abraia 0.9.0

Abraia Python SDK

Abraia-Multiple image analysis toolbox

The Abraia-Multiple package provides and easy and practical way to analyze and classify images directly from your browser. You just need to click on the open in Colab button to start with one of the available notebooks:

• Simple image analysis

• Deep image classification

• Hyperspectral image analysis

• Deep hyperspectral image classification

The multiple module provides support for HyperSpectral Image (HSI) analysis and classification.

MULTIPLE is result and it is being developed by ABRAIA in the Multiple project.

Configuration

Installed the package, you have to configure your ABRAIA KEY as environment variable:

export ABRAIA_KEY=api_key

On Windows you need to use set instead of export:

set ABRAIA_KEY=api_key

NOTE: To persist the configuration use your system options to set your ABRAIA_KEY environment variable and avoid to run the previous command every time you start a terminal/console session.

Hyperspectral image analysis toolbox

MULTIPLE provides seamless integration of multiple HyperSpectral Image (HSI) processing and analysis tools, integrating starte-of-the-art image manipulation libraries to provide ready to go scalable multispectral solutions.

For instance, you can directly load and save ENVI files, and their metadata.

from abraia import Multiple

multiple = Multiple()

img = multiple.load_image('test.hdr')
meta = multiple.load_metadata('test.hdr')
multiple.save_image('test.hdr', img, metadata=meta)

Upload and load HSI data

To start with, we may upload some data directly using the graphical interface, or using the multiple api:

multiple.upload_file('PaviaU.mat')

Now, we can load the hyperspectral image data (HSI cube) directly from the cloud:

img = multiple.load_image('PaviaU.mat')

Basic HSI visualization

Hyperspectral images cannot be directly visualized, so we can get some random bands from our HSI cube, and visualize these bands as like any other monochannel image.

from abraia import hsi

imgs, indexes = hsi.random(img)

plt.figure()
fig, ax = plt.subplots(2, 3)[1].reshape(-1)
for i, im in enumerate(imgs):
    ax[i].imshow(im, cmap='jet')
    ax[i].axis('off')
plt.show()

Pseudocolor visualization

A common operation with spectral images is to reduce the dimensionality, applying principal components analysis (PCA). We can get the first three principal components into a three bands pseudoimage, and visualize this pseudoimage.

pc_img = hsi.principal_components(img)
hsi.plot_image(pc_img, 'Principal components')

Classification model

Two classification models are directly available for automatic identification on hysperspectral images. One is based on support vector machines ('svm') while the other is based on deep image classification ('hsn'). Both models are available under a simple interface like bellow:

n_bands, n_classes = 30, 17
model = hsi.create_model('hsn', (25, 25, n_bands), n_classes)
model.train(X, y, train_ratio=0.3, epochs=5)
y_pred = model.predict(X)

Image analysis toolbox

Abraia provides a direct interface to directly load and save images. You can easily load the image data and the file metadata, or save a new image.

from abraia import Abraia

abraia = Abraia()

img = abraia.load_image('test.jpg')
meta = abraia.load_metadata('test.jpg')
abraia.save_image('test.png', img)

You can directly visualize the image using Matplotlib.

import matplotlib.pyplot as plt

plt.figure()
plt.title('Image')
plt.imshow(img)
plt.axis('off')
plt.show()

Upload and list files

Upload a local src file or a remote url to the cloud path and return the list of files and folders on the specified cloud folder.

folder = 'test/'
src = 'images/test.png'
path = f"{folder}test.png"
abraia.upload_file(src, path)
files, folders = abraia.list_files(folder)

Automatic image detection

Simply detect labels (tags), capture text, or detect faces in images (must be in JPEG format).

labels = abraia.detect_labels(path)
lines = abraia.capture_text(path)
faces = abraia.detect_faces(path)

Download and remove files

You can download or remove an stored file just specifying its path.

path = 'test/birds.jpg'
dest = 'images/birds.jpg'
abraia.download_file(path, dest)
abraia.remove_file(path)

Command line interface

The Abraia CLI tool provides a simple way to bulk resize, convert, and optimize your images and photos for web. Enabling the conversion from different input formats to get images in the right formats to be used in the web - JPEG, WebP, or PNG -. Moreover, it supports a number of transformations that can be applied to image batches. So you can easily convert your images to be directly published on the web.

Installation

The Abraia CLI is a Python tool which can be installed on Windows, Mac, and Linux:

python -m pip install -U abraia

The first time you run Abraia CLI you need to configure your API key, just write the command bellow and paste your key.

abraia configure

Resize images

To compress an image you just need to specify the input and output paths for the image:

abraia convert images/birds.jpg images/birds_o.jpg

To resize and optimize and image maintaining the aspect ratio is enough to specify the width or the height of the new image:

abraia convert --width 500 images/usain-bolt.jpeg images/usaint-bolt_500.jpeg

You can also automatically change the aspect ratio specifying both width and height parameters and setting the resize mode (pad, crop, thumb):

abraia convert --width 333 --height 333 --mode pad images/lion.jpg images/lion_333x333.jpg
abraia convert --width 333 --height 333 images/lion.jpg images/lion_333x333.jpg

So, you can automatically resize all the images in a specific folder preserving the aspect ration of each image just specifying the target width or height:

abraia convert --width 300 [path] [dest]

Or, automatically pad or crop all the images contained in the folder specifying both width and height:

abraia convert --width 300 --height 300 --mode crop [path] [dest]

Convert images

The JPEG image format is still the most common format to publish photos on the web. However, converting images to WebP provides a significant improvement for web publishing.

To convert images to a web format (JPEG, PNG, WebP) or between these formats you just need to change the filename extension for the destination file:

abraia convert garlic.jpg garlic.webp

In addition, you can also convert SVG and PSD files. For instance, converting a SVG to PNG is so simple as to type the command bellow:

abraia convert bat.svg bat.png

The SVG vector image is rendered in a Chrome instance to provide maximum fidelity, and preserving the transparent background.

Moreover, you can easily convert a PSD file (the layered image file used in Adobe Photoshop for saving data) flattening all the visible layers with a command like bellow:

abraia convert strawberry.psd strawberry.jpg
abraia convert strawberry.psd strawberry.png

When the PSD file is converted to JPEG a white background is added automatically, because the JPEG format does not support transparency. Instead, using the PNG or the WebP format you can preserve the transparent background.

Or, convert a batch of Photoshop files with a simple command. Just copy your PSD files to a folder, for instance the photoshop folder, and convert all the files in that folder.

abraia convert photoshop

You can also take web from the command line just specifying and url to get the capture.

abraia convert https://abraia.me screenshot.jpg

License

This software is licensed under the MIT License. View the license.