arXiv cs.AI· Shenghan Gao, Zhiling Zheng·· 10 小时前AI 评分34
用视觉 LLM 从 COF 文献图像中结构化提取衍射数据
Structured Extraction of Diffraction Data from Covalent Organic Frameworks
AI 导读
一套结合视觉大语言模型与经典计算机视觉的流水线,从 3,954 篇共价有机框架(COF)文章中提取出 11,445 条校准衍射曲线,并发布在开放数据库 COF-PEAK。与 60 个面板的人工数字化结果相比,提取的峰位中位偏差仅 0.07 度。数字化曲线还可追踪峰显著度随合成条件的变化,而论文通常只报告少数峰角。
正文 · 原文
Abstract:Powder X-ray diffraction (PXRD) is the primary structural evidence for covalent organic frameworks (COFs) and many other materials. Yet decades of measured patterns exist only as images in published figures. Automatic recovery is difficult, because PXRD figures vary widely in format, from a single curve to crowded stacks with labels, insets, and neighboring plots that challenge traditional computer vision. This work presents a pipeline in which a vision large language model (LLM) interprets the layout of each figure, locating the diffraction plot and its curves and sketching a coarse trace of each, while classical computer vision (CV) refines every trace to pixel-level accuracy. Applied to 3,954 COF articles, the pipeline produces 11,445 calibrated diffraction curves, released in the open database COF-PEAK. Compared with a hand digitization of 60 panels, extracted peak positions differ by a median of only 0.07 degrees. Whereas papers usually report only a few peak angles, which limits further analysis, the digitized curves enable tracking how peak prominence, a possible marker of crystallinity, changes with synthesis conditions. Vision LLMs and classical CV can thus turn such figures into reusable experimental data.
| Comments: | 66 pages: main text (19 pages, 7 figures, 3 tables) and Supporting Information (47 pages) in one file. Data and code: this https URL ; database website: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23680 [cs.CV] |
| (or arXiv:2611.23680v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23680 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shenghan Gao [view email]
[v1]
Wed, 18 Nov 2026 01:10:19 UTC (12,335 KB)
来源:arXiv cs.AI · arxiv.org