layout-parser
FastestDet
layout-parser | FastestDet | |
---|---|---|
6 | 1 | |
4,476 | 713 | |
2.1% | - | |
0.0 | 0.0 | |
2 months ago | about 1 year ago | |
Python | Python | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
layout-parser
-
Crates for converting PDF's into Markdown
I built my own solution using a combination of Tesseract and OpenCV (in python). But even though the source PDF content is computer generated, I still get sporadic OCR errors. After writing my solution, I came across this https://github.com/Layout-Parser/layout-parser which might be a better starting point for dealing with PDFs but I haven't tried it yet.
-
OCR help required
This sound more like a layout parking issue. Look at Layout Parser, it has helped me on many occasions when I was battling to extract info from PDF documents.
- Amateur programmer here. Will Rust be used in backend for software in the future?
-
Extract text from PDF
One of the tools I'm excited about (but haven't used in production) is LayoutParser. It's open-source, and can do some document image analysis especially on non-generic docs.
-
Document Classification
One project that I saw not to long ago which might be useful is this: https://github.com/Layout-Parser/layout-parser
- A Python Library for Document Layout Understanding
FastestDet
-
FastestDet: a new ultra real-time anchor free target detection algorithm designed for ARM CPU, with only 250K parameters,
The time consumption in the table is measured by ncnn. The test platform is RK3568 ARM CPU. Compared with Yolo-fastest, the time consumption of fastestdet single core is reduced by 50%, and the index of map0.5 is 3.4% higher than Yolo-fastest. In fact, due to the increase of input resolution, the calculation amount of FastestDet is nearly twice that of Yolo-fastest. However, thanks to the minimalist network structure and the reduction of memory access, the actual test time on multiple platforms is greatly reduced, especially on single core or weak performance platforms, and the speed is increased by 50%+
What are some alternatives?
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
PaddleViT - :robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
py-pdf-parser - A Python tool to help extracting information from structured PDFs.
ssd_keras - A Keras port of Single Shot MultiBox Detector
tika-python - Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.
BCNet - Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]
simpletransformers - Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
shabby-pages - ShabbyPages is a state-of-the-art corpus of born-digital document images with both ground truth and distorted versions appropriate for use in training models to reverse distortions and recover to original denoised documents.
pdf-extract - A rust library for extracting content from pdfs
GDR-Net - GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)
DA-RetinaNet - Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'