Ricoh Company, Ltd.

Ricoh Corporation

Other

Clarifai, Inc.

Ricoh California Research Center

Michael J Gormish

Edward L Schwartz

Martin P Boliek

Kathrin Berkner

Ahmad Zandi

John W Barrus

Kurt W Piersol

Kok Gi Wu

Alexander F Keith

Stephen R Savitzky

Sergey Chemishkian

James D Allen

David Geoffrey Stork

Xu Liu

Kenneth F Gudan

Yutaka Satoh

Richard D Kosoglow

Peter E Hart

Gregory J Wolff

Serene Banerjee

Christophe Marle

Jonathan J Hull

Jorge Moraleda

Max E McFarland

Guotong Feng

Silvio Savarese

Kevin Ridout

Shu Shi

Ekta Prashnani

Berna Erol

Hiroyuki Sakuyama

Bradley J Rhodes

Matthew Donald Zeiler

Mark Peairs

Tooru Suino

Geoffrey Nudd

Anshul Garg

Timothee Bailloeul

Bharathi Shekar

Sri Kaushik Pavani

Andrea Mariotti

Steven M Blonstein

Yinqing Zhao

Michael G E Griffin

Maya Rani Gupta

Yoshio Kawajiri

Greg Wolff

Xiaojun Feng

Samuel Dodge

Jesse Rappaport

Eran Nussinovitch

Systems, methods and computer program code are provided to perform visual searches.

Automatic unstructured knowledge cascade visual search

A previously trained classification model associated with the machine learning system is configured to process an input to generate i) a first prediction that represents a characteristic associated with the input, and ii) a representation of accuracy associated with the prediction. A retraining subsystem is configured to receive the input, the first prediction, and the representation of accuracy. The retraining subsystem processes the input to generate a prediction representing a characteristic. A sufficiency of certainty of the first prediction is determined based on at least the input, the first prediction, the measure of accuracy, and the second prediction. Based at least on the determined sufficiency the retraining subsystem causes the machine learning system to be automatically retrained, be retrained using the input with active learning or not retrained.

Systems, techniques, and interfaces for obtaining and annotating training instances

A method and apparatus for displaying and interacting with a user interface are described. In one embodiment, the method comprises: receiving first content for display on a display surface, displaying the first content at a first area of the display surface, capturing a stroke when written on the display surface over a first portion of the first content, and automatically creating a first page at a second area of the display surface, the second area being different than the first area and displaying the first content with the captured stroke.

Presenting associations of strokes with content

The disclosure includes a system and method for performing image rectification using a single image and information identified from the single image. An image recognition application receives an input image, identifies a plurality of objects in the input image, estimates rectification parameters for the plurality of objects, identifies a plurality of candidate rectification parameters using a voting procedure on the rectification parameters for the plurality of objects, estimates final rectification parameters based on the plurality of candidate rectification parameters, computes a global transformation matrix using the final rectification parameters, and performs image rectification on the input image using the global transformation matrix.

Single image rectification

A system and method that determines multiple linear groups of horizontally placed items in an image is disclosed. The method includes receiving an image including a portion of a shelving unit, identifying a plurality of items in the image, determining a plurality of facings, clustering the plurality of facings, merging a plurality of clusters and determining a list of linear groups in the image.

Linear grouping of recognized items in an image

A method and apparatus for associating strokes with content are described. In one embodiment, an apparatus comprises: a memory to store contexts for a plurality of strokes, wherein each context represents an association between at least one stroke and a portion of image data previously displayed; and a matching module coupled to the memory to: receive an indication of a new stroke to be associated a first image and a first context, determine if the portion the first context is the same as, overlaps or is independent of the contexts stored in the memory, and update the memory to include the new stroke by adding the new stroke to one of the contexts stored in the memory or storing the new stroke with the first context independent of the contexts already stored in the memory.

Associating strokes with content

A system and method that determines a seam between pairs of adjacent images for panoramic image stitching is disclosed. The method includes receiving a sequence of images, determining a pair of adjacent images in the sequence of images, matching one or more objects corresponding to a same object identifier in the pair of adjacent images, determining a seam in an overlap region between the pair of adjacent images and determining a portion of pixels from each image of the pair of adjacent images to represent in a stitched panoramic image based on the seam.

Panoramic image stitching using objects

An electronic writing solution server includes a workflow dashboard application that comprises a dashboard generator. The dashboard generator receives a collection of forms, each form in the collection being of a same type and having been created from a dashboard template, the dashboard template including an association of fields, steps and indicators in each form, identifies which fields have been filled in by at least one user for each form, determines a current step of a multistep workflow based on the fields that have been filled out for each form and generates a dashboard for displaying a number of forms that correspond to each step.

Creating a dashboard for tracking a workflow process involving handwritten forms

An electronic writing solution server includes a stroke autocompletion application that comprises an autocompletion processor. The autocompletion processor loads a blank form for a user, the form being associated with a list of auto completion target, retrieves a set of regions and a first form identifier (ID) included in the list of auto completion targets, receives information about the user, identifies a set of potential completion lists from a plurality of potential completion lists stored in a database based on the set of regions, the first form ID and the information about the user, retrieves at least one stroke from the set of potential completion lists for a region in the set of regions, ranks the at least one stroke and provides the at least one stroke to the user.

Stroke autocompletion in a form

A method for product recognition from multiple images includes producing a plurality of recognition results for a plurality of input images, stitching the plurality of input images into a single stitched image; merging the plurality of recognition results using information from stitching the plurality of input images to generate a merged recognition result; and outputting the merged recognition result. The disclosure also includes systems for implementing the method.

Method for product recognition from multiple images

The disclosure includes a system and method for distinguishing between items of similar appearance that vary in size. An image recognition application receives an image including a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a dimension of the region of interest for each identified item in pixels, determines a plurality of pixel-to-physical dimension ratios for each identified item, identifies a selected pixel-to-physical dimension ratio among the plurality of pixel-to-physical dimension ratios, and determines a stock keeping unit identifier of each identified item in the image based on the selected pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.

Distinguishing between stock keeping units using hough voting methodology

The disclosure includes a system and method for aggregating form data based on marks in graphic form fields. The system includes a controller, a request customization module, a search module and a presentation module. The controller receives data indicating an initiation of a search request from a user, data describing a form selected by the user, data describing a graphic form field specified by the user in the form and data describing a region of interest specified by the user in the graphic form field. The request customization module customizes the search request using the region of interest. The search module performs a form search on a collection of form data using the search request to determine one or more matching forms that each include at least one mark satisfying the region of interest. The presentation module provides the one or more matching forms to the user.

Form aggregation based on marks in graphic form fields

Growing community of inventors

Los Altos, CA, United States of America

Michael J Gormish