Shutterfly has been granted a patent for a photo design smart assistant system that reduces similar photos for display and product design. The system includes modules for calculating similarity distances between images, grouping images into bursts based on similarity distances, automatically selecting images from bursts for design creation, and producing physical photo products. The system uses hash values and threshold values to determine duplicate and new images within bursts. GlobalData’s report on Shutterfly gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Shutterfly, AI for workflow management was a key innovation area identified from patents. Shutterfly's grant share as of September 2023 was 69%. Grant share is based on the ratio of number of grants to total number of patents.
Patent granted for a system to reduce similar photos
A recently granted patent (Publication Number: US11763369B2) describes a system for reducing similar photos. The system includes a computing system with a processor, a similarity distance computation module, a burst grouping module, and a memory. The system is designed to automatically group images into bursts based on their similarity distances, which are calculated using hash values. If the similarity distance between two images is below a duplicate threshold value, the first image is designated as a duplicate. If the similarity distances between the first image and other images in the burst are above the duplicate threshold value, the first image is designated as a new image. The system also includes instructions to sequence the images in a chronological sequence and group them based on image capture times or locations.
Additionally, the system can automatically group images based on various factors such as image compositions, facial expressions, orientations of faces, sizes of faces, light exposures, importance of persons in the image, scene composition, dominant colors, color histograms, block color histograms, or cloth colors and patterns. The system can calculate similarity distances using a Hamming Distance between hash values, which can be calculated using hashing methods like pHash, Radial-Hash, or Wavelet-based hash.
The system further includes a photo selection module that automatically selects at least one image from the burst of images. The duplicate image can be discarded before selecting images. The selection can be based on the detection of faces, recognition of faces of family and close friends, or positions and focus of faces in the image. The system also includes an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst. The selected image can be displayed on a device, and the system can automatically select a product type, layout, or style for the photo product design. Multiple images from the burst can be presented for user selection in the photo product design or display.
In another embodiment, the system operates on a mobile device and includes instructions to calculate hash values of images, calculate similarity distances based on differences in color densities, edge orientations, or edge densities, and automatically group the images into bursts based on the similarity distances.
Overall, this patented system provides a comprehensive solution for reducing similar photos by automatically grouping them into bursts, selecting the best images, and creating photo product designs. It utilizes various factors and techniques to determine similarity distances and offers flexibility in customization and user selection.
To know more about GlobalData’s detailed insights on Shutterfly, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
