How to match: to learn or not to learn? (part 2)

The general pipeline of finding image correspondences.
Nearest neighbor strategy. Features from img1 (blue circles) are matched to features from img2 (red squares). You can see, that it is asymmetric and allowing “many-to-one” matches
Mutual nearest neighbor strategy. Features from img1 (blue circles) are matched to features from img2 (red squares). Only cross-consistent matches (green) are retained.
Second nearest ratio strategy. Features from img1 (blue circles) are matched to features from img2 (red squares). For each point in img1 we calculate two nearest neighbors and check their distance ratio . If both are too similar (>0.8, bottom at Figure), then the match is discarded. Only confident matches are kept. Right graph is from SIFT paper, justification of such strategy.
FGINN illustration from the MODS paper https://arxiv.org/abs/1503.02619
Learning to Find Good Correspondences https://arxiv.org/abs/1711.05971

All the matching strategies except the learned one, with toy examples are implemented here https://github.com/ducha-aiki/matching-strategies-comparison

Matching strategies comparison. The best ones are FGINN union and learned matching.

--

--

--

Computer Vision researcher and consultant. Co-founder of Ukrainian Research group “Szkocka”.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

From Sound to Image to Building an Image classifier for sound with fast.ai

Photo by Caio Silva on Unsplash

What Is ROC Curve?

The Many Flavors of Gradient Boosting Algorithms

介紹如何用AI辨識人的臉部情緒(Emotion AI) 第一部分

1 line of code for BERT, ALBERT, ELMO, ELECTRA, XLNET, GLOVE, Part of Speech with NLU and t-SNE

StackOverflow Semantic Search Engine

Machine Learning Writing Month: Generative Models

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Dmytro Mishkin

Dmytro Mishkin

Computer Vision researcher and consultant. Co-founder of Ukrainian Research group “Szkocka”.

More from Medium

Effective data cleaning using Cerebra Vision Intelligence

Defining Key Terms & Concepts in Neural Networks (Part 1)

Your Guide to Unsupervised Machine Learning — Clustering

Neural Networks: Introduction, Architecture and Working

Neural Networks :: Architecture & Introduction