公开(公告)号：US11861497B2

公开(公告)日：2024-01-02

申请号：US17565581

申请日：2021-12-30

Applicant: L'OREAL

Inventor： Alex Levinshtein ,  Cheng Chang ,  Edmund Phung ,  Irina Kezele ,  Wenzhangzhi Guo ,  Eric Elmoznino ,  Ruowei Jiang ,  Parham Aarabi

IPC: G06N3/08 ,  G06T7/11 ,  G06T7/90 ,  G06T1/20 ,  G06T11/00 ,  G06V10/44 ,  G06V40/16 ,  G06F18/21 ,  G06F18/24 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06F18/21 ,  G06F18/24 ,  G06T1/20 ,  G06T7/11 ,  G06T7/90 ,  G06T11/001 ,  G06V10/454 ,  G06V10/82 ,  G06V40/165 ,  G06V40/171 ,  G06T2200/24 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A system and method implement deep learning on a mobile device to provide a convolutional neural network (CNN) for real time processing of video, for example, to color hair. Images are processed using the CNN to define a respective hair matte of hair pixels. The respective object mattes may be used to determine which pixels to adjust when adjusting pixel values such as to change color, lighting, texture, etc. The CNN may comprise a (pre-trained) network for image classification adapted to produce the segmentation mask. The CNN may be trained for image segmentation (e.g. using coarse segmentation data) to minimize a mask-image gradient consistency loss. The CNN may further use skip connections between corresponding layers of an encoder stage and a decoder stage where shallower layers in the encoder, which contain high-res but weak features are combined with low resolution but powerful features from deeper decoder layers.

公开(公告)号：US20220122299A1

公开(公告)日：2022-04-21

申请号：US17565581

申请日：2021-12-30

Applicant: L'OREAL

Inventor： Alex LEVINSHTEIN ,  Cheng Chang ,  Edmund Phung ,  Irina Kezele ,  Wenzhangzhi Guo ,  Eric Elmoznino ,  Ruowei Jiang ,  Parham Aarabi

IPC: G06T11/00 ,  G06T7/11 ,  G06T7/90 ,  G06K9/62 ,  G06N3/08 ,  G06T1/20 ,  G06V10/44 ,  G06V40/16

Abstract: A system and method implement deep learning on a mobile device to provide a convolutional neural network (CNN) for real time processing of video, for example, to color hair. Images are processed using the CNN to define a respective hair matte of hair pixels. The respective object mattes may be used to determine which pixels to adjust when adjusting pixel values such as to change color, lighting, texture, etc. The CNN may comprise a (pre-trained) network for image classification adapted to produce the segmentation mask. The CNN may be trained for image segmentation (e.g. using coarse segmentation data) to minimize a mask-image gradient consistency loss. The CNN may further use skip connections between corresponding layers of an encoder stage and a decoder stage where shallower layers in the encoder, which contain high-res but weak features are combined with low resolution but powerful features from deeper decoder layers.

公开(公告)号：US11216988B2

公开(公告)日：2022-01-04

申请号：US16753214

申请日：2018-10-24

Applicant: L'OREAL

Inventor： Alex Levinshtein ,  Cheng Chang ,  Edmund Phung ,  Irina Kezele ,  Wenzhangzhi Guo ,  Eric Elmoznino ,  Ruowei Jiang ,  Parham Aarabi

IPC: G06K9/46 ,  G06T11/00 ,  G06T7/11 ,  G06T7/90 ,  G06K9/00 ,  G06K9/62 ,  G06N3/08 ,  G06T1/20

Abstract: A system and method implement deep learning on a mobile device to provide a convolutional neural network (CNN) for real time processing of video, for example, to color hair. Images are processed using the CNN to define a respective hair matte of hair pixels. The respective object mattes may be used to determine which pixels to adjust when adjusting pixel values such as to change color, lighting, texture, etc. The CNN may comprise a (pre-trained) network for image classification adapted to produce the segmentation mask. The CNN may be trained for image segmentation (e.g. using coarse segmentation data) to minimize a mask-image gradient consistency loss. The CNN may further use skip connections between corresponding layers of an encoder stage and a decoder stage where shallower layers in the encoder, which contain high-res but weak features are combined with low resolution but powerful features from deeper decoder layers.