Fingerprint indexing based on pyramid deep convolutional feature

Song, Dehua; Feng, Jufu

doi:10.1109/btas.2017.8272699

Cited by 19 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the seminal contributions of [22], [23] and [24], the past 10 years of research on fixed-length fingerprint representations has been quite stagnant. However, recent studies [25], [26], [27], [28] have utilized deep networks to extract highly discriminative fixed-length fingerprint representations. More specifically, (i) Cao and Jain [25] used global alignment and Inception v3 to learn fixed-length fingerprint representations.…”

Section: Prior Workmentioning

confidence: 99%

“…While these efforts show tremendous promise, each method has some limitations. In particular, (i) the algorithms proposed in [25] and [26] both required computationally demanding global alignment as a preprocessing step, and the accuracy is inferior to state-of-the-art COTS matchers. (ii) The representations extracted in [27] require the arduous process of minutiae-detection, patch extraction, patch-level inference, and an aggregation network to build a single global feature representation.…”

Section: Prior Workmentioning

confidence: 99%

“…More specifically, (i) Cao and Jain [25] used global alignment and Inception v3 to learn fixed-length fingerprint representations. (ii) Song and Feng [26] used deep networks to extract representations at various resolutions which were then aggregated into a global fixed-length representation. (iii) Song et al [27] further learned fixed-length minutiae descriptors which were aggregated into a global fixedlength representation via an aggregation network.…”

Section: Prior Workmentioning

confidence: 99%

See 2 more Smart Citations

Learning a Fixed-Length Fingerprint Representation

Engelsma

Cao²,

Jain

2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

We present DeepPrint, a deep network, which learns to extract fixed-length fingerprint representations of only 200 bytes. DeepPrint incorporates fingerprint domain knowledge, including alignment and minutiae detection, into the deep network architecture to maximize the discriminative power of its representation. The compact, DeepPrint representation has several advantages over the prevailing variable length minutiae representation which (i) requires computationally expensive graph matching techniques, (ii) is difficult to secure using strong encryption schemes (e.g. homomorphic encryption), and (iii) has low discriminative power in poor quality fingerprints where minutiae extraction is unreliable. We benchmark DeepPrint against two top performing COTS SDKs (Verifinger and Innovatrics) from the NIST and FVC evaluations. Coupled with a re-ranking scheme, the DeepPrint rank-1 search accuracy on the NIST SD4 dataset against a gallery of 1.1 million fingerprints is comparable to the top COTS matcher, but it is significantly faster (DeepPrint: 98.80% in 0.3 seconds vs. COTS A: 98.85% in 27 seconds). To the best of our knowledge, the DeepPrint representation is the most compact and discriminative fixed-length fingerprint representation reported in the academic literature.

show abstract

Section: Prior Workmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

Section: Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning a Fixed-Length Fingerprint Representation

Engelsma

Cao²,

Jain

2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…However, it is difficult to set the model threshold, and the classification rule function is complex and difficult to implement. Song et al [8] propose three-scale space indexing structure, which represents the global patterns, local details and fixed-length vectors respectively. These hierarchical indexing methods have some advantages, and also can be used for feature indexing of stereoscopic image/video in some way, but there are still some shortcomings that lead to poor efficiency.…”

Section: A Hierarchical Indexing Strategymentioning

confidence: 99%

Stereoscopic Image Feature Indexing Based on Hybrid Grid Multiple Suffix Tree and Hierarchical Clustering

Duan

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

In order to achieve content-based binocular stereoscopic image or video retrieval efficiently, a feature indexing algorithm based on hybrid grid multiple suffix tree and hierarchical clustering is proposed. With the RGB-D image model, the shape features of depth map obtained from the matching of binocular stereoscopic left image and right image and the color features of left image are extracted respectively. The features are quantified and hashed, and the optimized underlying features are sorted as leaf nodes of hierarchical indexing. Then the shape and color feature values of leaf nodes are mapped to the two-dimensional coordinates, and the 2D feature points are put into different grid hash areas respectively by clustering and labeled with multiple suffix tree. Furthermore, to construct the global index, a pointer to an array of clustering grid center point is defined according to the computation of grid area feature values. The experimental results show that compared to the double grid suffix tree and typical stereoscopic image feature indexing structure, the proposed algorithm can effectively reduce the indexing construction complexity While maintaining high recall, it can also greatly improve the query efficiency, which can better realize the feature indexing of binocular stereoscopic images or videos. INDEX TERMS Feature indexing, hierarchical clustering, hybrid grid multiple suffix tree, stereoscopic image.

show abstract

“…Comprehensive experiments were conducted to evaluate the retrieval performance of the proposed method on four benchmark databases. The experimental results in Appendix A reveal that the proposed MPC approach achieves a lower error rate than other prominent methods [8]. This is primarily because the power activation function enables the DCNN to learn a more discriminative and invariant representation of distortion.…”

mentioning

confidence: 96%