rsi-hash-commercial (Reverse Image Search)

Version Changelog

Plugin Version	Change
v1.0.0	Initial plugin release, with OLIVE 6.1.0

Description

The goal of reverse image search is to identify whether a given image is identical or near-identical or a sub-image of any image in a database of images. The database of images to be 'indexed' are enrolled in the plugin. A test image is then compared to all indexed images. The plugin uses the perceptual hash (pHash) method to find a compact hash of each image. Comparison scores can be output between 0 and 100, with higher being more similar. With a default threshold of 85, only comparison scores equal to or above this threshold will be output.

Domains

• image-v1
  • A general all-purpose domain used for standard image comparisons.

Functionality (Traits)

The functions of this plugin are defined by its Traits and implemented API messages. A list of these Traits is below, along with the corresponding API messages for each. Click the message name below to go to additional implementation details below.

• BOUNDING_BOX_SCORER – Score all submitted images returning an unused bounding box (0,0,0,0) and a similarity score per image comparison when a score is equal to or above the threshold.
  • BoundingBoxScorerRequest
• CLASS_MODIFIER – Enroll or 'index' new images into the database ready for reverse image search of analysis images.
  • ClassModificationRequest
  • ClassRemovalRequest

Compatibility

OLIVE 6.1+

Limitations

Known or potential limitations of the plugin are outlined below.

Detection Accuracy

The plugin simply exposes a well-known phash scoring functionality, and while it was designed to be robust to image cropping, flipping, etc., it is not always the case.

Localization Of Cropped Images

Although this plugin is a bounding box scorer, it does not attempt to determine the localization of a duplicate image. For instance, if a cropped image was compared against the original image, it would not output the bounding box in which the cropped image exists from the original. Instead, a default (0,0,0,0) is output for the bounding box.

Global Options

The following options are available to this plugin, adjustable in the plugin's configuration file; plugin_config.py.

Option Name	Description	Default	Expected Range
threshold	Detection threshold: Higher value results in less detections being output, but of higher reliability.	85.0	0.0 to 100.0