using 1337 macro images (64176 patches) to evaluate the fiber estimation accuracy for kozo, mitsumata, and gampi via three-fold cross-validation. The average fiber classification accuracy for patch images was observed to be 79.1%; accordingly, the average fiber estimation accuracy for macro images was 85.8%. Experimental results indicated that PFE can be realized in a nondestructive manner on macro images of paper captured using a digital camera.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3355115