Abstract: A method for processing image data, may include: receiving at least one image; segregating the at least one image into at least one region, based on a requested noise reduction level; and denoising the at least one image by varying at least one control feature of the segregated at least one region by a neural network to achieve the requested noise reduction level.

Abstract: A method for recognizing an action of at least one object in a plurality of images, includes obtaining a plurality of image frames by capturing at least one object on a ground plane; detecting a motion of the at least one object and a motion of the ground plane in each of the plurality of image frames; estimating a trajectory of the ground plane by tracking the motion of the ground plane; correcting the motion of the at least one object in each of the plurality of image frames based on the trajectory of the ground plane; and recognizing an action of the at least one object based on the corrected motion of the at least one object.

Abstract: There is provided a method and apparatus for performing gesture recognition in an electronic device, including: tracking a visible trajectory of a hand of a user from a plurality of frames captured by the electronic device, identifying, by the electronic device, a first frame where the hand of the user has gone out of a Field of View (FOV) of the electronic device, identifying the second frame where the hand of the user has come back into the FOV, predicting, using an Artificial Intelligence (AI) model, a trajectory of the hand of the user using one or more frames captured before the first frame, and one or more frames captured after the second frame, and recognizing at least one hand gesture performed during the visible trajectory of the hand of the user, and the predicted trajectory of the hand of the user.

Abstract: There is provided a method and electronic device for generating high resolution peak action frame. The method includes receiving a low resolution (LR) image stream with high frame speed and a high resolution (HR) image stream with low frame speed and detecting at least one pose of at least one human in the LR image stream. The method further includes obtaining a LR peak action frame in the LR image stream based on the at least one pose and identifying a close HR frame from the HR image stream which is closest to the LR peak action frame. The method further includes fetching the close HR frame from the HR image stream which is closest to the obtained LR peak action frame or generating a HR peak action frame by blending the identified HR frame and the LR peak action frame.

Abstract: A method 300B includes detecting a user input indicative of a trigger to modify the artifact of the image displayed at a user interface of an electronic device 100. Furthermore, the method 300B includes determining an artifact modification parameter based on a characteristic of the user input. Furthermore, the method 300B includes modifying the artifact in the image based on the artifact modification parameter.

Abstract: Apparatus and methods for generating High Dynamic Range (HDR) media, based on multi-stage compensation of motion in a captured scene is disclosed in the embodiments herein. Embodiments herein relates to the field of image processing devices suitable for processing two or more images of different exposures and more particularly to apparatus and methods for generating a High Dynamic Range (HDR) media, based on a multi-stage compensation of motion in a captured scene. The apparatus is configured to correct exposure alignment error and media registration error from a registered plurality of media frames comprising a plurality of exposure levels corresponding to the captured scene. The apparatus is configured to remove a plurality of false ghost artefacts in the plurality of media frames. The apparatus is configured to generate the HDR media, based on a generated ghost map.

Abstract: The present disclosure relates to method and apparatus for removing shadows from a High Resolution (HR) image. The HR image including shadows is received. The HR image converted into Low Resolution (LR) image. LR shadow-free image is generated from the LR image using first Artificial Intelligence (AI) model. A HR shadow-free image is generated based on combination of the LR shadow-free image and the HR image using second AI model. The present disclosure provides an efficient framework and lightweight network architectures which are used to remove the shadows based on corresponding shadow characteristics. The framework can be deployed in resource-constrained platforms. The present disclosure facilitates processing selected areas of the HR image and retaining the unselected area. Thus, less computational resources are required.

Abstract: A method for processing image data, may include: receiving at least one image; segregating the at least one image into at least one region, based on a requested noise reduction level; and denoising the at least one image by varying at least one control feature of the segregated at least one region by a neural network to achieve the requested noise reduction level.

Abstract: Apparatus and methods for generating High Dynamic Range (HDR) media, based on multi-stage compensation of motion in a captured scene is disclosed in the embodiments herein. Embodiments herein relates to the field of image processing devices suitable for processing two or more images of different exposures and more particularly to apparatus and methods for generating a High Dynamic Range (HDR) media, based on a multi-stage compensation of motion in a captured scene. The apparatus is configured to correct exposure alignment error and media registration error from a registered plurality of media frames comprising a plurality of exposure levels corresponding to the captured scene. The apparatus is configured to remove a plurality of false ghost artefacts in the plurality of media frames. The apparatus is configured to generate the HDR media, based on a generated ghost map.

Abstract: An image processing method, including preparing a first image; designating at least one region of interest (ROI) in the first image, generating restoration data; and generating a second image using the restoration data, the second image corresponding to the ROI, wherein a resolution of the second image is higher than a resolution of a region corresponding to the ROI in the first image.

Abstract: An image processing method, including preparing a first image; designating at least one region of interest (ROI) in the first image, generating restoration data; and generating a second image using the restoration data, the second image corresponding to the ROI, wherein a resolution of the second image is higher than a resolution of a region corresponding to the ROI in the first image.