Processing method for image tensor data

Patent metadata

Field	Value
Publication number	US-11449965-B2
Application number	US-202016735722-A
Country	US
Kind code	B2
Filing date	Jan 7, 2020
Priority date	Jan 17, 2019
Publication date	Sep 20, 2022
Grant date	Sep 20, 2022

Abstract

A processing method for image tensor data, which can greatly reduce the number of free parameters in the model, limit the weight layer flexibly, and can be applied to any order of image tensor data. In this processing method for image tensor data, TTRBM model of Restricted Boltzmann machine with tensor train format is introduced. The input and output data of this method are both represented by tensors, and the weight of the middle layer is also represented by tensors, and the restricted weight has the structure of tensor train. The number of free parameters in the middle layer is controlled by adjusting the rank of tensor train decomposition. The rank of TT decomposition is adjusted, and different feature representations with the same size are expressed.

First claim

What is claimed is:

1. A processing method for image tensor data, comprising the steps:
introducing a TTRBM model of Restricted Boltzmann machine with a tensor train format, TTRBM is Restricted Boltzmann Machine of Tensor Train; representing input and output data of the processing method by a plurality of tensors; and representing a weight of a middle layer by the plurality of tensors, wherein
a restricted weight has a structure of the tensor train; a number of free parameters in a middle layer is controlled by adjusting a rank of a tensor train (TT) decomposition; a rank of TT decomposition is adjusted; and different feature representations with a same size are expressed;
an energy function for the TTRBM model is formula (1):

E
⁡

(

𝒳
,

𝒴
;
Θ

)

=

-

〈

𝒳
,
𝔅

〉

-

〈

𝒴
,
C

〉

-

∑

i
1

,

⁢
…
⁢

,

i
D

j
1

,

⁢
…
⁢

,

j
D

⁢

𝒳
⁡

(

i
1

,
…
⁢

,

i
D

)

⁢

𝒴
⁡

(

j
1

,
…
⁢

,

j
D

)

⁢

G
1

⁡

[

i
1

,

j
1

]

⁢

⁢
…
⁢

⁢

G
D

⁡

[

i
D

,

j
D

]

,

(
1
)

Assignees

• Univ Beijing Technology

Inventors

• Sun Yanfeng
• Ju Fujiao

Classifications

• G06V40/169

  Holistic features and representations, i.e. based on the facial image taken as a whole · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/50

  by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis · CPC title

• G06V10/40

  Extraction of image or video features · CPC title

• G06T3/4046 Primary

  using neural networks · CPC title