Image augmentation for machine learning experiments.
-
Updated
Apr 6, 2024 - Python
Image augmentation for machine learning experiments.
A Tensorflow implementation of Spatial Transformer Networks.
A demo that implement image registration by matching SIFT descriptors and appling RANSAC and affine transformation.
[CVPR2020] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Image data augmentation on-the-fly by add new class on transforms in PyTorch and torchvision.
Stitching different perspective images into a single smooth panorama using Laplacian Blending.
Utils and convenience functions for large-scale bio-image analysis.
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)
Affine transformation virtual 3D object using a finger gesture-based interactive system in the virtual environment.
Mathematics library focused on geometry for Multiplatform Kotlin 1.3
Implementation of Lucas Kanade Tracking system using six parameter affine model and recursive Gauss-Newton process.
torch data augmentation toolbox (supports affine transform)
Geographic Coordinate Converter for Slovenia
Implementation of OpenCV methods for affine and perspective transformation
Flask Server for Face-Morp webapp. This server exposes api-endpoints to generate morphed GIFs of the incoming images.
This repository provides a Colab Notebook that shows how to use Spatial Transformer Networks inside CNNs in Keras.
This is a software utility for feature matching using affine and homography transformations
Implementation of Lucas-Kanade tracker algorithm to track a moving car, face of a baby and running Usain Bolt
This repository applies the affine and deformation transformation on the CT scan in the subject space, and register it to the MNI 1mm space
Add a description, image, and links to the affine-transformation topic page so that developers can more easily learn about it.
To associate your repository with the affine-transformation topic, visit your repo's landing page and select "manage topics."