GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → FantDing → Image-document-extract-and-correction

FantDing / Image-document-extract-and-correction

Licence: other
数字图像课程大作业，实现图片中文档提取与矫正。整体思路是通过hough变换检测出直线，进而得到角点，最后经过投影变换，进行矫正。整个项目只用到了opencv的IO操作(包括手写卷积，hough哈夫变换，投影变换等等)

Programming Languages

python
139335 projects - #7 most used programming language
C++
36643 projects - #6 most used programming language
shell
77523 projects

Labels

affine-transformationhough-linesdocument-extraction

Projects that are alternatives of or similar to Image-document-extract-and-correction

nemar
[CVPR2020] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Stars: ✭ 120 (+192.68%)
Mutual labels:  affine-transformation
ingest-file
Ingestors extract the contents of mixed unstructured documents into structured (followthemoney) data.
Stars: ✭ 40 (-2.44%)
Mutual labels:  document-extraction
Lucas-Kanade-Tracker
Implementation of Lucas Kanade Tracking system using six parameter affine model and recursive Gauss-Newton process.
Stars: ✭ 30 (-26.83%)
Mutual labels:  affine-transformation
Fingertip-Mixed-Reality
Affine transformation virtual 3D object using a finger gesture-based interactive system in the virtual environment.
Stars: ✭ 21 (-48.78%)
Mutual labels:  affine-transformation
Python Computer Vision from Scratch
This repository explores the variety of techniques commonly used to analyze and interpret images. It also describes challenging real-world applications where vision is being successfully used, both for specialized applications such as medical imaging, and for fun, consumer-level tasks such as image editing and stitching, which students can apply…
Stars: ✭ 219 (+434.15%)
Mutual labels:  hough-lines
Video-Stabilization-and-image-mosaicing
video stabilization: stabilize the videos which is taken from wavering camera. Image mosaicing: stitches multiple, overlapping snapshot images of a video together in order to produce one large image.
Stars: ✭ 16 (-60.98%)
Mutual labels:  affine-transformation
Imgaug
Image augmentation for machine learning experiments.
Stars: ✭ 12,107 (+29429.27%)
Mutual labels:  affine-transformation
Spatial-Transformer-Networks-with-Keras
This repository provides a Colab Notebook that shows how to use Spatial Transformer Networks inside CNNs in Keras.
Stars: ✭ 23 (-43.9%)
Mutual labels:  affine-transformation

简介

hahaha~~ 很开心又开始做新项目了，是《数字图像分析》大作业。实现文档提取与矫正。 整个项目只用到了opencv的IO操作(包括卷积，生成高斯滤波器等等)

更新

  • 2020.07.10
  • 2020.07.07
    • 使用im2col代替原来三重for循环的卷积形式，整体运行时间能减少一半 UFaXB8.png

运行纯python

默认. 有时间我添加下参数选项, 选择python还是c++版本

环境

  • pip install opencv-python numpy

run

  • python main.py
  • 在main.py中可以修改需要提取的文件，结果保存在result文件夹中

运行cpp混编

非默认. 有时间我添加下参数选项, 选择python还是c++版本

  • 配置好NumCpp / pybind11
  • 运行compile.sh脚本
  • 在corner_detection.py文件中修改c++版本卷积

技术栈

S&G ?

SG是自己乱起的，包含了两个技术栈：

  • S： Susan角点检测
  • G： Geometic几何校正

H&G !

通过实验发现直接检测角点根本实现不了，图片中角点太多，且不能加入先验进行过滤。遂通过 检测直线，求角点实现

  • H: Hough哈夫变换检测直线，得到角点
  • G: Geometic几何校正

结果

000026.jpg 000026.jpg 000872.jpg 000872.jpg 001402.jpg 001402.jpg 001552.jpg 001552.jpg 001201.jpg 001201.jpg

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].