CN105827226A - Control switch performing identification through fingerprints - Google Patents

Abstract

The invention discloses a control switch performing identification through fingerprints. A control switch a fingerprint identification program driving the control switch to turn on and a secret key program are included, the fingerprint identification program includes a fingerprint identification module, a fingerprint image processing module, a transmission module, a fingerprint verification module and a control module that controls the control switch to turn on which are electrically connected in sequence, the secret key program is electrically connected with the control module, and the control module is prompted to turn on the control switch after a valid fingerprint image is input to the fingerprint verification module or a correct password is input to the secret key program; and the fingerprint image processing module includes a fingerprint information verification submodule, an image grayscale processing submodule, an image texture parameter calculation submodule, an image segmentation submodule and an image enhancement submodule. The control switch performing identification through fingerprints is safe and efficient, and is high in fingerprint identification efficiency and precision.

Description

Switched by the control of fingerprint recognition

Technical field

The present invention relates to field of switches, be specifically related to be switched by the control of fingerprint recognition.

Background technology

In correlation technique, the control switch safety rank being identified by fingerprint is higher, but to finger require the highest, dry finger, wet finger, shallow texture finger recognition effect poor, recognition efficiency and accuracy of identification are relatively low.

Summary of the invention

For the problems referred to above, the present invention is provided a kind of and is switched by the control of fingerprint recognition safely and efficiently.

The purpose of the present invention realizes by the following technical solutions:

Provide and switched by the control of fingerprint recognition, it includes controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation；

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image is resolved into non-overlapping copies, sub-block that size is, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

$G(m,n;\mathrm{\σ})=\frac{1}{2\mathrm{\π}\mathrm{\σ}}{e}^{-\frac{d^2(m,n)}{2{\mathrm{\σ}}^2}}$

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position.

Preferably, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, set threshold value T according to the parametric texture of the described sub-block belonging to finger-print region₁, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Further, the described switch that controls by fingerprint recognition also includes examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.

The invention have the benefit that

1, safe and efficient, arrange and can strengthen the fingerprint recognition program of fingerprint image, wherein fingerprint image gray scale is processed, the fingerprint image after process can wiping out background noise, and texture will not obscure in filtering, and contrast is strengthened；Using adaptive impovement type gaussian filtering equation to be smoothed the frequency fields of fingerprint image, the frequency fields obtained more can reflect fingerprint texture characteristic；Use comprehensive distinguishing method based on half-tone information that fingerprint image is split, overcome the problem relying on directional information split-run can not accurately obtain texture variations intense regions direction, it is possible to accurately rapid extraction belongs to the sub-block in actual fingerprint region；The parametric texture of the sub-block belonging to finger-print region in Gabor filter described in basis sets threshold value, the value of Gaussian envelope constant is selected by the difference of the field of direction of each sub-block belonging to finger-print region and two sub-blocks of left and right neighborhood and the comparison of threshold value, fingerprint image can be strengthened targetedly, improve efficiency and the precision of fingerprint recognition；

2, the setting of buzzer siren, improves the security performance controlling switch by fingerprint recognition；

3, the setting of cipher key procedures, can help by fingerprint recognition control switch user finger injuries or other promote finger obsolete in the case of by oneself arrange password open control switch.

Accompanying drawing explanation

The invention will be further described to utilize accompanying drawing, but the embodiment in accompanying drawing does not constitute any limitation of the invention, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to obtain other accompanying drawing according to the following drawings.

The connection diagram of Fig. 1 component of the present invention.

Detailed description of the invention

The invention will be further described with the following Examples.

Embodiment 1

See Fig. 1, the invention provides and switched by the control of fingerprint recognition, it includes controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation.

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image is resolved into non-overlapping copies, sub-block that size is, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

$G(m,n;\mathrm{\σ})=\frac{1}{2\mathrm{\π}\mathrm{\σ}}{e}^{-\frac{d^2(m,n)}{2{\mathrm{\σ}}^2}}$

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position；

Preferably, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, set threshold value T according to the parametric texture of the described sub-block belonging to finger-print region₁, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Further, the described switch that controls by fingerprint recognition also includes examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.

The present embodiment efficient by the control switch safety of fingerprint recognition, wherein, the setting of cipher key procedures, can help by fingerprint recognition control switch user finger injuries or other promote finger obsolete in the case of by oneself arrange password open control switch；The setting of buzzer siren, improves the security performance controlling switch by fingerprint recognition；Setting can strengthen the fingerprint recognition program of fingerprint image, wherein processes fingerprint image gray scale, the fingerprint image after process can wiping out background noise, and texture will not obscure in filtering, and contrast is strengthened；Using adaptive impovement type gaussian filtering equation to be smoothed the frequency fields of fingerprint image, the frequency fields obtained more can reflect fingerprint texture characteristic；Use comprehensive distinguishing method based on half-tone information that fingerprint image is split, overcome the problem relying on directional information split-run can not accurately obtain texture variations intense regions direction, it is possible to accurately rapid extraction belongs to the sub-block in actual fingerprint region；The parametric texture of the sub-block belonging to finger-print region in Gabor filter described in basis sets threshold value, the value of Gaussian envelope constant is selected by the difference of the field of direction of each sub-block belonging to finger-print region and two sub-blocks of left and right neighborhood and the comparison of threshold value, fingerprint image can be strengthened targetedly, the present embodiment sets threshold value T₁=10 °, the efficiency of fingerprint recognition improves 15%, and precision improves 20%.

Embodiment 2

See Fig. 1, the invention provides and switched by the control of fingerprint recognition, it includes controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation；

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image is resolved into non-overlapping copies, sub-block that size is, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

$G(m,n;\mathrm{\σ})=\frac{1}{2\mathrm{\π}\mathrm{\σ}}{e}^{-\frac{d^2(m,n)}{2{\mathrm{\σ}}^2}}$

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position.

Preferably, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, set threshold value T according to the parametric texture of the described sub-block belonging to finger-print region₁, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Further, the described switch that controls by fingerprint recognition also includes examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.

The present embodiment efficient by the control switch safety of fingerprint recognition, wherein, the setting of cipher key procedures, can help by fingerprint recognition control switch user finger injuries or other promote finger obsolete in the case of by oneself arrange password open control switch；The setting of buzzer siren, improves the security performance controlling switch by fingerprint recognition；Setting can strengthen the fingerprint recognition program of fingerprint image, wherein processes fingerprint image gray scale, the fingerprint image after process can wiping out background noise, and texture will not obscure in filtering, and contrast is strengthened；Using adaptive impovement type gaussian filtering equation to be smoothed the frequency fields of fingerprint image, the frequency fields obtained more can reflect fingerprint texture characteristic；Use comprehensive distinguishing method based on half-tone information that fingerprint image is split, overcome the problem relying on directional information split-run can not accurately obtain texture variations intense regions direction, it is possible to accurately rapid extraction belongs to the sub-block in actual fingerprint region；The parametric texture of the sub-block belonging to finger-print region in Gabor filter described in basis sets threshold value, the value of Gaussian envelope constant is selected by the difference of the field of direction of each sub-block belonging to finger-print region and two sub-blocks of left and right neighborhood and the comparison of threshold value, fingerprint image can be strengthened targetedly, the present embodiment sets threshold value T₁=20 °, the efficiency of fingerprint recognition improves 20%, and precision improves 25%.

Embodiment 3

See Fig. 1, the invention provides and switched by the control of fingerprint recognition, it includes controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation；

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image is resolved into non-overlapping copies, sub-block that size is, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

$G(m,n;\mathrm{\σ})=\frac{1}{2\mathrm{\π}\mathrm{\σ}}{e}^{-\frac{d^2(m,n)}{2{\mathrm{\σ}}^2}}$

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position.

Preferably, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, setting threshold value T1 according to the parametric texture of the described sub-block belonging to finger-print region, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Further, the described switch that controls by fingerprint recognition also includes examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.

The present embodiment efficient by the control switch safety of fingerprint recognition, wherein, the setting of cipher key procedures, can help by fingerprint recognition control switch user finger injuries or other promote finger obsolete in the case of by oneself arrange password open control switch；The setting of buzzer siren, improves the security performance controlling switch by fingerprint recognition；Setting can strengthen the fingerprint recognition program of fingerprint image, wherein processes fingerprint image gray scale, the fingerprint image after process can wiping out background noise, and texture will not obscure in filtering, and contrast is strengthened；Using adaptive impovement type gaussian filtering equation to be smoothed the frequency fields of fingerprint image, the frequency fields obtained more can reflect fingerprint texture characteristic；Use comprehensive distinguishing method based on half-tone information that fingerprint image is split, overcome the problem relying on directional information split-run can not accurately obtain texture variations intense regions direction, it is possible to accurately rapid extraction belongs to the sub-block in actual fingerprint region；The parametric texture of the sub-block belonging to finger-print region in Gabor filter described in basis sets threshold value, the value of Gaussian envelope constant is selected by the difference of the field of direction of each sub-block belonging to finger-print region and two sub-blocks of left and right neighborhood and the comparison of threshold value, fingerprint image can be strengthened targetedly, the present embodiment sets threshold value T₁=15 °, the efficiency of fingerprint recognition improves 18%, and precision improves 20%.

Embodiment 4

See Fig. 1, the invention provides and switched by the control of fingerprint recognition, it includes controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation；

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image is resolved into non-overlapping copies, sub-block that size is, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

$G(m,n;\mathrm{\σ})=\frac{1}{2\mathrm{\π}\mathrm{\σ}}{e}^{-\frac{d^2(m,n)}{2{\mathrm{\σ}}^2}}$

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position.

Preferably, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, set threshold value T according to the parametric texture of the described sub-block belonging to finger-print region₁, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Further, the described switch that controls by fingerprint recognition also includes examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.

The present embodiment efficient by the control switch safety of fingerprint recognition, wherein, the setting of cipher key procedures, can help by fingerprint recognition control switch user finger injuries or other promote finger obsolete in the case of by oneself arrange password open control switch；The setting of buzzer siren, improves the security performance controlling switch by fingerprint recognition；Setting can strengthen the fingerprint recognition program of fingerprint image, wherein processes fingerprint image gray scale, the fingerprint image after process can wiping out background noise, and texture will not obscure in filtering, and contrast is strengthened；Using adaptive impovement type gaussian filtering equation to be smoothed the frequency fields of fingerprint image, the frequency fields obtained more can reflect fingerprint texture characteristic；Use comprehensive distinguishing method based on half-tone information that fingerprint image is split, overcome the problem relying on directional information split-run can not accurately obtain texture variations intense regions direction, it is possible to accurately rapid extraction belongs to the sub-block in actual fingerprint region；The parametric texture of the sub-block belonging to finger-print region in Gabor filter described in basis sets threshold value, the value of Gaussian envelope constant is selected by the difference of the field of direction of each sub-block belonging to finger-print region and two sub-blocks of left and right neighborhood and the comparison of threshold value, fingerprint image can be strengthened targetedly, the present embodiment sets threshold value T₁=18 °, the efficiency of fingerprint recognition improves 20%, and precision improves 18%.

Embodiment 5

See Fig. 1, the invention provides and switched by the control of fingerprint recognition, it includes controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation；

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image is resolved into non-overlapping copies, sub-block that size is, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

$G(m,n;\mathrm{\σ})=\frac{1}{2\mathrm{\π}\mathrm{\σ}}{e}^{-\frac{d^2(m,n)}{2{\mathrm{\σ}}^2}}$

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position.

Preferably, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, set threshold value T according to the parametric texture of the described sub-block belonging to finger-print region₁, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Further, the described switch that controls by fingerprint recognition also includes examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.

The present embodiment efficient by the control switch safety of fingerprint recognition, wherein, the setting of cipher key procedures, can help by fingerprint recognition control switch user finger injuries or other promote finger obsolete in the case of by oneself arrange password open control switch；The setting of buzzer siren, improves the security performance controlling switch by fingerprint recognition；Setting can strengthen the fingerprint recognition program of fingerprint image, wherein processes fingerprint image gray scale, the fingerprint image after process can wiping out background noise, and texture will not obscure in filtering, and contrast is strengthened；Using adaptive impovement type gaussian filtering equation to be smoothed the frequency fields of fingerprint image, the frequency fields obtained more can reflect fingerprint texture characteristic；Use comprehensive distinguishing method based on half-tone information that fingerprint image is split, overcome the problem relying on directional information split-run can not accurately obtain texture variations intense regions direction, it is possible to accurately rapid extraction belongs to the sub-block in actual fingerprint region；The parametric texture of the sub-block belonging to finger-print region in Gabor filter described in basis sets threshold value, the value of Gaussian envelope constant is selected by the difference of the field of direction of each sub-block belonging to finger-print region and two sub-blocks of left and right neighborhood and the comparison of threshold value, fingerprint image can be strengthened targetedly, the present embodiment sets threshold value T₁=12 °, the efficiency of fingerprint recognition improves 10%, and precision improves 18%.

Finally should be noted that; above example is only in order to illustrate technical scheme; rather than limiting the scope of the invention; although having made to explain to the present invention with reference to preferred embodiment; it will be understood by those within the art that; technical scheme can be modified or equivalent, without deviating from the spirit and scope of technical solution of the present invention.

Claims (3)

1. switched by the control of fingerprint recognition, it is characterized in that, including controlling switch, the fingerprint recognition program driving control switch to open and cipher key procedures, described fingerprint recognition program includes that the fingerprint identification module, fingerprint image processing module, transport module, fingerprint authentication module and the control that are sequentially connected electrically control the control module that switch cuts out, described cipher key procedures electrically connects with control module, and described fingerprint authentication module promotes control module to open control switch at the effective fingerprint image of input or cipher key procedures after input proper password；Described fingerprint image processing module includes:

(1) finger print information examines submodule, its temperature gathering detected tissue and pulse data, and the data gathered by analysis judge that the fingerprint image transmitted by fingerprint identification module is the most effective, if the temperature of the detected tissue that continuous more than 2 times gather and pulse data are all in preset range, then judge that the fingerprint image of fingerprint identification module transmission is effective；

(2) gradation of image processes submodule, for effective fingerprint image is carried out gray proces, with pixel (x during process, y) centered by, calculate gray average M, intermediate value Z in 3 × 3 neighborhoods, due to the described effective fingerprint image obtained and and its fingerprint image verified between in approximately the same plane can slightly deviation, set fingerprint image correction factorThe computing formula of gray average M is:

Grey scale pixel value after process is:

I (x, y) >=M time, I'(x, y)=M+Z/2

I (x, y) during ＜ M, I'(x, y)=M-Z/2

Wherein, I (x, y) be fingerprint image pixel (x, y) original gray value at place, I'(x, y) be fingerprint image after gray proces pixel (x, y) gray value at place,For described effective fingerprint image and and each pixel point value of its fingerprint image verified between standard deviation；

(3) image texture parameter computation module, it uses the field of direction of fingerprint image that gray proces crossed by adaptive impovement type gaussian filtering equation to be smoothed, during process, fingerprint image resolves into non-overlapping copies, size is the sub-block of 8 × 8, the coordinate of each central point of sub-block is (m, n), described adaptive impovement type gaussian filtering equation is:

Wherein, (m is n) that (m, n) to the distance of frequency plane initial point from central point to d；σ is filtering factor, represents the smoothness of Gaussian function, and the position that fingerprint ridge line and the valley line in sub-block more smooths arranges σ=0.6, arranges σ=5 in the fingerprint ridge line of sub-block and valley line fracture and fuzzy position.

Control switch by fingerprint recognition the most according to claim 1, is characterized in that, described fingerprint image processing module also includes:

(1) image segmentation submodule, the sub-block in actual fingerprint region is belonged to for rapid extraction in each sub-block, during extraction, by each sub-block (k after gradation of image processes, l) gray average M (k, l) and variance D (k, l) with the gray average M of all pixels of fingerprint image₀With variance D₀Compare, if M is (k, l) > M₀And D (k, l) > D₀, then this sub-block belongs to the sub-block in actual fingerprint region；

(2) image enhaucament submodule, it uses Gabor filter that the sub-block belonging to actual fingerprint region is carried out image enhancement processing, arranges δ_xWith δ_yIt is respectively the Gaussian envelope constant in x-axis and y-axis direction in the function of Gabor filter, calculates each sub-block belonging to finger-print region and difference c of the field of direction of two sub-blocks of left and right neighborhood₀, c₁, set threshold value T according to the parametric texture of the described sub-block belonging to finger-print region₁, the span of described threshold value T1 is 10 °～20 °, Gaussian envelope constant δ_xWith δ_yValue be:

c₀＜ T₁And c₁＜ T₁Time, δ_x=4, δ_y=4；

c₀＞ T₂And c₁＞ T₂Time, δ_x=5, δ_y=5；

Other situations, δ_x=4.5, δ_y=4.5.

Control switch by fingerprint recognition the most according to claim 1, it is characterized in that, also include examining the buzzer siren that submodule electrically connects with finger print information, described buzzer siren is positioned at control switch, if finger print information examines the temperature of detected tissue that in submodule, continuous more than 2 times gather and pulse data is all not in preset range, described buzzer siren is reported to the police.