Mechanism to facilitate image translation
Assigneesalesforce.com, inc.
InventorAmit Gupta
Life of this patent
Estimating the term…
Abstract
Techniques and structures to facilitate conversion of a workflow process is disclosed. The techniques include receiving an image, identifying one or more objects included in the image, identifying one or more properties associated with each of the one or more objects, generating a matrix including data including the identified objects and associated properties and processing the matrix at a machine learning model to determine whether the image is to be translated based on a determination that one or more objects and associated properties within the image are required to be translated.
Claims20
A method, comprising:
- generating or updating, by a computing system including a processor, a set of weights of a machine learning model using a set of data, the set of weights corresponding to a set of properties;
- obtaining, by the computing system, an image;
- performing, by the computing system, object detection such that one or more objects in the image are detected;
- identifying, by the computing system for at least one of the objects, a set of property values corresponding to the set of properties;
- generating, by the computing system, a matrix having data including, for at least one of the objects, the corresponding set of property values;
- and
- determining, by the computing system, by applying the machine learning model to the matrix, whether the image is to be translated, wherein determining whether the image is to be translated includes:
- applying, for at least one of the objects, at least a first weight of the set of weights to at least a first value of the set of property values of the object such that an output value is generated, the first value and first weight corresponding to a first property of the set of properties;
- and
- determining whether the image is to be translated based, at least in part, on the output value.
A non-transitory computer-readable medium having stored thereon instructions that, when executed by one or more processors, cause the one or more processors to:
- generate or update a set of weights of a machine learning model using a set of data, the set of weights corresponding to a set of properties;
- obtain an image;
- perform object detection such that one or more objects in the image are detected;
- identify, for at least one of the objects, a set of property values corresponding to the set of properties;
- generate a matrix having data including, for at least one of the objects, the corresponding set of property values;
- and
- determine, by applying the machine learning model to the matrix, whether the image is to be translated, wherein determining whether the image is to be translated includes:
- applying, for at least one of the objects, at least a first weight of the set of weights to at least a first value of the set of property values of the object such that an output value is generated, the first value and first weight corresponding to a first property of the set of properties;
- and
- determining whether the image is to be translated based, at least in part, on the output value.
A system, comprising:
- at least one physical memory device;
- and
- one or more processors, the one or more processors cause:
- generating or updating a set of weights of a machine learning model using a set of data, the set of weights corresponding to a set of properties;
- obtaining an image;
- performing object detection such that one or more objects in the image are detected;
- identifying, for at least one of the objects, a set of property values corresponding to the set of properties;
- generating a matrix having data including, for at least one of the objects, the corresponding set of property values;
- and
- determining, by applying the machine learning model to the matrix, whether the image is to be translated, wherein determining whether the image is to be translated includes:
- applying, for at least one of the objects, at least a first weight of the set of weights to at least a first value of the set of property values of the object such that an output value is generated, the first value and first weight corresponding to a first property of the set of properties;
- and
- determining whether the image is to be translated based, at least in part, on the output value.
Dependencies are inferred from the claim text.