A webcam-based 3x3x3 rubik's cube solver written in Python 3 and OpenCV.

Overview

Qbr

Qbr, pronounced as Cuber, is a webcam-based 3x3x3 rubik's cube solver written in Python 3 and OpenCV.

  • 🌈 Accurate color detection
  • 🔍 Accurate 3x3x3 rubik's cube detection
  • 🔠 Multilingual

Solve mode

solve mode

Calibrate mode

Isn't the default color detection working out for you? Use the calibrate mode to let Qbr be familiar with your cube's color scheme. If your room has proper lighting then this will give you a 99.9% guarantee that your colors will be detected properly.

Simply follow the on-screen instructions and you're ready to go.

calibrate mode calibrate mode success

Table of Contents

Introduction

The idea to create this came personally to mind when I started solving rubik's cubes. There were already so many professional programmers around the world who created robots that solve a rubik's cube in an ETA of 5 seconds and since 2016 in 1 second (link). That inspired me to create my own. I started using images only and eventually switched to webcam.

Installation

$ git clone --depth 1 https://github.com/kkoomen/qbr.git
$ cd qbr
$ python3 -m venv env
$ source ./env/bin/activate
$ pip3 install -r requirements.txt

Usage

Make sure you run source ./env/bin/activate every time you want to run the program.

Run Qbr:

$ ./src/qbr.py

This opens a webcam interface with the following things:

The first 9-sticker display (upper left corner)

This is preview mode. This will update immediately and display how Qbr has detected the colors.

The second 9-sticker display (upper left corner)

This is the snapshot state. When pressing SPACE it will create a snapshot in order to show you what state it has saved. You can press SPACE as many times as you'd like if it has been detected wrong.

Amount of sides scanned (bottom left corner)

The bottom left corner shows the amount of sides scanned. This is so you know if you've scanned in all sides before pressing ESC.

Interface language (top right corner)

In the top right corner you can see the current interface language. If you want to change the interface language you can press l to cycle through them. Continue to press l until you've found the right language.

Default language is set to English.

Available languages are:

  • English
  • Hungarian
  • Deutsch
  • French
  • Dutch
  • 简体中文

Full 2D cube state visualization (bottom right corner)

This visualization represents the whole cube state that is being saved and can be used to confirm whether the whole cube state has been scanned successfully.

Calibrate mode

The default color scheme contains the most prominent colors for white, yellow, red, orange, blue and green. If this can't detect your cube its colors properly then you can use calibrate mode.

Press c to go into calibrate mode in order to let Qbr be familiar with your cube's color scheme. Simply follow the on-screen instructions and you're ready to go.

Note: Your calibrated settings are automatically saved after you've calibrated your cube successfully. The next time you start Qbr it will automatically load it.

Tip: If you've scanned wrong, simple go out of calibrate mode by pressing c and go back into calibrate by pressing c again.

Getting the solution

Qbr checks if you have filled in all 6 sides when pressing ESC. If so, it'll calculate a solution if you've scanned it correctly.

You should now see a solution (or an error if you did it wrong).

How to scan your cube properly?

There is a strict way of scanning in the cube. Qbr will detect the side automatically, but the way you rotate the cube during the time you're scanning it is crucial in order for Qbr to properly calculate a solution. Make sure to follow the steps below properly:

  • Start off with the green side facing the camera and white on top, green being away from you. Start by scanning in the green side at this point.
  • After you've scanned in the green side, rotate the cube 90 or -90 degrees horizontally. It doesn't matter if you go clockwise or counter-clockwise. Continue to do this for the green, blue, red and orange sides until you are back at the green side.
  • You should now be in the same position like you started, having green facing the camera and white on top. Rotate the cube forward 90 degrees, resulting in green at the bottom and white facing the camera. Start scanning in the white side.
  • After you've scanned the white side, turn the cube back to how you started, having green in front again and white on top. Now rotate the cube backwards 90 degrees, resulting in green on top and yellow facing the camera. Now you can scan in the last yellow side.

If you've done the steps above correctly, you should have a solution from Qbr.

Keybindings

  • SPACE for saving the current state

  • ESC quit

  • c toggle calibrate mode

  • l switch interface language

Paramaters

You can use -n or --normalize to also output the solution in a "human-readable" format.

For example:

  • R will be: Turn the right side a quarter turn away from you.
  • F2 will be: Turn the front face 180 degrees.

Example runs

$ ./qbr.py
Starting position:
front: green
top: white

Moves: 20
Solution: U2 R D2 L2 F2 L U2 L F' U L U R2 B2 U' F2 D2 R2 D2 R2
$ ./qbr.py -n
Starting position:
front: green
top: white

Moves: 20
Solution: B2 U2 F' R U D' L' B' U L F U F2 R2 F2 D' F2 D R2 D2
1. Turn the back side 180 degrees.
2. Turn the top layer 180 degrees.
3. Turn the front side a quarter turn to the left.
4. Turn the right side a quarter turn away from you.
5. Turn the top layer a quarter turn to the left.
6. Turn the bottom layer a quarter turn to the left.
7. Turn the left side a quarter turn away from you.
8. Turn the back side a quarter turn to the right.
9. Turn the top layer a quarter turn to the left.
10. Turn the left side a quarter turn towards you.
11. Turn the front side a quarter turn to the right.
12. Turn the top layer a quarter turn to the left.
13. Turn the front side 180 degrees.
14. Turn the right side 180 degrees.
15. Turn the front side 180 degrees.
16. Turn the bottom layer a quarter turn to the left.
17. Turn the front side 180 degrees.
18. Turn the bottom layer a quarter turn to the right.
19. Turn the right side 180 degrees.
20. Turn the bottom layer 180 degrees.

Inspirational sources

Special thanks to HaginCodes for the main inspiration on how to improve my color detection.

https://github.com/HaginCodes/3x3x3-Rubiks-Cube-Solver

http://programmablebrick.blogspot.com/2017/02/rubiks-cube-tracker-using-opencv.html

https://gist.github.com/flyboy74/2cc3097f784c8c236a1a85278f08cddd

https://github.com/dwalton76/rubiks-color-resolver

License

Qbr is licensed under the MIT License.

Owner
Kim 金可明
Vim enthusiast; polyglot programmer; fullstack software engineer; QA engineer
Kim 金可明
Natural language detection

Detect the language of text. What’s so cool about franc? franc can support more languages(†) than any other library franc is packaged with support for

Titus 3.8k Jan 02, 2023
The CIS OCR PostCorrectionTool

The CIS OCR Post Correction Tool PoCoTo Source code for the Java-based PoCoTo client enabling fast interactive batch corrections of complete OCR error

CIS OCR Group 36 Dec 15, 2022
A list of hyperspectral image super-solution resources collected by Junjun Jiang

A list of hyperspectral image super-resolution resources collected by Junjun Jiang. If you find that important resources are not included, please feel free to contact me.

Junjun Jiang 301 Jan 05, 2023
A curated list of promising OCR resources

Call for contributor(paper summary,dataset generation,algorithm implementation and any other useful resources) awesome-ocr A curated list of promising

wanghaisheng 1.6k Jan 04, 2023
Fun program to overlay a mask to yourself using a webcam

Superhero Mask Overlay Description Simple project made for fun. It consists of placing a mask (a PNG image with transparent background) on your face.

KB Kwan 10 Dec 01, 2022
Responsive Doc. scanner using U^2-Net, Textcleaner and Tesseract

Responsive Doc. scanner using U^2-Net, Textcleaner and Tesseract Toolset U^2-Net is used for background removal Textcleaner is used for image cleaning

3 Jul 13, 2022
Generic framework for historical document processing

dhSegment dhSegment is a tool for Historical Document Processing. Its generic approach allows to segment regions and extract content from different ty

Digital Humanities Laboratory 343 Dec 24, 2022
Code for paper "Role-based network embedding via structural features reconstruction with degree-regularized constraint"

Role-based network embedding via structural features reconstruction with degree-regularized constraint Train python main.py --dataset brazil-flights

wang zhang 1 Jun 28, 2022
(CVPR 2021) Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

BRNet Introduction This is a release of the code of our paper Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds,

86 Oct 05, 2022
Image Smoothing and Blurring Using OpenCV

Image-Smoothing-and-Blurring-Using-OpenCV This repository contains codes for performing image smoothing and blurring using OpenCV. There are different

Happy N. Monday 3 Feb 15, 2022
Tensorflow-based CNN+LSTM trained with CTC-loss for OCR

Overview This collection demonstrates how to construct and train a deep, bidirectional stacked LSTM using CNN features as input with CTC loss to perfo

Jerod Weinman 489 Dec 21, 2022
Usando o Amazon Textract como OCR para Extração de Dados no DynamoDB

dio-live-textract2 Repositório de código para o live coding do dia 05/10/2021 sobre extração de dados estruturados e gravação em banco de dados a part

hugoportela 0 Jan 19, 2022
a Deep Learning Framework for Text

DeLFT DeLFT (Deep Learning Framework for Text) is a Keras and TensorFlow framework for text processing, focusing on sequence labelling (e.g. named ent

Patrice Lopez 350 Dec 19, 2022
Programa que viabiliza a OCR (Optical Character Reading - leitura óptica de caracteres) de um PDF.

Este programa tem o intuito de ser um modificador de arquivos PDF. Os arquivos PDFs podem ser 3: PDFs verdadeiros - em que podem ser selecionados o ti

Daniel Soares Saldanha 2 Oct 11, 2021
零样本学习测评基准,中文版

ZeroCLUE 零样本学习测评基准,中文版 零样本学习是AI识别方法之一。 简单来说就是识别从未见过的数据类别,即训练的分类器不仅仅能够识别出训练集中已有的数据类别, 还可以对于来自未见过的类别的数据进行区分。 这是一个很有用的功能,使得计算机能够具有知识迁移的能力,并无需任何训练数据, 很符合现

CLUE benchmark 27 Dec 10, 2022
This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra

Ju He 307 Jan 03, 2023
Fully-automated scripts for collecting AI-related papers

AI-Paper-Collector Web demo: https://ai-paper-collector.vercel.app/ (recommended) Colab notebook: here Motivation Fully-automated scripts for collecti

772 Dec 30, 2022
OCR-D-compliant page segmentation

ocrd_segment This repository aims to provide a number of OCR-D-compliant processors for layout analysis and evaluation. Installation In your virtual e

OCR-D 59 Sep 10, 2022
Python Computer Vision Aim Bot for Roblox's Phantom Forces

Python-Phantom-Forces-Aim-Bot Python Computer Vision Aim Bot for Roblox's Phanto

drag0ngam3s 2 Jul 11, 2022