1. A method for identifying a person using their finger-joint print including the outer skin around the proximal interphalangeal joint of a finger, the method comprising:
capturing an image of the finger-joint print of the person;
extracting a region of interest (ROI) image IROI based on a local convexity property of the finger-joint print;
extracting features representing the orientation of the lines in a finger-joint print image from the ROI image IROI using an extended Gabor phase coding scheme and the extracted features are represented in competitive code maps;
wherein angular distance between the competitive code maps is compared with a reference set in a database to identify the person.
2. The method according to claim 1, further comprising the initial step of placing the finger onto a triangular block.
3. The method according to claim 1, further comprising defining a ROI coordinate system to extract the ROI image IROI by:
cropping a coarse sub-image Icoarse from the captured image;
obtaining a corresponding edge image Iedge from the coarse sub-image Icoarse using a canny edge detector;
coding the corresponding edge image Iedge based on a local convexity property to obtain a convexity coding image Icc, such that each pixel on the corresponding edge image Iedge is assigned a code to represent the local convexity of this pixel;
obtaining a line X=x0 to best classify \u201c\u22121\u201d and \u201c1\u201d pixels on the convexity image Icc; and
taking the line X=x0 as the Y-axis of the ROI coordinate system and the line
y
=
height
\ue89e
\ue89e
of
\ue89e
\ue89e
I
coarse
2
as the X-axis.
4. The method according to claim 3, wherein the formula to obtain x0 is:
x
0
=
arg
x
\ue89e
\ue89e
min
\ue8a0
(
num
\ue89e
\ue89e
of
\ue89e
\ue89e
”
\ue89e
1
\ue89e
”
\ue89e
\ue89e
pixels
\ue89e
\ue89e
on
\ue89e
\ue89e
the
\ue89e
\ue89e
right
\ue89e
\ue89e
of
\ue89e
\ue89e
X
=
x
num
\ue89e
\ue89e
of
\ue89e
\ue89e
”
\ue89e
1
\ue89e
”
\ue89e
\ue89e
pixels
+
num
\ue89e
\ue89e
of
\ue89e
\ue89e
”
–
1
\ue89e
”
\ue89e
\ue89e
pixels
\ue89e
\ue89e
on
\ue89e
\ue89e
the
\ue89e
\ue89e
left
\ue89e
\ue89e
of
\ue89e
\ue89e
X
=
x
num
\ue89e
\ue89e
of
\ue89e
\ue89e
”
–
1
\ue89e
”
\ue89e
\ue89e
pixels
)
5. The method according to claim 1, wherein a real part GR of a neurophysiology-based Gabor filter is applied to the ROI image IROI to extract the orientation information of the ROI image IROI.
6. The method according to claim 5, wherein the orientation information is represented in a competitive code map defined by:
compCode
\ue8a0
(
x
,
y
)
=
arg
j
\ue89e
max
\ue89e
{
abs
(
I
ROI
\ue8a0
(
x
,
y
)
*
G
R
\ue8a0
(
x
,
y
,
\u03c9
,
\u03b8
j
)
)
}
,
j
=
{
0
,
\u2026
\ue89e
,
5
}
where * represents the convolution operation and GR represents the real part of neurophysiology-based Gabor function G.
7. The method according to claim 1, wherein the angular distance D(P,Q) is defined by the following equation:
D
\ue8a0
(
P
,
Q
)
=
\u2211
y
=
0
Rows
\ue89e
\u2211
x
=
0
Cols
\ue89e
(
P
M
\ue8a0
(
x
,
y
)
\u22c2
Q
M
\ue8a0
(
x
,
y
)
)
\xd7
G
\ue8a0
(
P
\ue8a0
(
x
,
y
)
,
Q
\ue8a0
(
x
,
y
)
)
3
\ue89e
\u2211
y
=
0
Rows
\ue89e
\u2211
x
=
0
Cols
\ue89e
P
M
\ue8a0
(
x
,
y
)
\u22c2
Q
M
\ue8a0
(
x
,
y
)
where
G
\ue8a0
(
P
\ue8a0
(
x
,
y
)
,
Q
\ue8a0
(
x
,
y
)
)
=
{
1
,
P
\ue8a0
(
x
,
y
)
=
6
\ue89e
\ue89e
and
\ue89e
\ue89e
Q
\ue8a0
(
x
,
y
)
\u2260
6
1
,
P
\ue8a0
(
x
,
y
)
\u2260
6
\ue89e
\ue89e
and
\ue89e
\ue89e
Q
\ue8a0
(
x
,
y
)
=
6
0
,
P
\ue8a0
(
x
,
y
)
=
Q
\ue8a0
(
x
,
y
)
min
\ue8a0
(
P
\ue8a0
(
x
,
y
)
–
Q
\ue8a0
(
x
,
y
)
,
Q
\ue8a0
(
x
,
y
)
–
(
P
\ue8a0
(
x
,
y
)
–
6
)
)
,
if
\ue89e
\ue89e
P
\ue8a0
(
x
,
y
)
>
Q
\ue8a0
(
x
,
y
)
\ue89e
\ue89e
and
\ue89e
\ue89e
P
(
x
,
y
)
\u2260
6
min
\ue8a0
(
Q
\ue8a0
(
x
,
y
)
–
P
\ue8a0
(
x
,
y
)
,
P
\ue8a0
(
x
,
y
)
–
(
Q
\ue8a0
(
x
,
y
)
–
6
)
)
,
if
\ue89e
\ue89e
P
\ue8a0
(
x
,
y
)
<
Q
\ue8a0
(
x
,
y
)
\ue89e
\ue89e
and
\ue89e
\ue89e
Q
(
x
,
y
)
\u2260
6
\ue89e
\ue89e
and
\u22c2
\ue89e
denotes
\ue89e
\ue89e
an
\ue89e
\ue89e
AND
\ue89e
\ue89e
operator
.
8. The method according to claim 1, wherein an A* path-finding searching algorithm is used to provide an approximate optimal solution to match the extracted features stored as competitive code maps.
9. A system for identifying a person using their finger-joint print including the outer skin around the proximal interphalangeal joint of a finger, the method comprising:
an image capture device to capture an image of the finger-joint print of the person;
a first extraction module to extract a region of interest (ROI) image IROI based on a local convexity property of the finger-joint print;
a second extraction module to extract features representing the orientation of the lines in a finger-joint print image from the ROI image IROI using an extended Gabor phase coding scheme and the extracted features are represented in competitive code maps;
wherein angular distance between the competitive code maps is compared with a reference set in a database to identify the person.
10. The system according to claim 9, further comprising a triangular block for placement of the finger.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A multi-spectral scanning microscope for imaging an object, comprising:
a plurality of discrete microscope objectives arranged in rows in a microscope array, said objectives being configured to image respective sections of the object during a scan of the object;
a scanning mechanism for producing said scan as a result of a relative movement between the microscope array and the object, wherein the scan is implemented along a linear direction of scan across the object and said rows of objectives are staggered with respect to the direction of scan, such that during the scan each of the objectives acquires image data corresponding to a respective continuous strip of the object along the direction of scan;
a detector optically coupled to the microscope array for capturing image data representative of respective images of said sections of the object imaged by said plurality of objectives;
a light source adapted to illuminate the object at multiple distinct wavelengths;
a mechanism for placing the object and the detector at respective distances from the microscope array so as to maintain a substantially constant magnification at each of said distinct wavelengths; and
a system for combining said image data captured by the detector during a sequence of scans of the scanning mechanism carried out at said multiple distinct wavelengths.
2. The scanning microscope of claim 1, wherein said light source includes light emitting diodes operating at each of said distinct wavelengths.
3. The scanning microscope of claim 1, wherein said light source includes a multi-sided drum with a corresponding plurality of sites, each site being capable of emitting one of said distinct wavelengths, and the light source further includes a mechanism for rotating the drum to selectively illuminate the object with any one of said distinct wavelengths.
4. The scanning microscope system of claim 3, wherein said light source includes light emitting diodes operating at each of said distinct wavelengths.
5. The scanning microscope of claim 1, wherein said light source includes a platter with a plurality of sites, each site being capable of emitting one of said distinct wavelengths, and the light source further includes a mechanism for rotating the platter to selectively illuminate the object with any one of said distinct wavelengths.
6. The scanning microscope of claim 5, wherein said light source includes light emitting diodes operating at each of said distinct wavelengths.
7. The scanning microscope of claim 1, wherein said mechanism is adapted for placing the object and the detector at distinct conjugate distances from the microscope array corresponding to said distinct wavelengths.
8. The scanning microscope of claim 1, wherein said system for combining the image data captured by the detector during a sequence of scans at multiple distinct wavelengths includes a vector of weighting factors associated with each pixel of the detector.
9. The scanning microscope of claim 1, wherein said light source includes a platter with a plurality of sites, each site being capable of emitting one of said distinct wavelengths, and the light source further includes a mechanism for rotating the platter to selectively illuminate the object with any one of said distinct wavelengths; said light source includes light emitting diodes operating at each of said distinct wavelengths;
said mechanism is adapted for placing the object and the detector at distinct conjugate distances from the microscope array corresponding to said distinct wavelengths; and said system for combining the image data captured by the detector during a sequence of scans at multiple distinct wavelengths includes a vector of weighting factors associated with each pixel of the detector.
10. A method for multi-spectral imaging of an object, comprising the steps of:
providing a plurality of discrete microscope objectives arranged in rows in a microscope array, said objectives being configured to image respective sections of the object during a scan of the object;
providing a scanning mechanism for producing said scan as a result of a relative movement between the microscope array and the object, wherein the scan is implemented along a linear direction of scan across the object and said rows of objectives are staggered with respect to the direction of scan, such that during the scan each of the objectives acquires image data corresponding to a respective continuous strip of the object along the direction of scan;
providing a pixel detector optically coupled to the microscope array for capturing image data representative of respective images of said sections of the object imaged by said plurality of objectives;
providing a light source adapted to illuminate the object at multiple distinct wavelengths;
providing a mechanism for placing the object and the detector at respective distances from the microscope array so as to maintain a substantially constant magnification at each of said distinct wavelengths;
scanning the object sequentially, using each of said distinct wavelengths, after having placed the object and the detector at said respective distances; and
combining image data captured by the detector during said sequential scanning step to provide a composite spectral image of the object.
11. The method of claim 10, further including the step of preceding the sequential scanning step with a scan using an auto-focus mechanism to produce a best-focus map for said microscope objectives at each acquisition position along said scan of the object, and further the step of applying the best-focus map to the microscope array during the sequential scanning step.
12. The method of claim 10, wherein said respective distances from the microscope array to maintain a substantially constant magnification at each of said distinct wavelengths mechanism are conjugate distances from the microscope array corresponding to the distinct wavelengths.
13. The method of claim 10, wherein said light source includes light emitting diodes operating at each of said distinct wavelengths.
14. The method of claim 10, wherein said light source includes a multi-sided drum with a corresponding plurality of sites, each site capable of emitting one of said distinct wavelengths, and the light source further includes a mechanism for rotating the drum to selectively illuminate the object with said distinct wavelengths during said sequential scanning step of the object.
15. The method of claim 14, wherein said light source includes light emitting diodes operating at each of said distinct wavelengths.
16. The method of claim 10, wherein said light source includes a platter with a plurality of sites, each site capable of emitting one of said distinct wavelengths, and the light source further includes a mechanism for rotating the platter to selectively illuminate the object with said distinct wavelengths during said sequential scanning step of the object.
17. The method of claim 16, wherein said light source includes light emitting diodes operating at each of said distinct wavelengths.
18. The method of claim 10, wherein said step of combining the image data captured by the detector during a sequence of scans at multiple distinct wavelengths includes applying a vector of weighting factors.
19. The method of claim 10, further including the following steps:
preceding the sequential scanning step with a scan using an auto-focus mechanism to produce a best-focus map for said microscope objectives at each acquisition position along said scan of the object; and
applying the best-focus map to the microscope array during the sequential scanning step;
wherein said respective distances from the microscope array to maintain a substantially constant magnification at each of said distinct wavelengths mechanism are conjugate distances from the microscope array corresponding to the distinct wavelengths; said light source includes a platter with a plurality of sites, each site capable of emitting one of said distinct wavelengths, and the light source further includes a mechanism for rotating the platter to selectively illuminate the object with said distinct wavelengths during said sequential scanning step of the object; said light source includes light emitting diodes operating at each of said distinct wavelengths; and said step of combining the image data captured by the detector during a sequence of scans at multiple distinct wavelengths includes applying a vector of weighting factors.