Zorroa Corporation

Juan Jose Buhler

Daniel Elliott Wexler

Daniel Elliot Wexler

Matthew Chambers

David DeBry

A method of searching for similar images is performed at a computing system having one or more processors and memory. The method includes receiving an input image having content, and generating a feature vector corresponding to the input image according to a trained classifier model. The feature vector has multiple components. The method further includes encoding the feature vector as a similarity hash by quantizing each component. The method also includes, for each reference image in a plurality of reference images: obtaining a reference hash for the reference image; computing similarity between the input image and the reference image by computing a distance between the reference hash and the similarity hash; and determining whether the computed distance is within a predetermined threshold. When the computed distance is within the predetermined threshold, the computing system returns the reference image as an image that is similar to the input image.

Determining similarity of images using multidimensional hash vectors corresponding to the images

A method manages an image catalog at a server system. The system receives reduced-resolution versions of one or more images stored in an image database of an external service distinct from the system. For each received reduced-resolution version, the system creates an index entry in the image catalog. The system receives a query from a user and matches the query to an index entry in the catalog, which corresponds to an image stored as a full-resolution version in the image database. The system requests authorization from the owner of the image. When authorization is received, the system retrieves the full-resolution version from the image database, and temporarily stores the full-resolution version in temporary storage. The system then transmits the full-resolution version of the image to the user and releases the full-resolution version of the image from the temporary storage in response to the transmitting the full-resolution version.

Systems and methods of building and using an image catalog

A method of analyzing and organizing printed documents is performed at a computing system having one or more processors and memory. The method includes receiving one or more printed documents, each including one or more pages. The method includes processing each page of each printed document. The method includes scanning the respective page to obtain an image file. The method also includes determining a document class for the respective page by inputting the image file to one or more trained classifier models, and generating a semantic analyzer pipeline including at least an optical character recognition (OCR)-based semantic analyzer. The method also includes applying the OCR-based semantic analyzer to the preprocessed output page to generate a preprocessed output page and to extract semantic information corresponding to the respective page. The method includes determining a digital organization for the respective printed document based on the extracted semantic information and the document class.

Digital organization of printed documents according to extracted semantic information

A method of managing an image catalog is performed by one or more servers. The process receives from a first user identification of one or more images in an image database. The image database is distinct from the servers. For each of the images, the process analyzes the image to extract keywords that describe the image and creates an index entry in the image catalog. The index entry includes the keywords. The process receives a query from a second user and matches the query to an index entry in the image catalog. The index entry corresponds to a first image in the image database. The process determines whether the second user is authorized to view the first image. When the second user is authorized to view the first image, the process retrieves the first image from the image database and transmits the first image to the second user.

A process displays a concatenated array of slit-compressed images corresponding to an ordered sequence of images. The slit-compressed images are concatenated along a single dimension according to the ordered sequence of images. Each slit-compressed image has an associated query that has search terms based on the respective image. The process displays a moveable slider that moves along the single dimension and identifies a current location within the array, and displays a respective thumbnail image corresponding to the current location. The process receives user input to move the moveable slider along the single dimension to a new location. The process displays a thumbnail representation of the image corresponding to the new location and executes the query corresponding to the current image to retrieve documents from a document repository related to the current image. The process then displays the retrieved documents for user selection.

Growing community of inventors

Woodside, CA, United States of America

Juan Jose Buhler