Pub Date : 2017-06-29DOI: 10.1109/BTAS.2017.8272757
S. S. Behera, Mahesh Gour, Vivek Kanhangad, N. Puhan
Periocular recognition has been an active area of research in the past few years. In spite of the advancements made in this area, the cross-spectral matching of visible (VIS) and near-infrared (NIR) periocular images remains a challenge. In this paper, we propose a method based on illumination normalization of VIS and NIR periocular images. Specifically, the approach involves normalizing the images using the difference of Gaussian (DoG) filtering, followed by the computation of a descriptor that captures structural details in the illumination normalized images using histogram of oriented gradients (HOG). Finally, the feature vectors corresponding to the query and the enrolled image are compared using the cosine similarity metric to generate a matching score. Performance of our algorithm has been evaluated on three publicly available benchmark databases of cross-spectral periocular images. Our approach yields significant improvement in performance over the existing approach.
{"title":"Periocular recognition in cross-spectral scenario","authors":"S. S. Behera, Mahesh Gour, Vivek Kanhangad, N. Puhan","doi":"10.1109/BTAS.2017.8272757","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272757","url":null,"abstract":"Periocular recognition has been an active area of research in the past few years. In spite of the advancements made in this area, the cross-spectral matching of visible (VIS) and near-infrared (NIR) periocular images remains a challenge. In this paper, we propose a method based on illumination normalization of VIS and NIR periocular images. Specifically, the approach involves normalizing the images using the difference of Gaussian (DoG) filtering, followed by the computation of a descriptor that captures structural details in the illumination normalized images using histogram of oriented gradients (HOG). Finally, the feature vectors corresponding to the query and the enrolled image are compared using the cosine similarity metric to generate a matching score. Performance of our algorithm has been evaluated on three publicly available benchmark databases of cross-spectral periocular images. Our approach yields significant improvement in performance over the existing approach.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126316805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-10DOI: 10.1109/BTAS.2017.8272700
Michal Balazia, Petr Sojka
This work offers a design of a video surveillance system based on a soft biometric — gait identification from MoCap data. The main focus is on two substantial issues of the video surveillance scenario: (1) the walkers do not cooperate in providing learning data to establish their identities and (2) the data are often noisy or incomplete. We show that only a few examples of human gait cycles are required to learn a projection of raw MoCap data onto a low-dimensional subspace where the identities are well separable. Latent features learned by Maximum Margin Criterion (MMC) method discriminate better than any collection of geometric features. The MMC method is also highly robust to noisy data and works properly even with only a fraction of joints tracked. The overall workflow of the design is directly applicable for a day-to-day operation based on the available MoCap technology and algorithms for gait analysis. In the concept we introduce, a walker's identity is represented by a cluster of gait data collected at their incidents within the surveillance system: They are how they walk.
{"title":"You are how you walk: Uncooperative MoCap gait identification for video surveillance with incomplete and noisy data","authors":"Michal Balazia, Petr Sojka","doi":"10.1109/BTAS.2017.8272700","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272700","url":null,"abstract":"This work offers a design of a video surveillance system based on a soft biometric — gait identification from MoCap data. The main focus is on two substantial issues of the video surveillance scenario: (1) the walkers do not cooperate in providing learning data to establish their identities and (2) the data are often noisy or incomplete. We show that only a few examples of human gait cycles are required to learn a projection of raw MoCap data onto a low-dimensional subspace where the identities are well separable. Latent features learned by Maximum Margin Criterion (MMC) method discriminate better than any collection of geometric features. The MMC method is also highly robust to noisy data and works properly even with only a fraction of joints tracked. The overall workflow of the design is directly applicable for a day-to-day operation based on the available MoCap technology and algorithms for gait analysis. In the concept we introduce, a walker's identity is represented by a cluster of gait data collected at their incidents within the surveillance system: They are how they walk.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121205156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-09DOI: 10.1109/BTAS.2017.8272706
Haibo Jin, Xiaobo Wang, Shengcai Liao, S. Li
Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is limited since they ignore the fact that different dimension of embedding may play different importance. In this paper, we propose to employ identification loss with center loss to train a deep model for person re-identification. The training process is efficient since it does not require image pairs or triplets for training while the inter-class distinction and intra-class variance are well handled. To boost the performance, a new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding. Experiments 1 on several benchmark datasets have shown the superiority of our method over the state-of-the-art alternatives on both accuracy and speed.
{"title":"Deep person re-identification with improved embedding and efficient training","authors":"Haibo Jin, Xiaobo Wang, Shengcai Liao, S. Li","doi":"10.1109/BTAS.2017.8272706","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272706","url":null,"abstract":"Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is limited since they ignore the fact that different dimension of embedding may play different importance. In this paper, we propose to employ identification loss with center loss to train a deep model for person re-identification. The training process is efficient since it does not require image pairs or triplets for training while the inter-class distinction and intra-class variance are well handled. To boost the performance, a new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding. Experiments 1 on several benchmark datasets have shown the superiority of our method over the state-of-the-art alternatives on both accuracy and speed.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131063068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-04DOI: 10.1109/BTAS.2017.8272727
Jan Svoboda, Federico Monti, M. Bronstein
Performance of fingerprint recognition depends heavily on the extraction of minutiae points. Enhancement of the fingerprint ridge pattern is thus an essential pre-processing step that noticeably reduces false positive and negative detection rates. A particularly challenging setting is when the fingerprint images are corrupted or partially missing. In this work, we apply generative convolutional networks to denoise visible minutiae and predict the missing parts of the ridge pattern. The proposed enhancement approach is tested as a pre-processing step in combination with several standard feature extraction methods such as MINDTCT, followed by biometric comparison using MCC and BO-ZORTH3. We evaluate our method on several publicly available latent fingerprint datasets captured using different sensors.
{"title":"Generative convolutional networks for latent fingerprint reconstruction","authors":"Jan Svoboda, Federico Monti, M. Bronstein","doi":"10.1109/BTAS.2017.8272727","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272727","url":null,"abstract":"Performance of fingerprint recognition depends heavily on the extraction of minutiae points. Enhancement of the fingerprint ridge pattern is thus an essential pre-processing step that noticeably reduces false positive and negative detection rates. A particularly challenging setting is when the fingerprint images are corrupted or partially missing. In this work, we apply generative convolutional networks to denoise visible minutiae and predict the missing parts of the ridge pattern. The proposed enhancement approach is tested as a pre-processing step in combination with several standard feature extraction methods such as MINDTCT, followed by biometric comparison using MCC and BO-ZORTH3. We evaluate our method on several publicly available latent fingerprint datasets captured using different sensors.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123099944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-04-21DOI: 10.1109/BTAS.2017.8272680
Sandipan Banerjee, John S. Bernhard, W. Scheirer, K. Bowyer, P. Flynn
In this paper, we propose a novel face synthesis approach that can generate an arbitrarily large number of synthetic images of both real and synthetic identities. Thus a face image dataset can be expanded in terms of the number of identities represented and the number of images per identity using this approach, without the identity-labeling and privacy complications that come from downloading images from the web. To measure the visual fidelity and uniqueness of the synthetic face images and identities, we conducted face matching experiments with both human participants and a CNN pre-trained on a dataset of 2.6M real face images. To evaluate the stability of these synthetic faces, we trained a CNN model with an augmented dataset containing close to 200,000 synthetic faces. We used a snapshot of this trained CNN to recognize extremely challenging frontal (real) face images. Experiments showed training with the augmented faces boosted the face recognition performance of the CNN.
{"title":"SREFI: Synthesis of realistic example face images","authors":"Sandipan Banerjee, John S. Bernhard, W. Scheirer, K. Bowyer, P. Flynn","doi":"10.1109/BTAS.2017.8272680","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272680","url":null,"abstract":"In this paper, we propose a novel face synthesis approach that can generate an arbitrarily large number of synthetic images of both real and synthetic identities. Thus a face image dataset can be expanded in terms of the number of identities represented and the number of images per identity using this approach, without the identity-labeling and privacy complications that come from downloading images from the web. To measure the visual fidelity and uniqueness of the synthetic face images and identities, we conducted face matching experiments with both human participants and a CNN pre-trained on a dataset of 2.6M real face images. To evaluate the stability of these synthetic faces, we trained a CNN model with an augmented dataset containing close to 200,000 synthetic faces. We used a snapshot of this trained CNN to recognize extremely challenging frontal (real) face images. Experiments showed training with the augmented faces boosted the face recognition performance of the CNN.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132707788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-03-30DOI: 10.1109/BTAS.2017.8272691
Donghyun Kim, Matthias Hernandez, Jongmoo Choi, G. Medioni
We propose a novel 3D face recognition algorithm using a deep convolutional neural network (DCNN) and a 3D face expression augmentation technique. The performance of 2D face recognition algorithms has significantly increased by leveraging the representational power of deep neural networks and the use of large-scale labeled training data. In this paper, we show that transfer learning from a CNN trained on 2D face images can effectively work for 3D face recognition by fine-tuning the CNN with an extremely small number of 3D facial scans. We also propose a 3D face expression augmentation technique which synthesizes a number of different facial expressions from a single 3D face scan. Our proposed method shows excellent recognition results on Bosphorus, BU-3DFE, and 3D-TEC datasets without using hand-crafted features. The 3D face identification using our deep features also scales well for large databases.
{"title":"Deep 3D face identification","authors":"Donghyun Kim, Matthias Hernandez, Jongmoo Choi, G. Medioni","doi":"10.1109/BTAS.2017.8272691","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272691","url":null,"abstract":"We propose a novel 3D face recognition algorithm using a deep convolutional neural network (DCNN) and a 3D face expression augmentation technique. The performance of 2D face recognition algorithms has significantly increased by leveraging the representational power of deep neural networks and the use of large-scale labeled training data. In this paper, we show that transfer learning from a CNN trained on 2D face images can effectively work for 3D face recognition by fine-tuning the CNN with an extremely small number of 3D facial scans. We also propose a 3D face expression augmentation technique which synthesizes a number of different facial expressions from a single 3D face scan. Our proposed method shows excellent recognition results on Bosphorus, BU-3DFE, and 3D-TEC datasets without using hand-crafted features. The 3D face identification using our deep features also scales well for large databases.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122249494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-18DOI: 10.1109/BTAS.2017.8272695
Andras Rozsa, Manuel Günther, T. Boult
Deep neural networks provide state-of-the-art performance on various tasks and are, therefore, widely used in real world applications. DNNs are becoming frequently utilized in biometrics for extracting deep features, which can be used in recognition systems for enrolling and recognizing new individuals. It was revealed that deep neural networks suffer from a fundamental problem, namely, they can unexpectedly misclassify examples formed by slightly perturbing correctly recognized inputs. Various approaches have been developed for generating these so-called adversarial examples, but they aim at attacking end-to-end networks. For biometrics, it is natural to ask whether systems using deep features are immune to or, at least, more resilient to attacks than end-to-end networks. In this paper, we introduce a general technique called the layerwise origin-target synthesis (LOTS) that can be efficiently used to form adversarial examples that mimic the deep features of the target. We analyze and compare the adversarial robustness of the end-to-end VGG Face network with systems that use Euclidean or cosine distance between gallery templates and extracted deep features. We demonstrate that iterative LOTS is very effective and show that systems utilizing deep features are easier to attack than the end-to-end network.
{"title":"LOTS about attacking deep features","authors":"Andras Rozsa, Manuel Günther, T. Boult","doi":"10.1109/BTAS.2017.8272695","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272695","url":null,"abstract":"Deep neural networks provide state-of-the-art performance on various tasks and are, therefore, widely used in real world applications. DNNs are becoming frequently utilized in biometrics for extracting deep features, which can be used in recognition systems for enrolling and recognizing new individuals. It was revealed that deep neural networks suffer from a fundamental problem, namely, they can unexpectedly misclassify examples formed by slightly perturbing correctly recognized inputs. Various approaches have been developed for generating these so-called adversarial examples, but they aim at attacking end-to-end networks. For biometrics, it is natural to ask whether systems using deep features are immune to or, at least, more resilient to attacks than end-to-end networks. In this paper, we introduce a general technique called the layerwise origin-target synthesis (LOTS) that can be efficiently used to form adversarial examples that mimic the deep features of the target. We analyze and compare the adversarial robustness of the end-to-end VGG Face network with systems that use Euclidean or cosine distance between gallery templates and extracted deep features. We demonstrate that iterative LOTS is very effective and show that systems utilizing deep features are easier to attack than the end-to-end network.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131471680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-18DOI: 10.1109/BTAS.2017.8272686
Manuel Günther, Andras Rozsa, T. Boult
Facial attributes are soft-biometrics that allow limiting the search space, e.g., by rejecting identities with non-matching facial characteristics such as nose sizes or eyebrow shapes. In this paper, we investigate how the latest versions of deep convolutional neural networks, ResNets, perform on the facial attribute classification task. We test two loss functions: the sigmoid cross-entropy loss and the Euclidean loss, and find that for classification performance there is little difference between these two. Using an ensemble of three ResNets, we obtain the new state-of-the-art facial attribute classification error of 8.00 % on the aligned images of the CelebA dataset. More significantly, we introduce the Alignment-Free Facial Attribute Classification Technique (AFFACT), a data augmentation technique that allows a network to classify facial attributes without requiring alignment beyond detected face bounding boxes. To our best knowledge, we are the first to report similar accuracy when using only the detected bounding boxes — rather than requiring alignment based on automatically detected facial landmarks — and who can improve classification accuracy with rotating and scaling test images. We show that this approach outperforms the CelebA baseline on unaligned images with a relative improvement of 36.8 %.
{"title":"AFFACT: Alignment-free facial attribute classification technique","authors":"Manuel Günther, Andras Rozsa, T. Boult","doi":"10.1109/BTAS.2017.8272686","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272686","url":null,"abstract":"Facial attributes are soft-biometrics that allow limiting the search space, e.g., by rejecting identities with non-matching facial characteristics such as nose sizes or eyebrow shapes. In this paper, we investigate how the latest versions of deep convolutional neural networks, ResNets, perform on the facial attribute classification task. We test two loss functions: the sigmoid cross-entropy loss and the Euclidean loss, and find that for classification performance there is little difference between these two. Using an ensemble of three ResNets, we obtain the new state-of-the-art facial attribute classification error of 8.00 % on the aligned images of the CelebA dataset. More significantly, we introduce the Alignment-Free Facial Attribute Classification Technique (AFFACT), a data augmentation technique that allows a network to classify facial attributes without requiring alignment beyond detected face bounding boxes. To our best knowledge, we are the first to report similar accuracy when using only the detected bounding boxes — rather than requiring alignment based on automatically detected facial landmarks — and who can improve classification accuracy with rotating and scaling test images. We show that this approach outperforms the CelebA baseline on unaligned images with a relative improvement of 36.8 %.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129603558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-04DOI: 10.1109/BTAS.2017.8272731
Ankan Bansal, Anirudh Nanduri, C. Castillo, Rajeev Ranjan, R. Chellappa
Recent progress in face detection (including keypoint detection), and recognition is mainly being driven by (i) deeper convolutional neural network architectures, and (ii) larger datasets. However, most of the large datasets are maintained by private companies and are not publicly available. The academic computer vision community needs larger and more varied datasets to make further progress. In this paper, we introduce a new face dataset, called UMDFaces, which has 367,888 annotated faces of 8,277 subjects. We also introduce a new face recognition evaluation protocol which will help advance the state-of-the-art in this area. We discuss how a large dataset can be collected and annotated using human annotators and deep networks. We provide human curated bounding boxes for faces. We also provide estimated pose (roll, pitch and yaw), locations of twenty-one key-points and gender information generated by a pre-trained neural network. In addition, the quality of keypoint annotations has been verified by humans for about 115,000 images. Finally, we compare the quality of the dataset with other publicly available face datasets at similar scales.
{"title":"UMDFaces: An annotated face dataset for training deep networks","authors":"Ankan Bansal, Anirudh Nanduri, C. Castillo, Rajeev Ranjan, R. Chellappa","doi":"10.1109/BTAS.2017.8272731","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272731","url":null,"abstract":"Recent progress in face detection (including keypoint detection), and recognition is mainly being driven by (i) deeper convolutional neural network architectures, and (ii) larger datasets. However, most of the large datasets are maintained by private companies and are not publicly available. The academic computer vision community needs larger and more varied datasets to make further progress. In this paper, we introduce a new face dataset, called UMDFaces, which has 367,888 annotated faces of 8,277 subjects. We also introduce a new face recognition evaluation protocol which will help advance the state-of-the-art in this area. We discuss how a large dataset can be collected and annotated using human annotators and deep networks. We provide human curated bounding boxes for faces. We also provide estimated pose (roll, pitch and yaw), locations of twenty-one key-points and gender information generated by a pre-trained neural network. In addition, the quality of keypoint annotations has been verified by humans for about 115,000 images. Finally, we compare the quality of the dataset with other publicly available face datasets at similar scales.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124701441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-30DOI: 10.1109/BTAS.2017.8272689
Yao Tang, Fei Gao, Jufu Feng
Minutiae play a major role in fingerprint identification. Extracting reliable minutiae is difficult for latent fingerprints which are usually of poor quality. As the limitation of traditional handcrafted features, a fully convolutional network (FCN) is utilized to learn features directly from data to overcome complex background noises. Raw fingerprints are mapped to a correspondingly-sized minutia-score map with a fixed stride. And thus a large number of minutiae will be extracted through a given threshold. Then small regions centering at these minutia points are entered into a convolutional neural network (CNN) to reclassify these minutiae and calculate their orientations. The CNN shares convolutional layers with the fully convolutional network to speed up. 0.45 second is used on average to detect one fingerprint on a GPU. On the NIST SD27 database, we achieve 53% recall rate and 53% precise rate that outperform many other algorithms. Our trained model is also visualized to show that we have successfully extracted features preserving ridge information of a latent fingerprint.
{"title":"Latent fingerprint minutia extraction using fully convolutional network","authors":"Yao Tang, Fei Gao, Jufu Feng","doi":"10.1109/BTAS.2017.8272689","DOIUrl":"https://doi.org/10.1109/BTAS.2017.8272689","url":null,"abstract":"Minutiae play a major role in fingerprint identification. Extracting reliable minutiae is difficult for latent fingerprints which are usually of poor quality. As the limitation of traditional handcrafted features, a fully convolutional network (FCN) is utilized to learn features directly from data to overcome complex background noises. Raw fingerprints are mapped to a correspondingly-sized minutia-score map with a fixed stride. And thus a large number of minutiae will be extracted through a given threshold. Then small regions centering at these minutia points are entered into a convolutional neural network (CNN) to reclassify these minutiae and calculate their orientations. The CNN shares convolutional layers with the fully convolutional network to speed up. 0.45 second is used on average to detect one fingerprint on a GPU. On the NIST SD27 database, we achieve 53% recall rate and 53% precise rate that outperform many other algorithms. Our trained model is also visualized to show that we have successfully extracted features preserving ridge information of a latent fingerprint.","PeriodicalId":372008,"journal":{"name":"2017 IEEE International Joint Conference on Biometrics (IJCB)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：