In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Systems and techniques are disclosed for improvement of machine learning systems based on enhanced training data. An example method includes providing a visual concurrent display of a set of images of features, the features requiring classification by a reviewing user. The user interface is provided to enable the reviewing user to assign classifications to the images, the user interface being configured to create, read, update, and/or delete classifications. The user interface is responsive to the user, with the user response indicating at least two images with a single classification. The user interface is updated to represent the single classification.

Systems and techniques are disclosed for improvement of machine learning systems based on enhanced training data. An example method includes providing a visual concurrent display of a set of images of features, the features requiring classification by a reviewing user. The user interface is provided to enable the reviewing user to assign classifications to the images, the user interface being configured to create, read, update, and/or delete classifications. The user interface is responsive to the user, with the user response indicating at least two images with a single classification. The user interface is updated to represent the single classification.

An information processing apparatus according to one embodiment includes a memory and one or more hardware processors. The memory stores order information in which an order of pieces of meta-information for a character to be recognized is defined. The one or more hardware processors are connected to the memory and function as a recognition unit and an update unit. The recognition unit serves to perform character recognition on an image including a character string by using first meta-information specified from the pieces of the meta-information. The update unit serves to update the first meta-information to second meta-information. in accordance with the order information in a case when a confidence score of the character recognition satisfies a predetermined condition. The character recognition is performed by using the second meta-information.

This disclosure describes interactive data processing systems configured to facilitate selection by a human associate of tentative results generated by an automated system from sensor data. In one implementation, an event may take place in a materials handling facility. The event may comprise a pick or place of an item from an inventory location, movement of a user, and so forth. The sensor data associated with the event is processed by an automated system to determine tentative results associated with the event. In some situations, an uncertainty may exist as to which of the tentative results accurately reflects the actual event. The system may then determine whether the event is to be merged with one or more temporally and spatially proximate events and, if so, the sensor data and tentative results for the merged event is sent to a human associate. The associate may select one of the tentative results.

This disclosure describes interactive data processing systems configured to facilitate selection by a human associate of tentative results generated by an automated system from sensor data. In one implementation, an event may take place in a materials handling facility. The event may comprise a pick or place of an item from an inventory location, movement of a user, and so forth. The sensor data associated with the event is processed by an automated system to determine tentative results associated with the event. In some situations, an uncertainty may exist as to which of the tentative results accurately reflects the actual event. The system may then determine whether the event is to be merged with one or more temporally and spatially proximate events and, if so, the sensor data and tentative results for the merged event is sent to a human associate. The associate may select one of the tentative results.

In one embodiment, a method includes accessing first image data generated by a first image sensor having a first filter array that has a first filter pattern. The first filter pattern includes a number of first filter types. The method also includes accessing second image data generated by a second image sensor having a second filter array that has a second filter pattern different from the first filter pattern. The second filter pattern includes a number of second filter types, the number of second filter types and the number of first filter types have at least one filter type in common. The method also includes determining a correspondence between one or more first pixels of the first image data and one or more second pixels of the second image data based on a portion of the first image data associated with the filter type in common.

In one embodiment, a method includes accessing first image data generated by a first image sensor having a first filter array that has a first filter pattern. The first filter pattern includes a number of first filter types. The method also includes accessing second image data generated by a second image sensor having a second filter array that has a second filter pattern different from the first filter pattern. The second filter pattern includes a number of second filter types, the number of second filter types and the number of first filter types have at least one filter type in common. The method also includes determining a correspondence between one or more first pixels of the first image data and one or more second pixels of the second image data based on a portion of the first image data associated with the filter type in common.

A system can include one or more processors and one or more non-transitory computer-readable storage media storing computing instructions configured to run on the one or more processors and perform: generating a training dataset for training a neural network detection model; identifying, using the neural network detection model, as trained, the non-compliant content in the synthetic training images; receiving, at the neural network detection model, at least one image; and utilizing the neural network detection model to determine whether the at least one image comprises the non-compliant content. Other embodiments are disclosed herein.

A system can include one or more processors and one or more non-transitory computer-readable storage media storing computing instructions configured to run on the one or more processors and perform: generating a training dataset for training a neural network detection model; identifying, using the neural network detection model, as trained, the non-compliant content in the synthetic training images; receiving, at the neural network detection model, at least one image; and utilizing the neural network detection model to determine whether the at least one image comprises the non-compliant content. Other embodiments are disclosed herein.