-
公开(公告)号：US20240296302A1
公开(公告)日：2024-09-05
申请号：US18177636
申请日：2023-03-02
Applicant: Adobe Inc.
Inventor： Sumeet KHURANA , Shvet CHAKRA , Nipun PODDAR , Neveen Prakash GOEL , Amit Gupta
CPC classification number: G06K15/1836 , G06N20/00
Abstract: Methods and systems are provided for facilitating implementation of machine learning models in embedded software. In embodiments, a lean machine learning model, having a limited number of layers, is trained in association with a complex machine learning model, having a greater number of layers. To this end, a complex machine learning model, having a first number of layers, can be trained based on an output generated from a lean machine learning model used as input to the complex machine learning model. Further, the lean machine learning model, having a second number of layers less than the first number of layers, is trained using a loss value generated in association with training the complex machine learning model. Thereafter, the trained lean machine learning model can be provided for implementation in an embedded software.
-
公开(公告)号：US12067302B2
公开(公告)日：2024-08-20
申请号：US18069446
申请日：2022-12-21
Applicant: Adobe Inc.
Inventor： Nipun Poddar , Sumeet Khurana , Rebecca Eleanor Hauser , Neha Pant , Naveen Prakash Goel , David Douglas Barnes , Anas Lnu , Amit Mittal , Amit Gupta , Abhishek Kumar Pandey
CPC classification number: G06F3/1204 , G06F3/1208 , G06F3/1256 , H04N1/6097
Abstract: Spot aware print workflow techniques and system are described. In an implementation, a digital document is received for printing that includes a plurality of objects. Spot functionality is detected as corresponding to a respective object based on object properties detected for the respective object. One or more spot planes for are generated based on the spot functionality and a determination is made of color values for the one or more spot planes, respectively, based on context data describing a context, in which, the one or more spot planes are to be printed. The spot planes having the color values are output for printing by a print mechanism.
-
Patent Agency Ranking
公开(公告)号：US11645786B2
公开(公告)日：2023-05-09
申请号：US17654529
申请日：2022-03-11
Applicant: Adobe Inc.
Inventor： Meet Patel , Mayur Hemani , Karanjeet Singh , Amit Gupta , Apoorva Gupta , Balaji Krishnamurthy
CPC classification number: G06T9/002 , G06N3/08 , G06T7/0002 , G06T2207/20081 , G06T2207/20084 , G06T2207/20224
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
-
公开(公告)号：US11335033B2
公开(公告)日：2022-05-17
申请号：US17032704
申请日：2020-09-25
Applicant: Adobe Inc.
Inventor： Meet Patel , Mayur Hemani , Karanjeet Singh , Amit Gupta , Apoorva Gupta , Balaji Krishnamurthy
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
-
公开(公告)号：US20220101564A1
公开(公告)日：2022-03-31
申请号：US17032704
申请日：2020-09-25
Applicant: Adobe Inc.
Inventor： Meet Patel , Mayur Hemani , Karanjeet Singh , Amit Gupta , Apoorva Gupta , Balaji Krishnamurthy
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing deep learning to intelligently determine compression settings for compressing a digital image. For instance, the disclosed system utilizes a neural network to generate predicted perceptual quality values for compression settings on a compression quality scale. The disclosed system fits the predicted compression distortions to a perceptual distortion characteristic curve for interpolating predicted perceptual quality values across the compression settings on the compression quality scale. Additionally, the disclosed system then performs a search over the predicted perceptual quality values for the compression settings along the compression quality scale to select a compression setting based on a perceptual quality threshold. The disclosed system generates a compressed digital image according to compression parameters for the selected compression setting.
-
16.发明申请公开(公告)号：US20210368064A1
公开(公告)日：2021-11-25
申请号：US16879019
申请日：2020-05-20
Applicant: Adobe Inc.
Inventor： Vipul Aggarwal , Pranjal Bhatnagar , Nipun Poddar , Naveen Goel , Amit Gupta
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing intelligent sectioning and selective document reflow for section-based printing. For example, the disclosed systems can intelligently identify document objects (e.g., document structures and sections) within a digital document by utilizing a machine-learning model. In so doing, the disclosed systems can identify document-object types and document-object locations for the document objects in the digital document. In turn, the disclosed systems can provide, for display within a dynamic printing interface, selectable document sections comprising the identified document objects. In response to a user selection of one or more of the selectable document sections, the disclosed system can generate a modified digital document for printing by reflowing the identified document objects in accordance with the user selection. In some cases, reflowing comprises removing unselected document objects and/or repositioning one or more of the selected document objects.
-
公开(公告)号：US11178311B2
公开(公告)日：2021-11-16
申请号：US16547163
申请日：2019-08-21
Applicant: ADOBE INC.
Inventor： Vipul Aggarwal , Naveen Prakash Goel , Amit Gupta
Abstract: A method, apparatus, and non-transitory computer readable medium for color reduction based on image segmentation are described. The method, apparatus, and non-transitory computer readable medium may provide for segmenting an input image into a plurality of regions, assigning a weight to each region, identifying one or more colors for each of the regions, selecting a color palette based on the one or more colors for each of the regions and the corresponding weight for each of the regions, and performing a color reduction on the input image using the selected color palette to produce a color reduced image. The weight assigned to each region may depend on factors including relevance, prominence, focus, position, or any combination thereof.
-
-
-
-
-
-
Search Results
17
records
(took 0.026 seconds)
