A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, by a model that includes trainable components, a learned image representation of a target image. The operations further include generating, by a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include generating a class activation map of the target image by, at least, convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image using the class activation map of the target image.

A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, by a model that includes trainable components, a learned image representation of a target image. The operations further include generating, by a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include generating a class activation map of the target image by, at least, convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image using the class activation map of the target image.

A metadata extraction machine accesses an image that depicts an item. The item depicted in the image may have an attribute that describes a characteristic of the item and an attribute descriptor that corresponds to the attribute of the item and specifies a value of the attribute. The metadata extraction machine performs an analysis of the image. The analysis may include identifying the attribute descriptor corresponding to the attribute based on image segmentation of the image. The metadata extraction machine transmits a communication to a device of a user based on the identifying of the attribute descriptor corresponding to the attribute of the item depicted in the image.

A metadata extraction machine accesses an image that depicts an item. The item depicted in the image may have an attribute that describes a characteristic of the item and an attribute descriptor that corresponds to the attribute of the item and specifies a value of the attribute. The metadata extraction machine performs an analysis of the image. The analysis may include identifying the attribute descriptor corresponding to the attribute based on image segmentation of the image. The metadata extraction machine transmits a communication to a device of a user based on the identifying of the attribute descriptor corresponding to the attribute of the item depicted in the image.

A method includes capturing an image of a powder bed with a visible light camera that shares an optical axis with a laser beam. The laser beam is configured for heating the powder bed. The method also includes increasing first intensities of first pixels of the image that are indicative of foreign objects within the image and normalizing second intensities of second pixels of the image that are indicative of uneven illumination of the powder bed. The method also includes processing the image via contrast limited adaptive histogram equalization after increasing the first intensities and after normalizing the second intensities. The method also includes using graph-based image segmentation to identify third pixels of the image that correspond to an area of the powder bed that has been processed by the laser beam and indicating the third pixels via a user interface.

A method includes capturing an image of a powder bed with a visible light camera that shares an optical axis with a laser beam. The laser beam is configured for heating the powder bed. The method also includes increasing first intensities of first pixels of the image that are indicative of foreign objects within the image and normalizing second intensities of second pixels of the image that are indicative of uneven illumination of the powder bed. The method also includes processing the image via contrast limited adaptive histogram equalization after increasing the first intensities and after normalizing the second intensities. The method also includes using graph-based image segmentation to identify third pixels of the image that correspond to an area of the powder bed that has been processed by the laser beam and indicating the third pixels via a user interface.

The present invention features a method for automated image-based prediction of physiologic and pathologic conditions of a vaginal wall of a patient using optical coherence tomography. In some embodiments, the method may comprise capturing, by a functional optical coherence tomography imaging probe, one or more images of the vaginal wall. The method may further comprise constructing a computing device a visualization of the vaginal wall, discretizing the visualization of the vaginal wall in to a discrete model, measuring a plurality of objective attributes from the discrete model, generating, based on the plurality of objective attributes, a Vaginal Health Index (VHI), generating an associated risk value based on the VHI and a plurality of patient attributes, reconstructing the visualization of the vaginal wall based on the associated risk value, and mapping the associated risk value to the visualization of the vaginal wall such that one or more at-risk areas are highlighted.

The present invention features a method for automated image-based prediction of physiologic and pathologic conditions of a vaginal wall of a patient using optical coherence tomography. In some embodiments, the method may comprise capturing, by a functional optical coherence tomography imaging probe, one or more images of the vaginal wall. The method may further comprise constructing a computing device a visualization of the vaginal wall, discretizing the visualization of the vaginal wall in to a discrete model, measuring a plurality of objective attributes from the discrete model, generating, based on the plurality of objective attributes, a Vaginal Health Index (VHI), generating an associated risk value based on the VHI and a plurality of patient attributes, reconstructing the visualization of the vaginal wall based on the associated risk value, and mapping the associated risk value to the visualization of the vaginal wall such that one or more at-risk areas are highlighted.

Embodiments of the subject matter described herein relate to generating a decision tree based on data pre-statistics. A plurality of data samples for a node of the decision tree are obtained, and the plurality of data samples have corresponding feature values with respect to a first feature. A target range is determined from a plurality of predefined numerical ranges so that the number of feature values falling into the target range is greater than a predetermined threshold number. Then, the remaining of the feature values other than the feature values falling into the target range are assigned to the respective numerical ranges, and the feature values falling into all the numerical ranges are counted based on the assignment of the remaining of the feature values, for allocation of the plurality of data samples to child nodes of the node. Accordingly, the data processing efficiency is substantially improved.

Embodiments of the subject matter described herein relate to generating a decision tree based on data pre-statistics. A plurality of data samples for a node of the decision tree are obtained, and the plurality of data samples have corresponding feature values with respect to a first feature. A target range is determined from a plurality of predefined numerical ranges so that the number of feature values falling into the target range is greater than a predetermined threshold number. Then, the remaining of the feature values other than the feature values falling into the target range are assigned to the respective numerical ranges, and the feature values falling into all the numerical ranges are counted based on the assignment of the remaining of the feature values, for allocation of the plurality of data samples to child nodes of the node. Accordingly, the data processing efficiency is substantially improved.