-
公开(公告)号：US20190266706A1
公开(公告)日：2019-08-29
申请号：US15907526
申请日：2018-02-28
Applicant: Adobe Inc.
Inventor： Prasenjit Mondal , Ruppesh Nalwaya , Ram Bhushan Agrawal , Deepanshu Arora , Anuj Shara
Abstract: Techniques are disclosed for generating a shadow map of a digital image. In some examples, a method may include generating a shadow mask of a digital image, generating a dilated de-noised binarized gradient image based on the shadow mask, generating a binarized median-filtered gray image based on the digital image and the dilated de-noised binarized gradient image, and generating a shadow map based on the shadow mask and the binarized median-filtered gray image. The generated shadow map can then be used to remove shadows from the digital image without degrading the quality of the image content in the digital image.
-
Patent Agency Ranking
公开(公告)号：US10997453B2
公开(公告)日：2021-05-04
申请号：US16260762
申请日：2019-01-29
Applicant: Adobe Inc.
Inventor： Prasenjit Mondal , Anuj Shara , Ankit Bal
Abstract: While a user holds a camera positioned relative to an object, a first image of the object and a second image of the object, as captured by the camera, may be obtained. Intensity variations between a first intensity map of the first image and a combination intensity map obtained from the first intensity map and a second intensity map of the second image may be compared. Then, a shadow may be identified within the first image, based on the intensity variations.
-
公开(公告)号：US10970847B2
公开(公告)日：2021-04-06
申请号：US16413922
申请日：2019-05-16
Applicant: Adobe Inc.
Inventor： Prasenjit Mondal , Anuj Shara , Ankit Bal , Deepanshu Arora , Siddharth Kumar
Abstract: Techniques are disclosed for document boundary detection (BD) from an input image using a combination of deep learning model and image processing algorithms. Quadrilaterals approximating the document boundaries in the input image are determined and rated separately using both these approaches: deep leaning using convolutional neural network (CNN) and heuristics using image processing algorithms. Thereafter, the best rated quadrilateral is selected from the quadrilaterals obtained from both the approaches.
-
公开(公告)号：US20200242388A1
公开(公告)日：2020-07-30
申请号：US16260762
申请日：2019-01-29
Applicant: Adobe Inc.
Inventor： Prasenjit Mondal , Anuj Shara , Ankit Bal
Abstract: While a user holds a camera positioned relative to an object, a first image of the object and a second image of the object, as captured by the camera, may be obtained. Intensity variations between a first intensity map of the first image and a combination intensity map obtained from the first intensity map and a second intensity map of the second image may be compared. Then, a shadow may be identified within the first image, based on the intensity variations.
-
公开(公告)号：US20200077005A1
公开(公告)日：2020-03-05
申请号：US16116764
申请日：2018-08-29
Applicant: Adobe Inc.
Inventor： Prasenjit Mondal , Anuj Shara , Ankit Bal
Abstract: There are described mobile devices, and methods thereof, for real time analyses of captured images. The device determines whether a light level of a first image meets or exceeds a low light threshold. The device also determines whether a shadow level of the first image meets or exceeds a shadow threshold in response to determining the light level does not meet or exceed the low light threshold. The light source is activated in response to determining the light level meets or exceeds the low light threshold or the shadow level meets or exceeds the shadow threshold. The device further determines whether a glare level of a second image meets or exceeds a glare threshold in response to identifying the second image. If so, then a final image is captured with the light source inactive. Otherwise, the final image is captured with the light source active.
-
公开(公告)号：US10559067B2
公开(公告)日：2020-02-11
申请号：US15907526
申请日：2018-02-28
Applicant: Adobe Inc.
Inventor： Prasenjit Mondal , Ruppesh Nalwaya , Ram Bhushan Agrawal , Deepanshu Arora , Anuj Shara
Abstract: Techniques are disclosed for generating a shadow map of a digital image. In some examples, a method may include generating a shadow mask of a digital image, generating a dilated de-noised binarized gradient image based on the shadow mask, generating a binarized median-filtered gray image based on the digital image and the dilated de-noised binarized gradient image, and generating a shadow map based on the shadow mask and the binarized median-filtered gray image. The generated shadow map can then be used to remove shadows from the digital image without degrading the quality of the image content in the digital image.
-
-
-
-
-
Search Results
6
records
(took 0.012 seconds)
