Abstract: A system and method that generates a planogram is disclosed. The method includes receiving, from an image processing module, a realogram, the realogram including information about items recognized in an image, aligning the items in the realogram using the information about the items recognized in the image, relocating the items horizontally and vertically such that the items are distributed among a plurality of aligned, non-overlapping slots, and providing the relocated items for display as a planogram of the items.

Abstract: A system and method that gathers and labels images for use by a machine learning algorithm for image classification is disclosed. The method includes acquiring a preview image including a portion of a scene, generating a user interface including the preview image, performing object detection on the preview image to detect a set of items, adding, to the first preview image, a set of regions of interest based on the object detection, each region of interest highlighting a location of a corresponding item in the set of items, receiving an image corresponding to the preview image, determining an object identifier associated with an item, and labeling the item in the image using the object identifier and a region of interest corresponding to the item.

Abstract: A system and method for image processing result visualization. The method includes receiving a job, wherein the job includes a panoramic image and image recognition information, and creating a visualization based on the job, wherein the visualization includes the panoramic image with the image recognition information layered over the panoramic image.

Abstract: A system and method that allows the capture of a series of images to create a single linear panoramic image is disclosed. The method includes capturing an image, dynamically comparing a previously captured image with a preview image on a display of a capture device until a predetermined overlap threshold is satisfied, generating a user interface to provide feedback on the display of the capture device to guide a movement of the capture device, and capturing the preview image with enough overlap with the previously captured image with little to no tilt for creating a linear panorama.

Abstract: The disclosure includes a system and method for aligning a realogram and a planogram. An alignment module of an image recognition application receives a realogram, the realogram including information about product recognitions, and a planogram corresponding to the realogram. The alignment module also generates a planogram brand chunk in the planogram, the planogram brand chunk grouping a plurality of planogram product facings belonging to a same brand, and a realogram brand chunk in the realogram based on the planogram brand chunk. The alignment module additionally identifies a planogram product facing in the planogram brand chunk and a realogram product facing in the realogram brand chunk and aligns the planogram product facing with the realogram product facing.

Abstract: The disclosure includes a system and method for comparing a realogram and a planogram to determine differences and generate suggestions, for example, a corrective action, and present the corrective action to a user. An application receives a realogram, the realogram including information about product recognitions, and a planogram corresponding to the realogram. The application aligns the realogram with the planogram using the information about product recognitions. The application retrieves a rule, detects an issue in the realogram based on applying the rule to the realogram aligned with the planogram, generates a corrective action corresponding to the issue in the realogram, and provides the corrective action for display as an overlay on the realogram.

Abstract: A system and method that gathers and labels images for use by a machine learning algorithm for image classification is disclosed. The method includes acquiring a preview image including a portion of a scene, generating a user interface including the preview image, performing object detection on the preview image to detect a set of items, adding, to the first preview image, a set of regions of interest based on the object detection, each region of interest highlighting a location of a corresponding item in the set of items, receiving an image corresponding to the preview image, determining an object identifier associated with an item, and labeling the item in the image using the object identifier and a region of interest corresponding to the item.

Abstract: A crowdsourced question and answer platform enhanced with image recognition technology is disclosed. The platform generates and organizes conversations surrounding an object recognized from an image uploaded by a user. Generating and organizing conversations includes receiving an image a from a user, analyzing the image to recognize an object in the image, receiving a comment related to the recognized object in the image from the user, generating content related to the recognized object in the image based on the received comment and adding the content related to the recognized object in the image to a conversation corresponding to the recognized object in the image.

Abstract: A system and method for image processing result visualization. The method includes receiving a job, wherein the job includes a panoramic image and image recognition information, and creating a visualization based on the job, wherein the visualization includes the panoramic image with the image recognition information layered over the panoramic image.

Abstract: A system and method for generating a conversation in a social network based on visual search results. A mixed media reality (MMR) engine indexes source materials as MMR objects, receives images from a user device and identifies matching MMR objects. A content management engine generates metadata corresponding to the MMR objects. A social network application generates conversations corresponding to the MMR object. The conversation includes multiple discussion threads. If a conversation already exists, the social network application provides the user with access to the conversation.

Abstract: A system and method that allows the capture of a series of images to create a single linear panoramic image is disclosed. The method includes capturing an image, dynamically comparing a previously captured image with a preview image on a display of a capture device until a predetermined overlap threshold is satisfied, generating a user interface to provide feedback on the display of the capture device to guide a movement of the capture device, and capturing the preview image with enough overlap with the previously captured image with little to no tilt for creating a linear panorama.

Abstract: A system and method for generating user interfaces for presenting a set of templates to guide a user to capture images of the items correctly sized under different conditions is disclosed. The method includes generating a first user interface configured to receive and present product information for an item including dimensions of the item, receiving a first image, generating a second user interface to present a template, the template including a bounding box sized to match the dimensions of the item, the second user interface configured to present the bounding box overlaid over a second image, receiving input to capture a portion of the second image within the bounding box, responsive to the input to capture the second image, generating a third user interface to present the first image and the captured portion of the second image as variants of a face of the item, and storing the captured portion of the second image as a variant of the face of the item and the information of the item in a database.

Abstract: A system and method for generating user interfaces for presenting a set of templates to guide a user to capture images of the items correctly sized under different conditions is disclosed. The method includes generating a first user interface configured to receive and present product information for an item including dimensions of the item, receiving a first image, generating a second user interface to present a template, the template including a bounding box sized to match the dimensions of the item, the second user interface configured to present the bounding box overlaid over a second image, receiving input to capture a portion of the second image within the bounding box, responsive to the input to capture the second image, generating a third user interface to present the first image and the captured portion of the second image as variants of a face of the item, and storing the captured portion of the second image as a variant of the face of the item and the information of the item in a database.

Abstract: A system and method that generates a planogram from a realogram is disclosed. The method includes receiving, from an image processing module, a realogram, the realogram including an image and information about a set of items recognized in the image, determining one or more linear groupings of a subset of the set of recognized items corresponding to each shelf, generating a planogram based on the realogram and the one or more linear groupings, generating a user interface for presentation on a client device of a user, presenting the realogram in a first portion of the user interface and the planogram in a second portion of the user interface, receiving user input via the user interface, and updating the planogram based on the user input.

Abstract: A system and method that calculates a yaw error in an image and provides a user interface to a user for correcting the yaw error. The method includes receiving an image, performing line detection in the image, computing a line parameterization for lines in the image, computing a yaw angle for the image and providing the yaw data calculated in the image.

Abstract: A Mixed Media Reality (MMR) system and associated techniques are disclosed. The MMR system provides mechanisms for forming a media document that includes media of at least two types (e.g., printed paper as a first medium and digital content and/or web link as a second medium). The MMR system provides mechanisms for forming a media document that includes media of at least two types, such as printed paper as a first medium and a digital photograph, digital movie, digital audio file, or web link as a second medium. Furthermore, the MMR system facilitates business methods that take advantage of the combination of a portable electronic device, such as a cellular camera phone, and a paper document.

Abstract: A context-aware targeted information delivery system comprises a mobile device, an MMR matching unit, a plurality of databases for user profiles, user context and advertising information, a plurality of comparison engines and a plurality of weight adjusters. The mobile device is coupled to deliver an image patch to the MMR matching unit which in turn performs recognition to produce recognize text. The recognized text is provided to a first and second comparison engines to produce relevant topics and relevant ads. The relevant topics and relevant ads are adjusted with information from a user context database including information such as location, date, time, and other information from a user profile. The third comparison engine compares the relevant topics and relevant ads to produce a set of final ads that are most related to the topics of interest for the user and delivered for display on to the mobile device.