3D Vascular Pattern Extraction from Grayscale Volumetric Ultrasound Images for Biometric Recognition Purposes

Abstract

Recognition systems based on palm veins are gaining increasing attention as they are highly distinctive and very hard to counterfeit. Most popular systems are based on infrared radiation; they have the merit to be contactless but can provide only 2D patterns. Conversely, 3D patterns can be achieved with Doppler or photoacoustic methods, but these approaches require too long of an acquisition time. In this work, a method for extracting 3D vascular patterns from conventional grayscale volumetric images of the human hand, which can be collected in a short time, is proposed for the first time. It is based on the detection of low-brightness areas in B-mode images. Centroids of these areas in successive B-mode images are then linked through a minimum distance criterion. Preliminary verification and identification results, carried out on a database previously established for extracting 3D palmprint features, demonstrated good recognition performances: EER = 2%, ROC AUC = 99.92%, and an identification rate of 100%. As further merit, 3D vein pattern features can be fused to 3D palmprint features to implement a costless multimodal recognition system.

Fluorescence, ultrasonic and photoacoustic imaging for analysis and diagnosis of diseases

“…31,32 Hence, substantial efforts have been made to develop improved ultrasonic imaging methods, including ultrasensitive, quantitative, high-resolution and high-frequency ultrasonic imaging, as well as 4D functional ultrasonic imaging, aimed at improving the accuracy of tumor diagnosis. [109][110][111][112][113][114][115][116][117] By combination with other image analysis techniques (e.g., artificial intelligence (AI) and deep learning), professionals can reduce interference from false positive signals and effectively determine the boundary of tumor tissues. 31,32,115 In 2017, Dong and coworkers developed an adaptive fuzzy C-means (FCM) method based on the Hausdorff distance definition to segment the ultrasonic imaging of breast cancer by adaptive selection of adjacent regions of each pixel for distance measurement and centroid updating.…”

“…31,32 Hence, substantial efforts have been made to develop improved ultrasonic imaging methods, including ultrasensitive, quantitative, high-resolution and high-frequency ultrasonic imaging, as well as 4D functional ultrasonic imaging, aimed at improving the accuracy of tumor diagnosis. 109–117 By combination with other image analysis techniques ( e.g. , artificial intelligence (AI) and deep learning), professionals can reduce interference from false positive signals and effectively determine the boundary of tumor tissues.…”

Biometric Recognition in 3D Medical Images: A Survey

“…A recent work from the year 2022 [50] further proposed 3D vascular pattern extraction method from gray-scale volumetric 3D ultrasound images. In this work, they further improved their centroid-based method from 2017 [46] with image enhancement method in form of a speckle-reducing anisotropic diffusion filter to reduce the speckle noise caused by the capture device.…”

Recognition Performance Analysis of a Multimodal Biometric System Based on the Fusion of 3D Ultrasound Hand-Geometry and Palmprint

“…Ultrasound technology has been widely investigated in the biometric field, particularly for extraction of fingerprint features [ 20 , 21 ] and, recently, the integration of the sensor in smartphone devices became reality [ 22 ]. Other characteristics, including hand geometry [ 23 , 24 ], palmprint [ 25 , 26 , 27 ], and hand veins [ 28 , 29 , 30 ] were also investigated.…”