Our proprietary technology, DejaVuAI, is useful as a stand-alone technology or could be used in an enterprise environment (Cloud/VM) for image comparison and search. Using our scripting API, we can be paired with other databases and analytics to achieve drastic efficiency and accuracy for image recognition. This new algorithm is much faster than traditional methods for finding identical and similar images based on feature recognition (SIFT, etc.) and Artificial Intelligence / Machine Learning (AI/ML).
By utilization of this algorithm, time, energy and cost required for image likeness or recognition for still or video images could be drastically reduced. It can be used for:
• Whole or partial images
• Single or multiple objects
• Video content
• EXIF and MetaData
• Foreground, midground, background, or overlay
• AR / XR / VR content (including Lightstream)
• Spherical, volumetric, 360º and 3D (with built-in dewarping for wall, panoramic, ½ sphere, and full sphere)
• Low resolution to extremely high resolution (like logos, words, etc.)
• Common and professional / scientific image formats (HDRI)
This algorithm is the underlying engine for our Windows & Linux GUI application, Photon. This image search tool is able to identify likeness and look past images that have been altered by:
• Recoloring (including images taken with different sensors, like IR, thermal and scientific scanners, like terahertz)
• Arbitrary rotation
• Blurring
• Cropping (including irregular shapes)
• Partial Obscuring
• Scaling
• Noise (natural or artificial, including adversarial noise)
• Compression artifacts
• Skewing / shearing
• Flipping / mirroring
Search results currently provide:
• Visual comparison with automatic alignment and partial transparency
• Image registration (rotation angle, translation, shift, scale, mirror)
• Similarity Groups (shows how groups of images are related to each other, with multiple levels of association.)
• Confidence score (%)
• Multiple matches
