Fingerprint Feature Extraction by Combining Texture, Minutiae, and Frequency Spectrum Using Multi-Task CNN

Takahashi, Ai; Koda, Yoshinori; Ito, Koichi; Aoki, Takafumi

doi:10.1109/ijcb48548.2020.9304861

Cited by 27 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is well-known that a CNN model can be used as a feature extractor by removing the fully connected layers and using the remaining layers for feature extraction [32,33]. Similarly, in this paper, the same approach is applied to the Swin Transformer model.…”

Section: Proposed Methodsmentioning

confidence: 99%

A Swin transformer and MLP based method for identifying cherry ripeness and decay

Song,

Yang,

Wang

2023

Front. Phys.

View full text Add to dashboard Cite

Cherries are a nutritionally beneficial and economically significant crop, with fruit ripeness and decay (rot or rupture) being critical indicators in the cherry sorting process. Therefore, accurately identifying the maturity and decay of cherries is crucial in cherry processing. With advancements in artificial intelligence technology, many studies have utilized photographs for non-destructive detection of fruit appearance quality. This paper proposes a cherry appearance quality identification method based on the Swin Transformer, which utilizes the Swin Transformer to extract cherry image feature information and then imports the feature information into classifiers such as multi-layer perceptron(MLP) and support vector machine(SVM) for classification. Through the comparison of multiple classifiers, the optimal classifier, namely, MLP, in combination with the Swin Transformer is obtained. Furthermore, performance comparisons are conducted with the original Swin-T method, traditional CNN models, and traditional CNN models combined with MLP. The results demonstrate the following: 1) The proposed method based on the Swin Transformer and MLP achieves an accuracy rate of 98.5%, which is 2.1% higher than the original Swin-T model and 1.0% higher than the best-performing combination of traditional CNN model and MLP. 2) The training time required for the Swin Transformer and MLP is only 78.43 s, significantly faster than other models. The experimental results indicate that the innovative approach of combining the Swin Transformer and MLP shows excellent performance in identifying cherry ripeness and decay. The successful application of this method provides a new solution for determining cherry appearance ripeness and decay. Therefore, this method plays a significant role in promoting the development of cherry sorting machines.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

A Swin transformer and MLP based method for identifying cherry ripeness and decay

Song,

Yang,

Wang

2023

Front. Phys.

View full text Add to dashboard Cite

show abstract

“…The author used minutiae features for the alignment of the fingerprints and an additional feature, minutiae-related ridges is used for matching. Takahashi et al [23] presented a CNN-based architecture that incorporates texture, frequency, and minutiae features for fingerprint recognition. They achieved better accuracy than any other conventional and VeriFinger methods.…”

Section: Comparison Among Approachesmentioning

confidence: 99%

Features Understanding for Contactless and Contact-Based Fingerprint Matching

Singh,

Agarwal

2024

Advancements in Communication and Systems

View full text Add to dashboard Cite

A contactless fingerprint is a novel approach to fingerprint recognition, that originated after the covid-19 pandemic because of hygiene issues. In contactless and contact-based fingerprint matching several patterns and features are used to study the ridge-valley patterns of the fingertip. So, the performance of a fingerprint matching system depends on the feature extraction phase. Therefore, feature selection should be done cautiously. Over the period, numerous features and corresponding approaches have been developed for fingerprint recognition. Selecting one or more features is a crucial step in fingerprint identification, which depends upon the database and type of application (like military, commercial, etc.). Hence, the purpose of this study is to do a comprehensive assessment of the available features for matching contact-based and contactless fingerprints.

show abstract

“…Automated processes such as identification or verification are involved in a biometric recognition system where physical or behavioral characteristics of a biometric trait are used. Fingerprint identification is one of the most authentic approaches for human identification [ 1 ], where ridges and minutiae (ridge ending and branch) of the fingerprint information play a significant role in the recognition process [ 2 , 3 , 4 , 5 , 6 , 7 ]. The fingerprint is the oldest and a widely adopted biometric trait in forensic and civilian applications [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Mohamed-Abdul-Cader

Banks

Chandran

2023

Sensors

View full text Add to dashboard Cite

The fingerprint is a widely adopted biometric trait in forensic and civil applications. Fingerprint biometric systems have been investigated using contact prints and latent and contactless images which range from low to high resolution. While the imaging techniques are advancing with sensor variations, the input fingerprint images also vary. A general fingerprint recognition pipeline consists of a sensor module to acquire images, followed by feature representation, matching and decision modules. In the sensor module, the image quality of the biometric traits significantly affects the biometric system’s accuracy and performance. Imaging modality, such as contact and contactless, plays a key role in poor image quality, and therefore, paying attention to imaging modality is important to obtain better performance. Further, underlying physical principles and the working of the sensor can lead to their own forms of distortions during acquisition. There are certain challenges in each module of the fingerprint recognition pipeline, particularly sensors, image acquisition and feature representation. Present reviews in fingerprint systems only analyze the imaging techniques in fingerprint sensing that have existed for a decade. However, the latest emerging trends and recent advances in fingerprint sensing, image acquisition and their challenges have been left behind. Since the present reviews are either obsolete or restricted to a particular subset of the fingerprint systems, this work comprehensively analyzes the state of the art in the field of contact-based, contactless 2D and 3D fingerprint systems and their challenges in the aspects of sensors, image acquisition and interoperability. It outlines the open issues and challenges encountered in fingerprint systems, such as fingerprint performance, environmental factors, acceptability and interoperability, and alternate directions are proposed for a better fingerprint system.

show abstract

Fingerprint Feature Extraction by Combining Texture, Minutiae, and Frequency Spectrum Using Multi-Task CNN

Cited by 27 publications

References 11 publications

A Swin transformer and MLP based method for identifying cherry ripeness and decay

A Swin transformer and MLP based method for identifying cherry ripeness and decay

Features Understanding for Contactless and Contact-Based Fingerprint Matching

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Contact Info

Product

Resources

About