Patent
Atlas literature
Patent
US 12,555,207 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example of a sample result of deblurring using the proposed FDeblur-GAN methodology and a state-of-the-art method, in accordance with …
FIG. 2 illustrates an example of an architecture of the proposed FDeblur-GAN methodology, in accordance with various embodiments of the present disclosure.
FIG. 3 illustrates examples of a blurred input fingerphoto, ground truth fingerphoto, the deblurred fingerphotos, and the 50 deblurred output, in accordance with …
FIG. 4 is a schematic diagram illustrating an example of a guided-attention (GA) mechanism, in accordance with various embodiments of the present disclosure. 55
FIG. 5 illustrates examples of blurred samples generated using different blurring kernels and the corresponding atten- tion maps, in accordance with various …
FIG. 6 illustrated examples of a ground truth fingerphoto 60 and sample blurred input fingerphoto with low to high parameter values for the blurring kernels, in …
FIGS. 7-9 illustrate examples of samples of blurred and deblurred from WVU dataset, IIT-B dataset and PolyU 65 dataset, in accordance with various embodiments …
FIG. 8 shows an example of a blurred sample from the IIT-B dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN.
FIG. 9 shows an example of a blurred sample from the PolyU dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN. The number on the bottom right …
FIG. 10 illustrates the matching performance on the WVU, IIT-B and PolyU datasets and models, in accordance with various embodiments of the present disclosure.
FIG. 11 illustrates an example of score distribution for the matching experiment on deblurred fingerphotos using FDe- blur-GAN and VeriFinger, in accordance …
FIG. 12 illustrates examples of NFIQ₂ quality score assessment of the ground truth, blurred, and deblurred fingerphotos from DeblurGAN-v2 and FDeblur-GAN, in …
FIG. 13 illustrates examples of real-world blurred finger- photos, in accordance with various embodiments of the present disclosure.
FIG. 14 illustrates the impact of each module in FDeblur- GAN on the quality of the deblurred samples, in accordance with various embodiments of the present …
FIG. 15 illustrates examples of log scaled ROC curves of different models evaluated during the ablation study, in accordance with various embodiments of the …
FIG. 16 illustrates examples of minutiae extraction on ground truth, deblurred fingerphoto by including and excluding the verifier, in accordance with various …
FIG. 17 is a schematic block diagram of one example of a system employed for fingerprint distortion rectification, in accordance with various embodiments of the …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method, comprising: obtaining a blurred image of a fingerprint; generating, using a guided-attention (GA) mechanism, an intermediate feature map of the blurred image, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generating a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The method of claim 1, wherein the predicted attention map is generated from the input feature map using a con-volutional layer and a Sigmoid function.
The method of claim 1, wherein generating the attended feature map comprises multiplying the input feature map with the predicted attention map.
The method of claim 1, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The method of claim 1, wherein the deblurred image is generated from the intermediate feature map using a con-volutional layer.
The method of claim 1, wherein the deblurred image is a deblurred output image of the fingerprint having a reso-lution equal to the blurred image of the fingerprint, the deblurred output image generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The method of claim 1, comprising identifying a blurring type associated with the blurred image based upon the intermediate feature map.
The method of claim 1, comprising generating a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map.
The method of claim 1, comprising determining a reconstruction loss based upon a comparison of the deblurred image and a corresponding ground truth image.
A system, comprising: processing circuitry comprising a processor and memory; and a fingerphoto deblurring application executable by the processing circuitry, where execution of the finger-photo deblurring application causes the processing cir-cuitry to: generate, using a guided-attention (GA) mechanism, an intermediate feature map of a blurred image of a fingerprint, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generate a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The system of claim 12, wherein the predicted atten-tion map is generated from the input feature map using a convolutional layer and a Sigmoid function.
The system of claim 12, wherein generating the attended feature map comprises multiplying the input fea-ture map with the predicted attention map.
The system of claim 12, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The system of claim 12, wherein the deblurred image is generated from the intermediate feature map using a convolutional layer.
The system of claim 12, wherein the deblurred image is generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The system of claim 12, comprising execution of the fingerphoto deblurring application causes the processing circuitry to generate a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
fingerphoto deblurring method using guided-attention (GA) mechanism
No layer stack recorded.
fingerphoto deblurring system with processing circuitry and GA mechanism application
No layer stack recorded.
FDeblur-GAN deep multi-task multi-stage generative model for fingerphoto deblurring
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 2
Cited non-patent literature · 3
Patent
Atlas literature
Patent
US 12,555,207 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example of a sample result of deblurring using the proposed FDeblur-GAN methodology and a state-of-the-art method, in accordance with …
FIG. 2 illustrates an example of an architecture of the proposed FDeblur-GAN methodology, in accordance with various embodiments of the present disclosure.
FIG. 3 illustrates examples of a blurred input fingerphoto, ground truth fingerphoto, the deblurred fingerphotos, and the 50 deblurred output, in accordance with …
FIG. 4 is a schematic diagram illustrating an example of a guided-attention (GA) mechanism, in accordance with various embodiments of the present disclosure. 55
FIG. 5 illustrates examples of blurred samples generated using different blurring kernels and the corresponding atten- tion maps, in accordance with various …
FIG. 6 illustrated examples of a ground truth fingerphoto 60 and sample blurred input fingerphoto with low to high parameter values for the blurring kernels, in …
FIGS. 7-9 illustrate examples of samples of blurred and deblurred from WVU dataset, IIT-B dataset and PolyU 65 dataset, in accordance with various embodiments …
FIG. 8 shows an example of a blurred sample from the IIT-B dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN.
FIG. 9 shows an example of a blurred sample from the PolyU dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN. The number on the bottom right …
FIG. 10 illustrates the matching performance on the WVU, IIT-B and PolyU datasets and models, in accordance with various embodiments of the present disclosure.
FIG. 11 illustrates an example of score distribution for the matching experiment on deblurred fingerphotos using FDe- blur-GAN and VeriFinger, in accordance …
FIG. 12 illustrates examples of NFIQ₂ quality score assessment of the ground truth, blurred, and deblurred fingerphotos from DeblurGAN-v2 and FDeblur-GAN, in …
FIG. 13 illustrates examples of real-world blurred finger- photos, in accordance with various embodiments of the present disclosure.
FIG. 14 illustrates the impact of each module in FDeblur- GAN on the quality of the deblurred samples, in accordance with various embodiments of the present …
FIG. 15 illustrates examples of log scaled ROC curves of different models evaluated during the ablation study, in accordance with various embodiments of the …
FIG. 16 illustrates examples of minutiae extraction on ground truth, deblurred fingerphoto by including and excluding the verifier, in accordance with various …
FIG. 17 is a schematic block diagram of one example of a system employed for fingerprint distortion rectification, in accordance with various embodiments of the …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method, comprising: obtaining a blurred image of a fingerprint; generating, using a guided-attention (GA) mechanism, an intermediate feature map of the blurred image, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generating a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The method of claim 1, wherein the predicted attention map is generated from the input feature map using a con-volutional layer and a Sigmoid function.
The method of claim 1, wherein generating the attended feature map comprises multiplying the input feature map with the predicted attention map.
The method of claim 1, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The method of claim 1, wherein the deblurred image is generated from the intermediate feature map using a con-volutional layer.
The method of claim 1, wherein the deblurred image is a deblurred output image of the fingerprint having a reso-lution equal to the blurred image of the fingerprint, the deblurred output image generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The method of claim 1, comprising identifying a blurring type associated with the blurred image based upon the intermediate feature map.
The method of claim 1, comprising generating a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map.
The method of claim 1, comprising determining a reconstruction loss based upon a comparison of the deblurred image and a corresponding ground truth image.
A system, comprising: processing circuitry comprising a processor and memory; and a fingerphoto deblurring application executable by the processing circuitry, where execution of the finger-photo deblurring application causes the processing cir-cuitry to: generate, using a guided-attention (GA) mechanism, an intermediate feature map of a blurred image of a fingerprint, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generate a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The system of claim 12, wherein the predicted atten-tion map is generated from the input feature map using a convolutional layer and a Sigmoid function.
The system of claim 12, wherein generating the attended feature map comprises multiplying the input fea-ture map with the predicted attention map.
The system of claim 12, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The system of claim 12, wherein the deblurred image is generated from the intermediate feature map using a convolutional layer.
The system of claim 12, wherein the deblurred image is generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The system of claim 12, comprising execution of the fingerphoto deblurring application causes the processing circuitry to generate a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
fingerphoto deblurring method using guided-attention (GA) mechanism
No layer stack recorded.
fingerphoto deblurring system with processing circuitry and GA mechanism application
No layer stack recorded.
FDeblur-GAN deep multi-task multi-stage generative model for fingerphoto deblurring
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 2
Cited non-patent literature · 3
Patent
Atlas literature
Patent
US 12,555,207 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example of a sample result of deblurring using the proposed FDeblur-GAN methodology and a state-of-the-art method, in accordance with …
FIG. 2 illustrates an example of an architecture of the proposed FDeblur-GAN methodology, in accordance with various embodiments of the present disclosure.
FIG. 3 illustrates examples of a blurred input fingerphoto, ground truth fingerphoto, the deblurred fingerphotos, and the 50 deblurred output, in accordance with …
FIG. 4 is a schematic diagram illustrating an example of a guided-attention (GA) mechanism, in accordance with various embodiments of the present disclosure. 55
FIG. 5 illustrates examples of blurred samples generated using different blurring kernels and the corresponding atten- tion maps, in accordance with various …
FIG. 6 illustrated examples of a ground truth fingerphoto 60 and sample blurred input fingerphoto with low to high parameter values for the blurring kernels, in …
FIGS. 7-9 illustrate examples of samples of blurred and deblurred from WVU dataset, IIT-B dataset and PolyU 65 dataset, in accordance with various embodiments …
FIG. 8 shows an example of a blurred sample from the IIT-B dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN.
FIG. 9 shows an example of a blurred sample from the PolyU dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN. The number on the bottom right …
FIG. 10 illustrates the matching performance on the WVU, IIT-B and PolyU datasets and models, in accordance with various embodiments of the present disclosure.
FIG. 11 illustrates an example of score distribution for the matching experiment on deblurred fingerphotos using FDe- blur-GAN and VeriFinger, in accordance …
FIG. 12 illustrates examples of NFIQ₂ quality score assessment of the ground truth, blurred, and deblurred fingerphotos from DeblurGAN-v2 and FDeblur-GAN, in …
FIG. 13 illustrates examples of real-world blurred finger- photos, in accordance with various embodiments of the present disclosure.
FIG. 14 illustrates the impact of each module in FDeblur- GAN on the quality of the deblurred samples, in accordance with various embodiments of the present …
FIG. 15 illustrates examples of log scaled ROC curves of different models evaluated during the ablation study, in accordance with various embodiments of the …
FIG. 16 illustrates examples of minutiae extraction on ground truth, deblurred fingerphoto by including and excluding the verifier, in accordance with various …
FIG. 17 is a schematic block diagram of one example of a system employed for fingerprint distortion rectification, in accordance with various embodiments of the …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method, comprising: obtaining a blurred image of a fingerprint; generating, using a guided-attention (GA) mechanism, an intermediate feature map of the blurred image, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generating a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The method of claim 1, wherein the predicted attention map is generated from the input feature map using a con-volutional layer and a Sigmoid function.
The method of claim 1, wherein generating the attended feature map comprises multiplying the input feature map with the predicted attention map.
The method of claim 1, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The method of claim 1, wherein the deblurred image is generated from the intermediate feature map using a con-volutional layer.
The method of claim 1, wherein the deblurred image is a deblurred output image of the fingerprint having a reso-lution equal to the blurred image of the fingerprint, the deblurred output image generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The method of claim 1, comprising identifying a blurring type associated with the blurred image based upon the intermediate feature map.
The method of claim 1, comprising generating a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map.
The method of claim 1, comprising determining a reconstruction loss based upon a comparison of the deblurred image and a corresponding ground truth image.
A system, comprising: processing circuitry comprising a processor and memory; and a fingerphoto deblurring application executable by the processing circuitry, where execution of the finger-photo deblurring application causes the processing cir-cuitry to: generate, using a guided-attention (GA) mechanism, an intermediate feature map of a blurred image of a fingerprint, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generate a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The system of claim 12, wherein the predicted atten-tion map is generated from the input feature map using a convolutional layer and a Sigmoid function.
The system of claim 12, wherein generating the attended feature map comprises multiplying the input fea-ture map with the predicted attention map.
The system of claim 12, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The system of claim 12, wherein the deblurred image is generated from the intermediate feature map using a convolutional layer.
The system of claim 12, wherein the deblurred image is generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The system of claim 12, comprising execution of the fingerphoto deblurring application causes the processing circuitry to generate a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
fingerphoto deblurring method using guided-attention (GA) mechanism
No layer stack recorded.
fingerphoto deblurring system with processing circuitry and GA mechanism application
No layer stack recorded.
FDeblur-GAN deep multi-task multi-stage generative model for fingerphoto deblurring
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 2
Cited non-patent literature · 3
Patent
Atlas literature
Patent
US 12,555,207 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 illustrates an example of a sample result of deblurring using the proposed FDeblur-GAN methodology and a state-of-the-art method, in accordance with …
FIG. 2 illustrates an example of an architecture of the proposed FDeblur-GAN methodology, in accordance with various embodiments of the present disclosure.
FIG. 3 illustrates examples of a blurred input fingerphoto, ground truth fingerphoto, the deblurred fingerphotos, and the 50 deblurred output, in accordance with …
FIG. 4 is a schematic diagram illustrating an example of a guided-attention (GA) mechanism, in accordance with various embodiments of the present disclosure. 55
FIG. 5 illustrates examples of blurred samples generated using different blurring kernels and the corresponding atten- tion maps, in accordance with various …
FIG. 6 illustrated examples of a ground truth fingerphoto 60 and sample blurred input fingerphoto with low to high parameter values for the blurring kernels, in …
FIGS. 7-9 illustrate examples of samples of blurred and deblurred from WVU dataset, IIT-B dataset and PolyU 65 dataset, in accordance with various embodiments …
FIG. 8 shows an example of a blurred sample from the IIT-B dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN.
FIG. 9 shows an example of a blurred sample from the PolyU dataset and deblurred samples using DeblurGAN-v2 and FDeblur-GAN. The number on the bottom right …
FIG. 10 illustrates the matching performance on the WVU, IIT-B and PolyU datasets and models, in accordance with various embodiments of the present disclosure.
FIG. 11 illustrates an example of score distribution for the matching experiment on deblurred fingerphotos using FDe- blur-GAN and VeriFinger, in accordance …
FIG. 12 illustrates examples of NFIQ₂ quality score assessment of the ground truth, blurred, and deblurred fingerphotos from DeblurGAN-v2 and FDeblur-GAN, in …
FIG. 13 illustrates examples of real-world blurred finger- photos, in accordance with various embodiments of the present disclosure.
FIG. 14 illustrates the impact of each module in FDeblur- GAN on the quality of the deblurred samples, in accordance with various embodiments of the present …
FIG. 15 illustrates examples of log scaled ROC curves of different models evaluated during the ablation study, in accordance with various embodiments of the …
FIG. 16 illustrates examples of minutiae extraction on ground truth, deblurred fingerphoto by including and excluding the verifier, in accordance with various …
FIG. 17 is a schematic block diagram of one example of a system employed for fingerprint distortion rectification, in accordance with various embodiments of the …
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A method, comprising: obtaining a blurred image of a fingerprint; generating, using a guided-attention (GA) mechanism, an intermediate feature map of the blurred image, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generating a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The method of claim 1, wherein the predicted attention map is generated from the input feature map using a con-volutional layer and a Sigmoid function.
The method of claim 1, wherein generating the attended feature map comprises multiplying the input feature map with the predicted attention map.
The method of claim 1, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The method of claim 1, wherein the deblurred image is generated from the intermediate feature map using a con-volutional layer.
The method of claim 1, wherein the deblurred image is a deblurred output image of the fingerprint having a reso-lution equal to the blurred image of the fingerprint, the deblurred output image generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The method of claim 1, comprising identifying a blurring type associated with the blurred image based upon the intermediate feature map.
The method of claim 1, comprising generating a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map.
The method of claim 1, comprising determining a reconstruction loss based upon a comparison of the deblurred image and a corresponding ground truth image.
A system, comprising: processing circuitry comprising a processor and memory; and a fingerphoto deblurring application executable by the processing circuitry, where execution of the finger-photo deblurring application causes the processing cir-cuitry to: generate, using a guided-attention (GA) mechanism, an intermediate feature map of a blurred image of a fingerprint, wherein the GA mechanism generates the intermediate feature map by: generating an attended feature map from an input feature map based upon a predicted attention map; and adding the input feature map to the attended feature map; and generate a deblurred image of the fingerprint based at least in part upon the intermediate feature map.
The system of claim 12, wherein the predicted atten-tion map is generated from the input feature map using a convolutional layer and a Sigmoid function.
The system of claim 12, wherein generating the attended feature map comprises multiplying the input fea-ture map with the predicted attention map.
The system of claim 12, wherein the input feature map is generated from an intermediate feature map generated by a preceding GA mechanism.
The system of claim 12, wherein the deblurred image is generated from the intermediate feature map using a convolutional layer.
The system of claim 12, wherein the deblurred image is generated by: up-sampling the intermediate feature map; and applying a convolutional layer.
The system of claim 12, comprising execution of the fingerphoto deblurring application causes the processing circuitry to generate a second intermediate feature map of the blurred image using a second GA mechanism, the second intermediate feature map having a resolution less than the intermediate feature map. ∗ ∗ ∗ ∗ ∗
Layer stacks claimed or described, ordered top of device to substrate.
fingerphoto deblurring method using guided-attention (GA) mechanism
No layer stack recorded.
fingerphoto deblurring system with processing circuitry and GA mechanism application
No layer stack recorded.
FDeblur-GAN deep multi-task multi-stage generative model for fingerphoto deblurring
No layer stack recorded.
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 2
Cited non-patent literature · 3
