Otary library, shape your images, image your shapes.

Welcome to Otary

Otary — elegant, readable, and powerful image and 2D geometry Python library.

Features

The main features of Otary are:

• Unification: Otary offers a cohesive solution for image and geometry manipulation, letting you work seamlessly without switching tools.

• Readability: Self-explanatory by design. Otary’s clean, readable code eliminates the need for comments, making it easy for beginners to learn and for experts to build efficiently.

• Performance: optimized for speed and efficiency, making it suitable for high-performance applications. It is built on top of NumPy and OpenCV, which are known for their speed and performance.

• Interactivity: designed to be Interactive and user-friendly, ideal for Jupyter notebooks and live exploration.

• Flexibility: provides a flexible and extensible architecture, allowing developers to customize and extend its functionality as needed.

Installation

Otary is available on PyPI. You can install it with:

pip install otary

Example

Let me illustrate the usage of Otary with a simple example. Imagine you need to:

1. read an image from a pdf file
2. draw an rectangle on it, shift and rotate the rectangle
3. crop a part of the image
4. rotate the cropped image
5. apply a threshold
6. show the image

In order to compare the use of Otary versus other libraries, I will use the same example but with different libraries. Try it yourself on your favorite LLM (like ChatGPT) by copying the query:

Generate a python code to read an image from a pdf, draw a rectangle on it, shift and rotate the rectangle, crop a part of the image, rotate the cropped image, apply a threshold on the image.

Using Otary you can do it with few lines of code:

import otary as ot

im = ot.Image.from_pdf("path/to/you/file.pdf", page_nb=0)

rectangle = ot.Rectangle([[1, 1], [4, 1], [4, 4], [1, 4]]) * 100
rectangle.shift([50, 50]).rotate(angle=30, is_degree=True)

im = (
    im.draw_polygons([rectangle])
    .crop(x0=50, y0=50, x1=450, y1=450)
    .rotate(angle=90, is_degree=True)
    .threshold_simple(thresh=200)
)

im.show()

Using Otary makes the code:

• Much more readable and hence maintainable
• Much more interactive
• Much simpler, simplifying libraries management by only using one library and not manipulating multiple libraries like Pillow, OpenCV, Scikit-Image, PyMuPDF etc.

Enhanced Interactivity

In a Jupyter notebook, you can easily test and iterate on transformations by simply commenting part of the code as you need it.

im = (
    im.draw_polygons([rectangle])
    # .crop(x0=50, y0=50, x1=450, y1=450)
    # .rotate(angle=90, is_degree=True)
    .threshold_simple(thresh=200)
)