The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize context-aware sensors and multi-dimensional gesture inputs across a digital image to generate enhanced digital images. In particular, the disclosed systems can provide a dynamic sensor over a digital image within a digital enhancement user interface (e.g., a user interface without visual elements for modifying parameter values). In response to selection of a sensor location, the disclosed systems can determine one or more digital image features at the sensor location. Based on these features, the disclosed systems can select and map parameters to movement directions. Moreover, the disclosed systems can identify a user input gesture comprising movements in one or more directions across the digital image. Based on the movements and the one or more features at the sensor location, the disclosed systems can modify parameter values and generate an enhanced digital image.

Provided are a panoramic photographing method and device, a camera and a mobile terminal, the method includes: when panoramic photographing is performed, firstly, a ranging device acquires the depth information of the object to be photographed, that is the distance between the object to be photographed and the photographing device, and then the offset corresponding to the current distance is acquired according to a preset mapping relationship, and the original imaging of the object to be photographed is subsequently shifted in the panoramic image to form a corrected panoramic image.

Processing a dithered image comprising a grid of pixels including defining an array of pixels corresponding to a sub-region of the image; performing edge detection along the rows and the columns of the array; counting the number of edges detected along the rows of the array to determine the number of horizontal edges in the array; counting the number of edges detected along the columns of the array to determine the number of vertical edges in the array; identifying whether the sub-region is dithered based on the number of horizontal and vertical edges in the array; and selectively processing the corresponding sub-region of the image based on whether or not the sub-region is identified to be dithered. The identification step may also be based on the lengths of segments of similar pixels in the lines of the array.

The present disclosure provides a face identification method and a terminal device using the same. The method includes: obtaining a to-be-detected image; performing a brightness enhancement process on the to-be-detected image based on a preset second calculation method to generate a to-be-identified face image; obtaining a first channel value of each channel corresponding to each pixel in the to-be-identified face image; performing another brightness enhancement process on the to-be-identified face image based on each first channel value and a preset first calculation method to obtain a target to-be-identified face image; and performing a face identification process on the target to-be-identified face image to obtain an identification result. Through the above-mentioned scheme, an enhanced face identification manner for the images of low brightness is provided.

A wide field fundus camera is disclosed to implement multiple illumination beam projectors and to capture multiple retinal images at various viewing angles to facilitate wide field retinal examination. The wide field fundus camera contemplates an ultra-wide field lens that can provide edge to edge imaging of the entire retina at a single alignment. The wide field fundus camera contemplates configuration of said multiple illumination beam projectors to provide visualization of retina and Purkinje reflections simultaneously to facilitate determination of proper camera alignment with the eye. The wide field fundus camera further contemplates control of multiple illumination beam projectors in a programmable manner to further assess alignment of each illumination beam projector with the eye and to capture said multiple retinal images. The wide field fundus camera further contemplates a consumer image recording device with fast auto focusing and fast continuous image capture to make the device easy to use and quick to respond. The wide field fundus camera further contemplates narrow and broad slit beam illuminations to enhance autofocusing, imaging through less transparent crystalline lens, and reduction of haze due to reflected and scattered light from camera and ocular surfaces other than the retina. The wide field camera contemplates a real-time algorithm to reduce said reflected and scattered light haze in said retinal images. The wide field camera further contemplates automated montage of said multiple retinal images into a single wide field FOV retinal montage and automated removal reflected and scattered light haze from said retinal montage. The wide field camera further contemplates to automatically identify camera alignment with the eye and standardize an alignment procedure to simplify reflected and scattered light haze to facilitate dehaze and auto montage of said retinal images.

Disclosed is a method of enhancing the visibility of blood vessels in a colour image captured by an image capturing device of a medical device. The colour image having a plurality of colour channels and a plurality of pixels. The method comprises for at least some of said plurality of pixels the steps of: (a) processing data obtained from a first colour channel together with data obtained from a second colour channel to determine a value of a first parameter indicative of the intensity in the red spectrum relative to the total intensity of said pixel; (b) using said value of said first parameter to alter said pixel, wherein said first parameter has at least three possible values, and wherein the strength of the alteration is dependent on the value of said first parameter.

In implementations of systems for single image reflection removal, a computing device implements a removal system to receive data describing a digital image that depicts light reflected by a surface and light transmitted through the surface. The removal system predicts an edge map of a transmitted image for the light transmitted through the surface by processing the data using a first machine learning model trained on a first type of training data. A reflected component is predicted for the light reflected by the surface by processing the data using a second machine learning model trained on a second type of training data. A corrected digital image is generated that does not depict the light reflected by the surface based on the data, the edge map of the transmitted image, and the reflected component.

Methods, systems, and non-transitory computer readable media are disclosed for intelligently enhancing details in edited images. The disclosed system iteratively updates residual detail latent code for segments in edited images where detail has been lost through the editing process. More particularly, the disclosed system enhances an edited segment in an edited image based on details in a detailed segment of an image. Additionally, the disclosed system may utilize a detail neural network encoder to project the detailed segment and a corresponding segment of the edited image into a residual detail latent code. In some embodiments, the disclosed system generates a refined edited image based on the residual detail latent code and a latent vector of the edited image.

An image processing method includes a first step of acquiring input data including a captured image and optical system information relating to a state of an optical system used for capturing the captured image and a second step of inputting the input data to a machine learning model and of generating an estimated image acquired by sharpening the captured image or by reshaping blurs included in the captured image.

Methods and apparatus are disclosed for implementing data augmentation within a storage controller of a data storage device based on machine learning data read from a non-volatile memory (NVM) array of a memory die. Some particular aspects relate to configuring the storage controller to generate augmented versions of training images for use in training a Deep Learning Accelerator of an image recognition system by rotating, translating, skewing, cropping, etc., a set of initial training images obtained from a host device and stored in the NVM array. Other aspects relate to controlling components of the memory die to generate noise-augmented images by, for example, storing and then reading training images from worn regions of the NVM array to inject noise into the images. Data augmentation based on data read from multiple memory dies is also described, such as image data spread across multiple NVM arrays or multiple memory dies.