Image recognition system, image recognition server, and image recognition
View Patent ↗An object of the present invention is to provide an image recognition system, an image recognition server, and an image recognition method having a new high security framework that can achieve utilization of multi-device diversity. The image recognition system according to the present disclosure includes a computationally non-intensive encryption algorithm based on random unitary transformation and achieves a high level of security. In addition, the image recognition system achieves high recognition performance by using ensemble learning to integrate recognition results based on the dictionaries of different devices.
1. An image recognition system, comprising N terminals (N is an integer not less than 2), M transfer servers (M is an integer not less than 1), and an image recognition server, wherein each of the N terminals, M transfer servers and the image recognition server are implemented by a processor and a memory having computer program instructions stored thereon and executed by the processor,
wherein when an image y i j is expressed, by using a dictionary matrix D i i being an M×K matrix having, as elements of the M×K matrix, K (K>M) bases, and a sparse coefficient X i j being a K-dimensional vector, as y i j =D i i ·X i j , where i is a class to which an image to be identified belongs, and j and k (k∈j) are numbers of the terminals,
the terminals are configured to encrypt a testing image using a random unitary matrix Qp generated by using a key p, to generate an encrypted testing image, and transfer the encrypted testing image to a specified one of the transfer servers,
the transfer servers are configured to downsample the encrypted testing image, transform the downsampled and encrypted testing image to a one-dimensional encrypted image vector, and transfer the encrypted image vector to the image recognition server, and
the image recognition server is configured to use a plurality of encrypted dictionaries generated by encrypting, by using the random unitary matrix Op, a plurality of dictionaries generated using different training images, to solve, by Orthogonal Matching Pursuit, an optimization problem represented by Math. C1 for each of the plurality of encrypted dictionaries, to estimate a class, to which the encrypted image vector belongs, for each of the plurality of the encrypted dictionaries, and is further configured to perform ensemble learning on the class estimated for each of the plurality of the encrypted dictionaries to determine a single class to which the encrypted image vector belongs:
[
Math
.
C1
]
X
~
(
j
,
k
)
=
arg
min
X
j
D
_
j
X
j
-
y
_
k
2
s
.
t
.
X
j
0
≤
∈
(
C1
)
where, D j is the encrypted dictionary of a terminal of number j, X j is a sparse coefficient of the terminal of number j, and y k is the encrypted image vector generated by downsampling the encrypted testing image from the terminal of number k (k∈j) and transforming the encrypted testing image to a one-dimensional vector.
2. An image recognition server, comprising:
a processor; and
a memory having computer program instructions stored thereon, when executed by the processor, perform to:
receive an encrypted image vector and a plurality of encrypted dictionaries, the encrypted image vector being generated by downsampling an encrypted testing image and transforming the downsampled and encrypted testing image to a one-dimensional vector, the encrypted testing image being generated by encrypting a testing image using a random unitary matrix Qp generated by using a key p, the plurality of encrypted dictionaries being generated by encrypting, by using the random unitary matrix Qp, a plurality of dictionaries generated using different training images; and
solve, by Orthogonal Matching Pursuit, an optimization problem represented by Math. C1 for each of the plurality of encrypted dictionaries, to estimate a class, to which the encrypted image vector belongs, for each of the plurality of the encrypted dictionaries, and further configured to perform ensemble learning on the class estimated for each of the plurality of the encrypted dictionaries to determine a single class to which the encrypted image vector belongs:
[
Math
.
C1
]
X
~
(
j
,
k
)
=
arg
min
X
j
D
_
j
X
j
-
y
_
k
2
s
.
t
.
X
j
0
≤
∈
(
C1
)
where, D j is the encrypted dictionary of a terminal of number j, X j is a sparse coefficient of the terminal of number j, and y k is the encrypted image vector generated by downsampling the encrypted testing image from the terminal of number k (k∈j) and transforming the encrypted testing image to a one-dimensional vector;
where the terminals are configured to encrypt a testing image using a random unitary matrix Qp generated by using a key p, to generate an encrypted testing image, and transfer the encrypted testing image to a specified one of the transfer servers.
3. An image recognition method performed in an image recognition system including N terminals (N is an integer not less than 2), M transfer servers (M is an integer not less than 1), and an image recognition server, the method comprising:
when an image yl is expressed, by using a dictionary matrix D i j being an M×K matrix having, as elements of the M×K matrix, K (K>M) bases, and a sparse coefficient X i j being a K-dimensional vector, as y i j =D i j ·X i j , where i is a class to which an image to be identified belongs, and j and k (k∈j) are numbers of the terminals,
encrypting, by the terminals, a testing image using a random unitary matrix Qp generated by using a key p, to generate an encrypted testing image, and transferring the encrypted testing image to a specified one of the transfer servers;
downsampling, by the transfer servers, the encrypted testing image, transforming the downsampled and encrypted testing image to a one-dimensional encrypted image vector, and transferring the encrypted image vector to the image recognition server; and
using, by the image recognition server, a plurality of encrypted dictionaries generated by encrypting, by using the random unitary matrix Qp, a plurality of dictionaries generated using different training images, to solve, by Orthogonal Matching Pursuit, an optimization problem represented by Math. C1 for each of the plurality of encrypted dictionaries, to estimate a class, to which the encrypted image vector belongs, for each of the plurality of the encrypted dictionaries, and performing ensemble learning on the class estimated for each of the plurality of the encrypted dictionaries to determine a single class to which the encrypted image vector belongs:
[
Math
.
C1
]
X
~
(
j
,
k
)
=
arg
min
X
j
D
_
j
X
j
-
y
_
k
2
s
.
t
.
X
j
0
≤
∈
(
C1
)
where, D j is the encrypted dictionary of a terminal of number j, X j is a sparse coefficient of the terminal of number j, and y k is the encrypted image vector generated by downsampling the encrypted testing image from the terminal of number k (k∈j) and transforming the encrypted testing image to a one-dimensional vector.