https://github.com/shettysach/handwriting-calculator

A calculator that uses handwritten digits and operators to calculate the result, using contour detection and CNN model prediction. Tensorflow (Keras) is used to create, train and load the neural network model used for predictions. CustomTKinter is used to provide the GUI. OpenCV and Pillow (PIL) are used for contour detection.
https://github.com/shettysach/handwriting-calculator

basic-arithmetic-operations calculator cnn cnn-keras convolutional-neural-networks digit-recognition handwriting-calculator handwritten-digit-recognition jupyter-notebook keras keras-models keras-neural-networks mnist mnist-classification mnist-handwriting-recognition opencv opencv2 pillow tensorflow tensorflow-models

Last synced: 5 days ago
JSON representation

A calculator that uses handwritten digits and operators to calculate the result, using contour detection and CNN model prediction. Tensorflow (Keras) is used to create, train and load the neural network model used for predictions. CustomTKinter is used to provide the GUI. OpenCV and Pillow (PIL) are used for contour detection.

• Host: GitHub
• URL: https://github.com/shettysach/handwriting-calculator
• Owner: shettysach
• Created: 2023-09-28T06:51:49.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-04-15T15:22:04.000Z (7 months ago)
• Last Synced: 2024-10-11T08:43:05.005Z (28 days ago)
• Topics: basic-arithmetic-operations, calculator, cnn, cnn-keras, convolutional-neural-networks, digit-recognition, handwriting-calculator, handwritten-digit-recognition, jupyter-notebook, keras, keras-models, keras-neural-networks, mnist, mnist-classification, mnist-handwriting-recognition, opencv, opencv2, pillow, tensorflow, tensorflow-models
• Language: Jupyter Notebook
• Homepage:
• Size: 14.9 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Handwriting-Calculator

A calculator that uses handwritten digits and operators to calculate the result, using contour detection and CNN model prediction.

- Tensorflow (Keras) is used to create, train and load the neural network model used for predictions.

- CustomTKinter is used to provide the GUI.

- OpenCV and Pillow (PIL) are used to read input from the GUI canvas and to obtain contours for individual digits/operators.

- The individual digits/operators are detected and predicted. The predictions are combined into a string and evaluated to get the result.

![demo0](https://github.com/ShettySach/Handwriting-Calculator/assets/132273464/c8643ca4-2bad-46f7-ba14-13b01e7a9d2b)

#### Contour boxes (green), predicted values (blue) and accuracies (red)

![Contours](https://github.com/ShettySach/Handwriting-Calculator/assets/132273464/5e3e7121-21ca-4337-a86c-c5656c305bb2)

## Requirements -

```bash

pip install -r requirements.txt

```

* Tensorflow (Keras)

* OpenCV

* Pillow (PIL)

* Pandas

* Numpy

* CustomTkinter

## Instructions -

* Clone the repo and run the Jupyter notebook, **MAIN.ipynb** or run **MAIN.py**

* You can use digits `0 to 9`, operators `+ - × /`, decimal point `.` and parentheses `( )`

* You can also use ×× for exponentiation and // for floor division

  

### Data

* [MNIST dataset](https://www.kaggle.com/datasets/hojjatk/mnist-dataset)

* [Symbol dateset by Irfan Chahyadi ](https://github.com/irfanchahyadi/Handwriting-Calculator/blob/master/src/dataset/data.pickle)