A9.com, Inc.

Amazon Technologies, Inc.

Song Cao

Rahul Bhotika

Colin Jon Taylor

Meng Wang

Mark Scott Waldo

Ismet Zeki Yalniz

Michael Patrick Cutter

Jonathan Wu

Chun-Kai Wang

Hao Wu

Daniya Zamalieva

Lixin Duan

Techniques for keypoint-based multi-label word segmentation and localization are described. A machine learning model identifies bounding regions of text within an image, and then generates multiple channel matrices representing predicted keypoints of the text within the bounding regions. The keypoints can be used to rectify the corresponding graphical content from the image including the text to improve the ability to perform optical character recognition and identify the text. Line and word segmentation and localization can be performed together.

Keypoint-based multi-label word segmentation and localization

Machine learning-based approaches are used to identify complementary sets of items, such as articles of clothing and accessories that 'match,' and suggest items that would complement a given item of interest. A simulated representation of how the item of interest and the identified complementary items would look together is then generated. For example, given a particular piece of clothing or other apparel item of interest, additional items that complement the item of interest can be identified and suggested to a potential purchaser of the item. Additionally, a three-dimensional (3D) or pseudo-3D representation of a human body can be generated to model the apparel item of interest and the identified complementary apparel items to give the user an idea of how the suggested outfit would look on a user. The representation can be modified to more closely resemble a particular user.

Virtual dressing room

An auxiliary device can be used to display a fiducial that contains information useful in determining the physical size of the fiducial as displayed on the auxiliary device. A primary device can capture image data including a representation of the fiducial. The scale and orientation of the fiducial can be determined, such that a graphical overlay can be generated of an item of interest that corresponds to that scale and orientation. The overlay can then be displayed along with the captured image data, in order to provide an augmented reality experience wherein the image displayed on the primary device represents a scale-appropriate view of the item in a location of interest corresponding to the location of the auxiliary device. As the primary device is moved and the viewpoint of the camera changes, changes in relative scale and orientation to the fiducial are determined and the overlay is updated accordingly.

Auxiliary device as augmented reality platform

Growing community of inventors

Seattle, WA, United States of America

Song Cao