A document processing system processes a document image to identify document image regions including floating images, structured data units, and unstructured floating text. A first masked image is generated by deleting any floating images from the document image and a second masked image is generated by deleting any structured data units from the first masked image. The structured data units and the unstructured floating text are thus identified serially one after another. Textual data is extracted from the structured data units and the unstructured floating text by processing the corresponding document image regions via optical character recognition (OCR). Entities are extracted from the textual data using natural language processing (NLP) techniques.

A document processing system processes a document image to identify document image regions including floating images, structured data units, and unstructured floating text. A first masked image is generated by deleting any floating images from the document image and a second masked image is generated by deleting any structured data units from the first masked image. The structured data units and the unstructured floating text are thus identified serially one after another. Textual data is extracted from the structured data units and the unstructured floating text by processing the corresponding document image regions via optical character recognition (OCR). Entities are extracted from the textual data using natural language processing (NLP) techniques.

Selection and decoding of an optical pattern in a real scene from a frozen image of a video preview includes presenting a plurality of images on a display. A plurality of optical patterns are in the plurality of images. The display is frozen by one image, a frozen image, on the display. An optical pattern is identified by a user selecting the optical pattern in the frozen image. The optical pattern is decoded.

Selection and decoding of an optical pattern in a real scene from a frozen image of a video preview includes presenting a plurality of images on a display. A plurality of optical patterns are in the plurality of images. The display is frozen by one image, a frozen image, on the display. An optical pattern is identified by a user selecting the optical pattern in the frozen image. The optical pattern is decoded.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for predicting object pose. In one aspect, a method includes receiving an image of an object having one or more feature points; providing the image as an input to a neural network subsystem trained to receive images of objects and to generate an output including a heat map for each feature point; applying a differentiable transformation on each heat map to generate respective one or more feature coordinates for each feature point; providing the feature coordinates for each feature point as input to an object pose solver configured to compute a predicted object pose for the object, wherein the predicted object pose for the object specifies a position and an orientation of an object; and receiving, at the output of the object pose solver, a predicted object pose for the object in the image.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for predicting object pose. In one aspect, a method includes receiving an image of an object having one or more feature points; providing the image as an input to a neural network subsystem trained to receive images of objects and to generate an output including a heat map for each feature point; applying a differentiable transformation on each heat map to generate respective one or more feature coordinates for each feature point; providing the feature coordinates for each feature point as input to an object pose solver configured to compute a predicted object pose for the object, wherein the predicted object pose for the object specifies a position and an orientation of an object; and receiving, at the output of the object pose solver, a predicted object pose for the object in the image.

An apparatus for determining a speed of a vehicle along a road by processing a first image and a second image of the road captured by a camera on the vehicle and comprising respective road marker images of a road marker, the apparatus arranged to: determine a location of the road marker in the first image; predict a location of the road marker in the second image based on the determined location, an estimate of the vehicle speed, and a time period between capture of the images; detect the road marker in a portion of the second image at the predicted location; estimate a distance moved by the vehicle during the time period based on the determined location, and a location of the detected road marker in the portion of the second image; and calculate the speed based on the estimated distance and the time period.

Selection of on optical pattern in a scene is identified by overlaying, on a display, an indicator of a detected optical pattern identifying a location of the optical pattern in one or more images, receiving a user input on the display at a position that does not overlap the location of the optical pattern, and presenting information related to the optical pattern, based on receiving the user input, even though the position of user input did not overlap the location of the optical pattern. The user input can be received at a detached selection indicator and/or using an adaptive input area.

Selection of on optical pattern in a scene is identified by overlaying, on a display, an indicator of a detected optical pattern identifying a location of the optical pattern in one or more images, receiving a user input on the display at a position that does not overlap the location of the optical pattern, and presenting information related to the optical pattern, based on receiving the user input, even though the position of user input did not overlap the location of the optical pattern. The user input can be received at a detached selection indicator and/or using an adaptive input area.

A system for detecting and associating elements in an image comprises detecting a plurality of text tokens in a query image. A first element is determined based on an entry point object list and the plurality of text tokens, wherein the entry point object list comprises of text objects or template shapes present in the query image. A plurality of region of interests (ROIs) around the first element in the query image are determined and a plurality of ROI images are created from the query image based on the plurality of ROIs. Determine a potential second element present in the plurality of ROI images. Generate a confidence score for each of the potential second elements. Filter the results based on the confidence score and a predetermined threshold to determine a second element. Subsequently, associate the second element with the first element as single component.