CN107657444A - A kind of POS quick payment system based on fingerprint recognition - Google Patents
A kind of POS quick payment system based on fingerprint recognition Download PDFInfo
- Publication number
- CN107657444A CN107657444A CN201710900890.5A CN201710900890A CN107657444A CN 107657444 A CN107657444 A CN 107657444A CN 201710900890 A CN201710900890 A CN 201710900890A CN 107657444 A CN107657444 A CN 107657444A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- fingerprint information
- fingerprint
- msup
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 claims description 58
- 238000009499 grossing Methods 0.000 claims description 20
- 230000009466 transformation Effects 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 230000001131 transforming effect Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 210000002569 neuron Anatomy 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000002238 attenuated effect Effects 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/20—Point-of-sale [POS] network systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4014—Identity check for transactions
- G06Q20/40145—Biometric identity checks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G07G1/00—Cash registers
- G07G1/12—Cash registers electronically operated
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention provides one kind and is based on fingerprint recognition POS quick payment system, the system includes POS and finger print information storage server, the POS and finger print information storage server pass through network connection, when fingerprint is paid, finger print information is sent to finger print information storage server by POS, finger print information storage server recalls feeds back to POS with the bank card information of this fingerprint binding, holder selected in POS needed for the bank card that uses, subsequent treatment is identical with the pattern for POS of commonly swiping the card.The present invention had both improved the convenience of payment, also increased the security of payment, it is thus also avoided that lose the situation for the bank card carried with.
Description
Technical Field
The invention relates to a POS machine, in particular to a rapid payment system of the POS machine based on fingerprint identification.
Background
Compared with cash payment, the non-cash payment has the advantages of safety, rapidness, reliability and the like. A POS machine, which is a payment terminal widely used in cashless payment, is installed in a special merchant and an acceptance site of a bank card to be networked with a computer, thereby realizing automatic electronic fund transfer.
The existing POS machine reads magnetic stripe information of a card holder of a bank card through a card reader, an operator of the POS machine inputs transaction amount, the card holder inputs personal identification information (namely a password), and the POS machine sends the information to a card sending bank system through a UnionPay center to finish online transaction. This requires the cardholder to carry the bank card to be used, and once the cardholder does not carry the bank card, the bank card cannot be used, which causes inconvenience.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a POS machine fast payment system based on fingerprint identification.
The purpose of the invention is realized by adopting the following technical scheme:
a POS machine fast payment system based on fingerprint identification is characterized by comprising a POS machine and a fingerprint information storage server; the fingerprint POS machine is connected with the fingerprint information storage server through a network;
the POS machine is provided with a fingerprint acquisition device and a fingerprint processing device, and the fingerprint acquisition device is used for acquiring fingerprint information of a payer; the fingerprint processing device is used for processing fingerprint information and transmitting the obtained fingerprint texture characteristics to the fingerprint information storage server;
the fingerprint information storage server is used for identifying the identity of the payer according to the received fingerprint texture characteristics, calling bank card information bound with the payer in advance according to the identity of the payer, feeding the bank card information back to the POS machine, and the payer selects a bank card to be used from the fed back bank card information and inputs payment amount and a password for payment. The subsequent processing is the same as the existing payment mode.
The invention has the beneficial effects that: (1) the convenience of payment is improved, so that the card can still pay by replacing the bank card with the fingerprint under the condition that the card holder does not carry the bank card, and the convenience of payment of the card holder is improved; (2) the loss of the bank card is avoided, and the bank card carried by a card holder cannot be lost due to careless custody because the consumption of the bank card is not required to be carried; (3) the security of payment is increased, and the fingerprint payment system can confirm the identity of the payer, and the danger that the bank card is stolen and swiped by people is avoided.
Drawings
FIG. 1 is a block diagram of the framework of the present invention;
FIG. 2 is a block diagram of the fingerprint acquisition device and the fingerprint processing device of the POS machine of the present invention.
Reference numerals:
a POS machine 1; a fingerprint information storage server 2; a fingerprint acquisition device 3; a fingerprint processing device 4; a smoothing unit 41; an enhancement processing unit 42; a texture extraction unit 43.
Detailed Description
The invention is further described in connection with the following application scenarios.
Referring to fig. 1-2, a POS machine fast payment system based on fingerprint identification is characterized by comprising a POS machine 1 and a fingerprint information storage server 2; the POS machine 1 is connected with the fingerprint information storage server 2 through a network;
the POS machine comprises a display screen, a keyboard and a card swiping slot; the POS machine 1 is also provided with a fingerprint acquisition device 3 and a fingerprint processing device 4, and the fingerprint acquisition device 3 is used for acquiring fingerprint information of a payer; the fingerprint processing device 4 is used for processing fingerprint information and transmitting the obtained fingerprint texture characteristics to the fingerprint information storage server 2;
the fingerprint information storage server 2 is used for identifying the identity of the payer according to the received fingerprint texture characteristics, calling bank card information bound with the payer in advance according to the identity of the payer, feeding the bank card information back to the POS machine 1, and the payer selects a bank card to be used from the fed back bank card information and inputs payment amount and a password for payment. The subsequent processing is the same as the existing payment mode.
The fingerprint processing device 4 comprises a smoothing processing unit 41, an enhancement processing unit 42 and a texture extraction unit 43; the smoothing unit 41 is configured to denoise the acquired fingerprint information; the enhancement processing unit 42 is configured to perform enhancement processing on the de-noised fingerprint information; the texture extraction unit 43 is configured to extract fingerprint texture features after enhancement processing.
The embodiment of the invention improves the convenience of payment, ensures that the card holder can still pay by replacing the bank card with the fingerprint under the condition that the card holder does not carry the bank card, and improves the convenience of payment of the card holder; the loss of the bank card is avoided, and the bank card carried by a card holder cannot be lost due to careless custody because the consumption of the bank card is not required to be carried; the security of payment is increased, and the fingerprint payment system can confirm the identity of the payer, and the danger that the bank card is stolen and swiped by people is avoided.
Preferably, the smoothing unit 41 is configured to perform a segmentation operation on the acquired fingerprint information, select a region with a size of 256 × 256 and containing rich fingerprint texture information, that is, an ROI region, perform smoothing on the ROI region, remove random noise in the ROI region, and obtain the fingerprint information S after the smoothing process1The method specifically comprises the following steps:
1) according to the acquired fingerprint information, carrying out segmentation operation on the fingerprint information, and selecting a region which is 256 multiplied by 256 and contains abundant fingerprint texture information, namely an ROI (region of interest);
2) processing the ROI area by adopting a Fourier transform algorithm, transforming the ROI area from a space domain into a frequency domain, smoothing the ROI area in the frequency domain by using an attenuation function D (a, b), performing inverse Fourier transform on the ROI area after smoothing, transforming the ROI area after smoothing from the frequency domain into the space domain to obtain fingerprint information S after smoothing1(ii) a The attenuation function D (a, b) is expressed as:
wherein, let (m, n) be the coordinates of pixel points in ROI region, (a, b) be the coordinates of corresponding pixel points in ROI region located in frequency domain, D (a, b) be attenuation function value, F0Is the cut-off frequency, κ is the attenuation factor, and is a positive integer greater than zero;
the high-frequency components of the ROI area located in the frequency domain are attenuated stepwise with an attenuation function D (a, b) so as to be higher than F0Is attenuated for high frequency components below F0All frequencies of (a) pass;
3) transforming the smoothed ROI region from the frequency domain to the space domain by inverse Fourier transform to obtain smoothed fingerprint information S1。
Has the advantages that: the ROI is transformed from a space domain into a frequency domain by Fourier change, and is subjected to smoothing treatment by using an attenuation function D (a, b) in the frequency domain, so that random noise in fingerprint information can be effectively removed, the texture information of the fingerprint is reserved, and the identification degree is improved for identifying the identity information of a card holder when the fingerprint is subsequently used for carrying out quick payment.
Preferably, the enhancement processing unit 42 is used for converting the fingerprint information S1From the spatial domain into the fuzzy domain, in which fingerprint information S is1Carrying out nonlinear transformation and fuzzy inverse transformation to obtain fingerprint information S after enhancement processing2(ii) a The method specifically comprises the following steps:
1) fingerprint information S by adopting nonlinear membership function2Transforming the spatial domain to a fuzzy domain, wherein the self-defined nonlinear membership function of the fuzzy domain is as follows:
wherein Hp,qAs fingerprint information S1Membership value, J, at inner pixel point (p, q)p,qAs fingerprint information S1Grey value at inner pixel point (p, q), JavgAs fingerprint information S1Average gray value of JmaxAs fingerprint information S1The maximum gray value of the inner;
traversal of fingerprint information S1All the pixel points are processed to obtain fingerprint information S1Membership values of all the internal pixel points;
2) to Hp,qAnd carrying out nonlinear transformation, and obtaining a new fuzzy characteristic plane H' through the nonlinear transformation, wherein the nonlinear transformation function formula is defined as:
Hp,q＇＝Zl(Hp,q)＝Zl(Zl-1(Hp,q)),l＝1,2,3…
wherein Hp,qIs a fuzzy membership value after nonlinear transformation, JcThe fuzzy membership degree is a self-defined fuzzy membership degree threshold value; zl(Hp,q) Is a mapping function;
3) to Hp,qPerforming a non-linear inverse transformation to transform the denoised ROI image in the blur domain from the blur domain to the spatial domain, with the inverse transformation formula:
wherein: j. the design is a squarep,q' is an inverse transform function value obtained by an inverse transform;
traversing all pixel points, total J, in the fuzzy domainp,qThe set of composition is the fingerprint information S after enhancement processing2。
Has the advantages that: the fingerprint information S in the fuzzy domain can be enhanced by adopting a fuzzy domain enhancement algorithm1The texture features of the fingerprint are enhanced, the texture information of the fingerprint is kept, and meanwhile, the fingerprint can be well inhibitedThe interference of other random noises in the fingerprint information improves the accuracy and the identification degree of the fingerprint information and improves the safety of the fingerprint payment method.
Preferably, the texture extracting unit 43 is used for extracting the fingerprint information S after enhancement processing2Obtaining the fingerprint texture characteristics after the enhancement processing, wherein the fingerprint information after the enhancement processing is S2The size of (2) is 256 × 256, specifically:
1) fingerprint information S after enhancement processing by adopting convolutional neural network model2Extracting texture information; the realization method comprises the following steps: enhancing the processed fingerprint information S2As an input image, a convolution operation is performed on the input image by adopting a convolution filter with the size of 11 × 11 to obtain 96 feature maps with the size of 55 × 55, and data obtained by the convolution is subjected to transformation and normalization processing, wherein the normalization formula is as follows:
wherein,representing fingerprint information S after enhancement processing2The normalized value of the neuron activation degree calculated by the d convolution filter at the inner pixel point (r, s) through the application of the convolution kernel,representing fingerprint information S after enhancement processing2the activation degree of the neurons is calculated by the d-th convolution filter at the internal pixel point (r, s) through applying convolution kernels, N is the mapping number of the convolution kernels close to the same spatial position, and N is the total number of the convolution kernels, α, beta and ξ are preset values;
performing down-sampling on the data after the normalization processing, wherein a down-sampling window is 3 multiplied by 3, the step length is 2, and 96 characteristic graphs with the size of 27 multiplied by 27 are obtained; using 256 filters of size 5 × 5 × 48Performing convolution operation on 96 feature maps with the size of 27 × 27 to obtain 384 feature maps with the size of 13 × 13; performing convolution operation on 384 characteristic maps by 13 × 13 by adopting 256 filters with the size of 3 × 3 × 192 to obtain 256 characteristic maps by 13 × 13, and performing down-sampling operation on the obtained 256 characteristic maps by 13 × 13, wherein the down-sampling window size is 3 × 3, the step size is 2, and 256 characteristic maps with the size of 6 × 6 are obtained; arranging 256 pixel points of the 6 multiplied by 6 characteristic diagram obtained by down sampling into a line, and performing dimensionality reduction operation by using a neural network to obtain a 4096-dimensional output result; after the result after the dimensionality reduction processing is input into a full-connection neural network, the output is the fingerprint information S after the enhancement processing24096-dimensional characteristics of;
2) and performing dimensionality reduction operation on the extracted data by using a principal component analysis algorithm to obtain the enhanced fingerprint texture features.
Has the advantages that: for the fingerprint information S after enhancement processing2The method utilizes the convolutional neural network model to extract the textural features, and adopts a normalization processing mode to normalize the activation degree of the neurons during convolutional operation, thereby being beneficial to generalization of the convolutional neural network model and reducing the error rate of convolutional layers2The texture information in the method can well show the global characteristics of the fingerprint information by the full connection layer, and meanwhile, the fingerprint can be identified and identified in the later period, so that the fingerprint quick payment is completed.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (5)
1. A POS machine fast payment system based on fingerprint identification is characterized by comprising a POS machine and a fingerprint information storage server; the POS machine is connected with the fingerprint information storage server through a network;
the POS machine comprises a display screen, a keyboard and a card swiping slot; the POS machine is also provided with a fingerprint acquisition device and a fingerprint processing device, and the fingerprint acquisition device is used for acquiring fingerprint information of a payer; the fingerprint processing device is used for processing fingerprint information and transmitting the obtained fingerprint texture characteristics to the fingerprint information storage server;
the fingerprint information storage server is used for identifying the identity of the payer according to the received fingerprint texture characteristics, calling bank card information bound with the payer in advance according to the identity of the payer, feeding the bank card information back to the POS machine, and the payer selects a bank card to be used from the fed back bank card information and inputs payment amount and a password for payment.
2. The POS quick payment system of claim 1, wherein: the fingerprint processing device comprises a smoothing processing unit, an enhancement processing unit and a texture extraction unit; the smoothing processing unit is used for denoising the acquired fingerprint information; the enhancement processing unit is used for enhancing the de-noised fingerprint information; the texture extraction unit is used for extracting the fingerprint texture features after enhancement processing.
3. The POS quick payment system of claim 2, wherein: the smoothing unit is used for carrying out segmentation operation on the acquired fingerprint information, selecting a region with the size of 256 multiplied by 256 and containing abundant fingerprint texture information, namely an ROI (region of interest), carrying out smoothing processing on the ROI region, removing random noise in the ROI region and obtaining fingerprint information S subjected to smoothing processing1The method specifically comprises the following steps:
1) according to the acquired fingerprint information, carrying out segmentation operation on the fingerprint information, and selecting a region which is 256 multiplied by 256 and contains abundant fingerprint texture information, namely an ROI (region of interest);
2) processing the ROI area by adopting a Fourier transform algorithm, transforming the ROI area from a space domain into a frequency domain, smoothing the ROI area in the frequency domain by using an attenuation function D (a, b), performing inverse Fourier transform on the ROI area after smoothing, transforming the ROI area after smoothing from the frequency domain into the space domain to obtain fingerprint information S after smoothing1(ii) a The attenuation function D (a, b) is expressed as:
<mrow> <mi>D</mi> <mrow> <mo>(</mo> <mi>a</mi> <mo>,</mo> <mi>b</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mfrac> <mn>1</mn> <mrow> <mn>1</mn> <mo>+</mo> <msup> <mrow> <mo>&lsqb;</mo> <mfrac> <mroot> <mrow> <msup> <mi>a</mi> <mn>2</mn> </msup> <mo>+</mo> <msup> <mi>b</mi> <mn>2</mn> </msup> </mrow> <mn>2</mn> </mroot> <msub> <mi>F</mi> <mn>0</mn> </msub> </mfrac> <mo>&rsqb;</mo> </mrow> <mrow> <mn>2</mn> <mi>&kappa;</mi> </mrow> </msup> </mrow> </mfrac> </mtd> <mtd> <mrow> <mroot> <mrow> <msup> <mi>a</mi> <mn>2</mn> </msup> <mo>+</mo> <msup> <mi>b</mi> <mn>2</mn> </msup> </mrow> <mn>2</mn> </mroot> <mo>&le;</mo> <msub> <mi>F</mi> <mn>0</mn> </msub> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mrow> <mroot> <mrow> <msup> <mi>a</mi> <mn>2</mn> </msup> <mo>+</mo> <msup> <mi>b</mi> <mn>2</mn> </msup> </mrow> <mn>2</mn> </mroot> <mo>></mo> <msub> <mi>F</mi> <mn>0</mn> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
wherein, let (m, n) be the coordinates of pixel points in ROI region, (a, b) be the coordinates of corresponding pixel points in ROI region located in frequency domain, D (a, b) be attenuation function value, F0Is the cut-off frequency, κ is the attenuation factor, and is a positive integer greater than zero;
the high-frequency components of the ROI area located in the frequency domain are attenuated stepwise with an attenuation function D (a, b) so as to be higher than F0Is attenuated for high frequency components below F0All frequencies of (a) pass;
3) transforming the smoothed ROI region from the frequency domain to the space domain by inverse Fourier transform to obtain smoothed fingerprint information S1。
4. The POS quick payment system of claim 3, wherein: the enhancement processing unit is used for converting fingerprint information S1From the spatial domain into the fuzzy domain, in which fingerprint information S is1Carrying out nonlinear transformation and fuzzy inverse transformation to obtain fingerprint information S after enhancement processing2(ii) a The method specifically comprises the following steps:
1) fingerprint information S by adopting nonlinear membership function2Transforming the spatial domain to a fuzzy domain, wherein the self-defined nonlinear membership function of the fuzzy domain is as follows:
<mrow> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mo>=</mo> <msub> <mi>log</mi> <mn>2</mn> </msub> <mo>&lsqb;</mo> <mn>1</mn> <mo>+</mo> <mfrac> <mrow> <msub> <mi>J</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mo>+</mo> <msub> <mi>J</mi> <mrow> <mi>a</mi> <mi>v</mi> <mi>g</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>J</mi> <mi>max</mi> </msub> <mo>-</mo> <msub> <mi>J</mi> <mrow> <mi>a</mi> <mi>v</mi> <mi>g</mi> </mrow> </msub> </mrow> </mfrac> <mo>&rsqb;</mo> </mrow>
wherein Hp,As fingerprint information S1Membership value, J, at inner pixel point (p, q)p,As fingerprint information S1Grey value at inner pixel point (p, q), JavgAs fingerprint information S1Average gray value of JmaxAs fingerprint information S1The maximum gray value of the inner;
traversal of fingerprint information S1All the pixel points are processed to obtain fingerprint information S1Membership values of all the internal pixel points;
2) to Hp,And carrying out nonlinear transformation, and obtaining a new fuzzy characteristic plane H' through the nonlinear transformation, wherein the nonlinear transformation function formula is defined as:
Hp,q＇＝Zl(Hp,q)＝Zl(Zl-1(Hp,q)),l＝1,2,3…
<mrow> <msub> <mi>Z</mi> <mi>l</mi> </msub> <mrow> <mo>(</mo> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>ln</mi> <msup> <mrow> <mo>(</mo> <mfrac> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mi>&epsiv;</mi> </mfrac> <mo>)</mo> </mrow> <mn>3</mn> </msup> </mrow> </mtd> <mtd> <mrow> <mn>0</mn> <mo>&le;</mo> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mo><</mo> <msub> <mi>J</mi> <mi>c</mi> </msub> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>1</mn> <mo>-</mo> <mi>ln</mi> <msup> <mrow> <mo>(</mo> <mfrac> <mrow> <mn>1</mn> <mo>-</mo> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> </mrow> <mrow> <mn>1</mn> <mo>+</mo> <mi>&epsiv;</mi> </mrow> </mfrac> <mo>)</mo> </mrow> <mn>3</mn> </msup> </mrow> </mtd> <mtd> <mrow> <msub> <mi>J</mi> <mi>c</mi> </msub> <mo>&le;</mo> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mo><</mo> <mn>1</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
wherein Hp,qIs a fuzzy membership value after nonlinear transformation, JcThe fuzzy membership degree is a self-defined fuzzy membership degree threshold value; zl(Hp,q) Is a mapping function;
3) to Hp,qPerforming a non-linear inverse transformation to transform the denoised ROI image in the blur domain from the blur domain to the spatial domain, with the inverse transformation formula:
<mrow> <msup> <msub> <mi>J</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> <mo>&prime;</mo> </msup> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>J</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>J</mi> <mrow> <mi>a</mi> <mi>v</mi> <mi>g</mi> </mrow> </msub> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <msup> <mn>2</mn> <msub> <mi>H</mi> <mrow> <mi>p</mi> <mo>,</mo> <mi>q</mi> </mrow> </msub> </msup> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>+</mo> <msub> <mi>J</mi> <mrow> <mi>a</mi> <mi>v</mi> <mi>g</mi> </mrow> </msub> </mrow>
wherein: j. the design is a squarep,q' is an inverse transform function value obtained by an inverse transform;
traversing all pixel points, total J, in the fuzzy domainp,qThe set of composition is the fingerprint information S after enhancement processing2。
5. The POS quick payment system of claim 4, wherein: the texture extraction unit is used for extracting the fingerprint information S after enhancement processing2Obtaining the fingerprint texture characteristics after the enhancement processing, wherein the fingerprint information after the enhancement processing is S2The size of (2) is 256 × 256, specifically:
1) fingerprint information S after enhancement processing by adopting convolutional neural network model2Extracting texture information; the realization method comprises the following steps: enhancing the processed fingerprint information S2As an input image, a convolution operation is performed on the input image by adopting a convolution filter with the size of 11 × 11 to obtain 96 feature maps with the size of 55 × 55, and data obtained by the convolution is subjected to transformation and normalization processing, wherein the normalization formula is as follows:
<mrow> <msubsup> <mi>&theta;</mi> <mrow> <mi>r</mi> <mo>,</mo> <mi>s</mi> </mrow> <mi>d</mi> </msubsup> <mo>=</mo> <mfrac> <msubsup> <mi>e</mi> <mrow> <mi>r</mi> <mo>,</mo> <mi>s</mi> </mrow> <mi>d</mi> </msubsup> <msup> <mrow> <mo>(</mo> <mi>&alpha;</mi> <mo>+</mo> <msubsup> <mo>&Sigma;</mo> <mrow> <mi>max</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>,</mo> <mi>d</mi> <mo>-</mo> <mfrac> <mi>n</mi> <mn>2</mn> </mfrac> <mo>)</mo> </mrow> </mrow> <mrow> <mi>max</mi> <mrow> <mo>(</mo> <mi>N</mi> <mo>-</mo> <mn>1</mn> <mo>,</mo> <mi>d</mi> <mo>+</mo> <mfrac> <mi>n</mi> <mn>2</mn> </mfrac> <mo>)</mo> </mrow> </mrow> </msubsup> <msup> <mrow> <mo>(</mo> <mrow> <mi>&beta;</mi> <mo>&times;</mo> <msubsup> <mi>e</mi> <mrow> <mi>r</mi> <mo>,</mo> <mi>s</mi> </mrow> <mi>d</mi> </msubsup> </mrow> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mi>&xi;</mi> </msup> </mfrac> </mrow>
wherein,representing fingerprint information S after enhancement processing2The normalized value of the neuron activation degree calculated by the d convolution filter at the inner pixel point (r, s) through the application of the convolution kernel,representing fingerprint information S after enhancement processing2the activation degree of the neurons is calculated by the d-th convolution filter at the internal pixel point (r, s) through applying convolution kernels, N is the mapping number of the convolution kernels close to the same spatial position, N is the total number of the convolution kernels, α, beta and ξ are preset values;
performing down-sampling on the data after the normalization processing, wherein a down-sampling window is 3 multiplied by 3, the step length is 2, and 96 characteristic graphs with the size of 27 multiplied by 27 are obtained;carrying out convolution operation on 96 feature maps with the size of 27 × 27 by adopting 256 filters with the size of 5 × 5 × 48 to obtain 384 feature maps with the size of 13 × 13; performing convolution operation on 384 characteristic maps by 13 × 13 by adopting 256 filters with the size of 3 × 3 × 192 to obtain 256 characteristic maps by 13 × 13, and performing down-sampling operation on the obtained 256 characteristic maps by 13 × 13, wherein the down-sampling window size is 3 × 3, the step size is 2, and 256 characteristic maps with the size of 6 × 6 are obtained; arranging 256 pixel points of the 6 multiplied by 6 characteristic diagram obtained by down sampling into a line, and performing dimensionality reduction operation by using a neural network to obtain a 4096-dimensional output result; after the result after the dimensionality reduction processing is input into a full-connection neural network, the output is the fingerprint information S after the enhancement processing24096-dimensional characteristics of;
2) and performing dimensionality reduction operation on the extracted data by using a principal component analysis algorithm to obtain the enhanced fingerprint texture features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710900890.5A CN107657444A (en) | 2017-09-28 | 2017-09-28 | A kind of POS quick payment system based on fingerprint recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710900890.5A CN107657444A (en) | 2017-09-28 | 2017-09-28 | A kind of POS quick payment system based on fingerprint recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107657444A true CN107657444A (en) | 2018-02-02 |
Family
ID=61115944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710900890.5A Pending CN107657444A (en) | 2017-09-28 | 2017-09-28 | A kind of POS quick payment system based on fingerprint recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107657444A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109270394A (en) * | 2018-10-16 | 2019-01-25 | 江苏佳源科技有限公司 | A kind of intelligent low-pressure branch monitoring system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2002324636A1 (en) * | 2001-08-09 | 2003-02-24 | The Golub Cororation | Methods and systems for check processing using blank checks at a point-of-sale |
| CN102368292A (en) * | 2011-09-07 | 2012-03-07 | 常州蓝城信息科技有限公司 | Method for extracting multi-biometric characteristics of senior citizen |
| CN102611828A (en) * | 2012-01-11 | 2012-07-25 | 四川大学 | Real-time enhanced processing system for foggy continuous video image |
| CN103605963A (en) * | 2013-03-01 | 2014-02-26 | 新乡学院 | Fingerprint identification method |
| CN103942899A (en) * | 2014-04-04 | 2014-07-23 | 上海工程技术大学 | Fingerprint pos machine and fingerprint payment system |
| CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
-
2017
- 2017-09-28 CN CN201710900890.5A patent/CN107657444A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2002324636A1 (en) * | 2001-08-09 | 2003-02-24 | The Golub Cororation | Methods and systems for check processing using blank checks at a point-of-sale |
| CN102368292A (en) * | 2011-09-07 | 2012-03-07 | 常州蓝城信息科技有限公司 | Method for extracting multi-biometric characteristics of senior citizen |
| CN102611828A (en) * | 2012-01-11 | 2012-07-25 | 四川大学 | Real-time enhanced processing system for foggy continuous video image |
| CN103605963A (en) * | 2013-03-01 | 2014-02-26 | 新乡学院 | Fingerprint identification method |
| CN103942899A (en) * | 2014-04-04 | 2014-07-23 | 上海工程技术大学 | Fingerprint pos machine and fingerprint payment system |
| CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 刘点: "非接触掌纹图像增强与识别算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109270394A (en) * | 2018-10-16 | 2019-01-25 | 江苏佳源科技有限公司 | A kind of intelligent low-pressure branch monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9542684B2 (en) | Biometric based authorization systems for electronic fund transfers | |
| US20200027090A1 (en) | Systems and methods for authenticating financial transactions | |
| CN103714323B (en) | Fingerprint Image Enhancement and fingerprint identification device | |
| CN109345375B (en) | Suspicious money laundering behavior identification method and device | |
| CN102024141A (en) | Face recognition method based on Gabor wavelet transform and local binary pattern (LBP) optimization | |
| CN105069622A (en) | Face identification payment system facing mobile terminal and face identification payment method facing mobile terminal | |
| CN105303439A (en) | Bank system adopting human face recognition to enter account and confirming service through fingerprint | |
| CN113723309A (en) | Identity recognition method, identity recognition device, equipment and storage medium | |
| US20190057390A1 (en) | Biometric system for authenticating a biometric request | |
| WO2021025627A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
| CN107657444A (en) | A kind of POS quick payment system based on fingerprint recognition | |
| Fernandez et al. | Protection of online images against theft using robust multimodal biometric watermarking and T-norms | |
| US10504117B2 (en) | Methods, systems, and articles of manufacture for fingerprinting signatures and enhanced signature capturing for charge card transactions on mobile communication devices | |
| CN110309891B (en) | Reverse thrust system and method based on big data reading | |
| CN111967879A (en) | Online safe payment management system based on face recognition | |
| US20190295094A1 (en) | System and method for enabling receipt of electronic payments | |
| JP2023052065A (en) | Method and system of safe payment | |
| CN113516096B (en) | Finger vein ROI (region of interest) region extraction method and device | |
| US20190205855A1 (en) | Point-of-sale system for processing a payment transaction across multiple point-of-sale devices | |
| CN104102997A (en) | Credit card streaming media identification technology and online payment realization method | |
| Singh et al. | Secure swipe machine with help of biometric security | |
| CN108830594B (en) | Multi-mode electronic fare payment system | |
| US11798305B1 (en) | Methods and systems for determining the authenticity of an identity document | |
| CN104143141A (en) | Financial payment method based on credit card scanning technology | |
| CN110781477B (en) | Backstepping system based on big data reading |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180202 |
|
| RJ01 | Rejection of invention patent application after publication |