-
公开(公告)号：US20230063209A1
公开(公告)日：2023-03-02
申请号：US17464036
申请日：2021-09-01
发明人： Omar OREIFEJ
摘要： A system and method for denoising a sequence of images while maintaining a consistent appearance among images displayed consecutively in the sequence. A machine learning system maps a first input image in the sequence of images to a first output image based on a neural network algorithm and determines a first network loss based on differences between the first output image and a ground truth image. The system further maps a second input image in the sequence of images to a second output image based on the neural network algorithm and determines a second network loss based on differences between the second output image and the ground truth image. The system determines a consistency loss based on differences between the first output image and the second output image and updates the neural network algorithm based on the first network loss, the second network loss, and the consistency loss.
-
公开(公告)号：US20240257303A1
公开(公告)日：2024-08-01
申请号：US18608582
申请日：2024-03-18
IPC分类号： G06T3/4046 , G06T5/70 , G06T7/90
CPC分类号： G06T3/4046 , G06T5/70 , G06T7/90
摘要： This disclosure provides methods, devices, and systems for low-light imaging. In some implementations, an image processor may be configured to reduce or remove noise associated with an image based, at least in part, on a neural network. For example, the neural network may be trained to infer a denoised representation of the image. In some aspects, the image processor may scale the brightness level of the image to fall within a normalized range of values associated with the neural network. In some other aspects, a machine learning system may scale the brightness levels of input images to match the brightness levels of ground truth images used to train the neural network. Still further, in some aspects, the machine learning system may scale the brightness levels of the input images and the brightness levels of the ground truth images to fall within the normalized range of values during training.
-
公开(公告)号：US20220366532A1
公开(公告)日：2022-11-17
申请号：US17317227
申请日：2021-05-11
摘要： This disclosure provides methods, devices, and systems for low-light imaging. In some implementations, an image processor may be configured to reduce or remove noise associated with an image based, at least in part, on a neural network. For example, the neural network may be trained to infer a denoised representation of the image. In some aspects, the image processor may scale the brightness level of the image to fall within a normalized range of values associated with the neural network. In some other aspects, a machine learning system may scale the brightness levels of input images to match the brightness levels of ground truth images used to train the neural network. Still further, in some aspects, the machine learning system may scale the brightness levels of the input images and the brightness levels of the ground truth images to fall within the normalized range of values during training.
-
公开(公告)号：US20220366189A1
公开(公告)日：2022-11-17
申请号：US17317480
申请日：2021-05-11
摘要： This disclosure provides methods, devices, and systems for low-light imaging. The present implementations more specifically relate to selecting images that can be used for training a neural network to infer denoised representations of images captured in low light conditions. In some aspects, a machine learning system may obtain a series of images of a given scene, where each of the images is associated with a different SNR (representing a unique combination of exposure and gain settings). The machine learning system may identify a number of saturated pixels in each image and classify each of the images as a saturated image or a non-saturated image based on the number of saturated pixels. The machine learning system may then select the non-saturated image with the highest SNR as the ground truth image, and the non-saturated images with lower SNRs as the input images, to be used for training the neural network.
-
5.发明申请SYSTEMS AND METHODS FOR COARSE-TO-FINE RIDGE-BASED BIOMETRIC IMAGE ALIGNMENT 有权基于粗略的基于RIDGE的生物量图像对齐的系统和方法公开(公告)号：US20170004341A1
公开(公告)日：2017-01-05
申请号：US14788662
申请日：2015-06-30
发明人： Omar OREIFEJ , Kuntal SENGUPTA , Adam SCHWARTZ , Krishna CHINNI
CPC分类号： G06K9/001 , G06K9/0004 , G06K9/6202
摘要： Systems and methods for aligning images are disclosed. A method includes: receiving a first skeletonized biometric image; generating a first coarse representation of the first skeletonized biometric image; identifying a set of candidate transformations that align the first skeletonized biometric image to a second skeletonized biometric image based on comparing transformed versions of the first coarse representation to a second coarse representation of the second skeletonized biometric image; selecting a first candidate transformation as the candidate transformation that minimizes a difference metric between a transformed version of the first skeletonized biometric image and the second skeletonized biometric image; and determining whether the first skeletonized biometric image transformed by the first candidate transformation matches the second skeletonized biometric image, wherein the first skeletonized biometric image transformed by the first candidate transformation matches the second skeletonized biometric image if the difference metric satisfies a threshold.
摘要翻译： 公开了用于对准图像的系统和方法。 一种方法包括：接收第一骷髅生物图像; 生成所述第一骨架化生物图像的第一粗略表示; 基于将所述第一粗略表示的变换版本与所述第二骨架化生物图像的第二粗略表示进行比较来识别将所述第一骨架化生物图像与第二骨架生物图像对准的候选变换集合; 选择第一候选变换作为最小化第一骨架化生物图像的变换版本与第二骨架化生物图像之间的差异度量的候选变换; 以及确定由所述第一候选变换变换的所述第一骨架化生物图像是否与所述第二骨架化生物图像匹配，其中如果所述差值度量满足阈值，则由所述第一候选变换变换的所述第一骨架化生物图像与所述第二骨架化生物图像匹配。
-
-
-
-
搜索结果
5 条记录 (耗时 0.013 秒)
