Skip to main content

Use OpenCV to extract image crops using homography and feature matching

Project description

Image extraction using a template. Uses homography and feature matching, storing results in a SQLite database in the user’s home directory for faster reprocessing.

Usage

from image_extract.extract import Extracter
ex = Extracter()
ex.crop_images(image_directory, crop_template, file_extension[, match_points])

Successful crops are extracted to a directory called successful_crops, directly underneath image_directory. Each template used creates a subdirectory, named after its md5 hash:

image_directory
    - img1.jpg
    - …
    - imgn.jpg
    - successful_crops
        - 2a1bdab44c5e81af34f47f3395a3da7e
            - img1_cropped.jpg

The optional match_points argument controls the number of matching points which must be detected in order for a template match to be deemed successful. It’s set to 30 by default.

Summaries

Call ex.summary(path) to see information on extracted crops for a given directory.

Deleting Extracted Crops

Call ex.delete(path[, template_md5]) to delete extracted crops for a given template. If no template md5 value is given, all extracted crops in that directory are removed.

Accuracy

For best results, the template image should be of the same (or similar) resolution as the image from which the crop is to be extracted.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

imagecrop-0.0.10-py2-none-any.whl (9.6 kB view hashes)

Uploaded Python 2

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page