Systems and methods are disclosed for selecting target objects within digital images utilizing a multi-modal object selection neural network trained to accommodate multiple input modalities. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators corresponding to various input modalities. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user inputs corresponding to different input modalities to select target objects in digital images. Specifically, the disclosed systems and methods can transform user inputs into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

Disclosed is a computer implemented method for identifying an object in a plurality of images. The method may include a step of receiving, through an input device, a delineation of the object in at least one image of the plurality of images. Further, the method may include a step of identifying, using the processor, an image region corresponding to the object in the at least one image based on the delineation. Furthermore, the method may include a step of tracking, using the processor, the image region across the plurality of images.

Systems and techniques are described herein for directing a user conversation to obtain an editing query, and removing and replacing objects in an image based on the editing query. Pixels corresponding to an object in the image indicated by the editing query are ascertained. The editing query is processed to determine whether it includes a remove request or a replace request. A search query is constructed to obtain images, such as from a database of stock images, including fill material or replacement material to fulfill the remove request or replace request, respectively. Composite images are generated from the fill material or the replacement material and the image to be edited. Composite images are harmonized to remove editing artifacts and make the images look natural. A user interface exposes images, and the user interface accepts multi-modal user input during the directed user conversation.

Methods and systems including computer programs encoded on a computer storage medium, for generating and displaying object recognition state indicators during object recognition processing of an image. In one aspect, a method includes performing object recognition on an image displayed in an application environment of an application on a user device using an object recognition model having multiple object recognition states including an identification state, where a candidate object in the image is positively identified, and one or more precursor states to the identification state, and where each of the precursor states has a different respective indicator for display within the image during the respective precursor state that visually emphasizes the candidate object and the identification state has a different respective indicator for display within the image during the identification state that visually emphasizes the positively identified object as being positively identified.

Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

An image processing apparatus is configured to acquire a first image group and a second image group and execute image processing on the first and second image groups. The image processing apparatus includes: a processor comprising hardware, wherein the processor is configured to: compare the number of images of interest in the first image group, with the number of images of interest in the second image group; and determine, based on a result of the comparison, priority of processing on the first image group and processing on the second image group.

Methods and systems including computer programs encoded on a computer storage medium, for generating and displaying object recognition state indicators during object recognition processing of an image. In one aspect, a method includes performing object recognition on an image displayed in an application environment of an application on a user device using an object recognition model having multiple object recognition states including an identification state, where a candidate object in the image is positively identified, and one or more precursor states to the identification state, and where each of the precursor states has a different respective indicator for display within the image during the respective precursor state that visually emphasizes the candidate object and the identification state has a different respective indicator for display within the image during the identification state that visually emphasizes the positively identified object as being positively identified.

Systems and methods are disclosed for selecting target objects within digital images. In particular, in one or more embodiments, the disclosed systems and methods generate a trained neural network based on training digital images and training indicators. Moreover, one or more embodiments of the disclosed systems and methods utilize a trained neural network and iterative user indicators to select targeted objects in digital images. Specifically, the disclosed systems and methods can transform user indicators into distance maps that can be utilized in conjunction with color channels and a trained neural network to identify pixels that reflect the target object.

An apparatus comprises at least one processing device comprising a processor coupled to a memory. The at least one processing device is configured to obtain an input visual stimulus, to detect feature points in the input visual stimulus, and to identify densities of the detected feature points in each of two or more distinct regions of the input visual stimulus. The at least one processing device is also configured to determine relative information density in the two or more distinct regions of the input visual stimulus. The at least one processing device is further configured to modify a design of the input visual stimulus to adjust the relative information density among at least two of the two or more distinct regions of the input visual stimulus.

A system and method for imaging a target in a patient's body uses a pre-acquired image of the target and a catheter having a position sensor and an ultrasonic imaging sensor. The catheter is placed in the patient's body and positional information of a portion of the catheter in the patient's body is determined using the position sensor. The catheter is used to generate an ultrasonic image of the target using the ultrasonic imaging sensor. An image processor is used for determining positional information for any pixel of the ultrasonic image of the target and registering the pre-acquired image with the ultrasonic image; and a display is used for displaying the registered pre-acquired image and ultrasonic image.