An image processing device capable of reducing the load of image processing while shortening the time required for the image processing which uses super-resolution processing. The image processing device includes a process determination section which determines an execution necessity of the super-resolution processing in relation to image data during execution of a production process for every type of target object, a super-resolution processing section which executes the super-resolution processing which uses a plurality of items of the image data according to determination results of the process determination section to generate high resolution data, and a state recognition section which recognizes a state of the target object based on, of the image data and the high resolution data, the one corresponding to the determination results of the process determination section.

Adaptive imaging methods and systems for generating enhanced low light video of an object for medical visualization are disclosed and include acquiring, with an image acquisition assembly, a sequence of reference frames and/or a sequence of low light video frames depicting the object, assessing relative movement between the image acquisition assembly and the object based on at least a portion of the acquired sequence of reference video frames or the acquired sequence of low light video frames, adjusting a level of image processing of the low light video frames based at least in part on the relative movement between the image acquisition assembly and the object, and generating a characteristic low light video output from a quantity of the low light video frames, wherein the quantity of the low light video frames is based on the adjusted level of image processing of the low light video frames.

A video display system includes: a tone mapping processor that performs a tone mapping process of converting a luminance of a video by using conversion characteristics according to a maximum luminance of the video; and a display that displays the video that has undergone the tone mapping process. The tone mapping processor switches between a first tone mapping process of dynamically changing the conversion characteristics according to a time-dependent change in the maximum luminance of the video and a second tone mapping process that is performed using constant conversion characteristics irrespective of the time-dependent change in the maximum luminance of the video.

An electronic device may be provided with a display. A content generator such as a camera may capture images in high dynamic range mode or standard dynamic range mode. The images may have associated image metadata such as face detection information, camera settings, color and luminance histograms, and image classification information. Control circuitry in the electronic device may determine tone mapping parameters for the captured images based on the image metadata. The tone mapping parameters for a given image may be stored with the image in the metadata file. When it is desired to display the image, the control circuitry may apply a tone mapping process to the image according to the stored tone mapping parameters. The algorithm that is used to determine tone mapping parameters based on image metadata may be based on user preference data gathered from a population of users.

In embodiments, an electronic device may include a first camera disposed on one surface of the electronic device, a second camera disposed on the one surface, a depth sensor disposed on the one surface, and a processor configured to: cause the first camera to acquire a first one or more images of an external object, and generate depth information of the external object using a selected one of the first camera and second camera or the depth sensor, the selected one based on color information or texture pattern information corresponding to the external object in the first one or more images.

An image processing method and an electronic device are provided. The method includes: obtaining a plurality of first images; obtaining first depth information; generating a second image according to the plurality of first images; identifying a subject and a background of the second image according to the first depth information; determining whether the subject of the second image needs to be optimized; when the subject of the second image needs to be optimized, optimizing the subject of the second image, generating an output image according to the background and the optimized subject, and outputting the output image; and when the subject of the second image does not need to be optimized, generating the output image according to the background and the subject and outputting the output image.

A method for providing an output data set as a function of an input data set includes applying an algorithm for reducing image noise to the input data set or an intermediate data set determined as a function of the input data set to determine a noise-reduced signal data set. The method includes determining a noise data set as difference between the input data set or the intermediate data set and the signal data set. The method includes determining a modified noise data set by applying a noise-processing algorithm to the noise data set and/or determining a modified signal data set by applying a signal processing algorithm to the signal data set. The method includes determining an output data set by adding the modified noise data set to the signal data set or the modified signal data set, or adding the noise data set to the modified signal data set.

For medical imaging such as MRI, machine training is used to train a network for segmentation using both the imaging data and protocol data (e.g., meta-data). The network is trained to segment based, in part, on the configuration and/or scanner, not just the imaging data, allowing the trained network to adapt to the way each image is acquired. In one embodiment, the network architecture includes one or more blocks that receive both types of data as input and output both types of data, preserving relevant features for adaptation through at least part of the trained network.

Techniques are provided for improving image data quality, such as in functional imaging follow-up studies, using reconstruction, post-processing, and/or deep-learning enhancement approaches in a way that automatically improves analysis fidelity, such as lesion tracking fidelity. The disclosed approaches may be useful in improving the performance of automatic analysis methods as well as in facilitating reviews performed by clinician.

Disclosed is a method and apparatus for recognizing an object, the method including determining whether an image comprises a blur, determining a blur type of the blur based on control information of a vehicle, in response to the image comprising the blur, selecting a de-blurring scheme corresponding to the determined blur type, de-blurring the image using the selected de-blurring scheme, and recognizing an object in the image based the de-blurred image.