公开(公告)号：US10685428B2

公开(公告)日：2020-06-16

申请号：US16185860

申请日：2018-11-09

Applicant: Hong Kong Applied Science and Technology Research Institute Co., Ltd.

Inventor： Yan Wang ,  Hailiang Li ,  Yang Liu ,  Man Yau Chiu ,  Zhi Bin Lei

IPC: G06K9/36 ,  G06T3/40 ,  G06K9/00 ,  G06T5/50 ,  G06T7/73

Abstract: Methods and systems which provide super-resolution synthesis based on weighted results from a random forest classifier are described. Embodiments apply a trained random forest classifier to low-resolution patches generated from the low-resolution input image to classify the low-resolution input patches. As each low-resolution patch is fed into the random forest classifier, each decision tree in the random forest classifier “votes” for a particular class for each of the low-resolution patches. Each class is associated with a projection matrix. The projection matrices output by the decision trees are combined by a weighted average to calculate an overall projection matrix corresponding to the random forest classifier output, which is used to calculate a high-resolution patch for each low-resolution patch. The high-resolution patches are combined to generate a synthesized high-resolution image corresponding to the low-resolution input image.

公开(公告)号：US20200151852A1

公开(公告)日：2020-05-14

申请号：US16185860

申请日：2018-11-09

Applicant: Hong Kong Applied Science and Technology Research Institute Co., Ltd.

Inventor： Yan Wang ,  Hailiang Li ,  Yang Liu ,  Man Yau Chiu ,  Zhi Bin Lei

IPC: G06T3/40 ,  G06K9/00 ,  G06T7/73 ,  G06T5/50

Abstract: Methods and systems which provide super-resolution synthesis based on weighted results from a random forest classifier are described, Embodiments apply a trained random forest classifier to low resolution patches generated from the low-resolution input image to classify the low resolution input patches. As each low-resolution patch is fed into the random forest classifier, each decision tree in the random forest classifier “votes” for a particular class for each of the low-resolution patches. Each class is associated with a projection matrix. The projection matrices output by the decision trees are combined by a weighted average to calculate an overall projection matrix corresponding to the random forest classifier output, which is used to calculate a high-resolution patch for each low-resolution patch. The high-resolution patches are combined to generate a synthesized high-resolution image corresponding to the low-resolution input image.