Search for: All records

In this paper we present AMPNet, an acoustic abnormality detection model deployed at ACV Auctions to automatically identify engine faults of vehicles listed on the ACV Auctions platform. We investigate the problem of engine fault detection and discuss our approach of deep-learning based audio classification on a large-scale automobile dataset collected at ACV Auctions. Specifically, we discuss our data collection pipeline and its challenges, dataset preprocessing and training procedures, and deployment of our trained models into a production setting. We perform empirical evaluations of AMPNet and demonstrate that our framework is able to successfully capture various engine anomalies agnostic of vehicle type. Finally we demonstrate the effectiveness and impact of AMPNet in the real world, specifically showing a 20.85% reduction in vehicle arbitrations on ACV Auctions' live auction platform. 

Traditional fingerprint authentication requires the acquisition of data through touch-based specialized sensors. However, due to many hygienic concerns including the global spread of the COVID virus through contact with a surface has led to an increased interest in contactless fingerprint image acquisition methods. Matching fingerprints acquired using contactless imaging against contact-based images brings up the problem of performing cross modal fingerprint matching for identity verification. In this paper, we propose a cost-effective, highly accurate and secure end-to-end contactless fingerprint recognition solution. The proposed framework first segments the finger region from an image scan of the hand using a mobile phone camera. For this purpose, we developed a cross-platform mobile application for fingerprint enrollment, verification, and authentication keeping security, robustness, and accessibility in mind. The segmented finger images go through fingerprint enhancement to highlight discriminative ridge-based features. A novel deep convolutional network is proposed to learn a representation from the enhanced images based on the optimization of various losses. The proposed algorithms for each stage are evaluated on multiple publicly available contactless databases. Our matching accuracy and the associated security employed in the system establishes the strength of the proposed solution framework. 

Abstract Capitalizing on the photoacoustic effect, we developed a new fingerprint sensing system that can reveal both fingerprints and underlying vascular structures at a high spatial resolution. Our system is built on a 15 MHz linear transducer array, a research ultrasound system, and a 532-nm pulsed laser. A 3D image was obtained by scanning the linear array over the fingertip. The acquired fingerprint images strongly agreed with the images acquired from ultrasound. Additional experiments were also conducted to investigate the effect of acoustic coupling. We discovered that high-quality fingerprint and vessel images can be acquired from both wet and dry fingers using our photoacoustic system. The reduced subdermal features in dry coupling can be enhanced through post-processing. Compared to existing fingerprint scanners, the photoacoustic approach provides a higher quality 3D image of the fingerprint, as well as unique subdermal vasculature structures, making the system almost impossible to counterfeit. 

Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models. We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN synthesized faces. 

Multistage, or serial, fusion refers to the algorithms sequentially fusing an increased number of matching results at each step and making decisions about accepting or rejecting the match hypothesis, or going to the next step. Such fusion methods are beneficial in the situations where running additional matching algorithms needed for later stages is time consuming or expensive. The construction of multistage fusion methods is challenging, since it requires both learning fusion functions and finding optimal decision thresholds for each stage. In this paper, we propose the use of single neural network for learning the multistage fusion. In addition we discuss the choices for the performance measurements of the trained algorithms and for the selection of network training optimization criteria. We perform the experiments using three face matching algorithms and IJB-A and IJB-C databases. 

In recent years, biometrics (e.g., fingerprint or face recognition) has replaced traditional passwords and PINs as a widely used method for user authentication, particularly in personal or mobile devices. Differing from state-of-the-art biometrics, heart biometrics offer the advantages of liveness detection, which provides strong tolerance to spoofing attacks. To date, several authentication methods primarily focusing on electrocardiogram (ECG) have demonstrated remarkable success; however, the degree of exploration with other cardiac signals is still limited. To this end, we discuss the challenges in various cardiac domains and propose future prospectives for developing effective heart biometrics systems in real-world applications. 

The security of biometric templates is of paramount importance. Leakage of biometric information may result in loss of private data and can lead to the compromise of the biometric system. Yet, the security of templates is often overlooked in favour of performance. In this paper, we present a plug-and-play framework for creating secure face templates with negligible degradation in the performance of the system. We propose a significant bit based representation which guarantees security in addition to other biometric aspects such as cancelability and reproducibility. In addition to being scalable, the proposed method does not make unrealistic assumptions regarding the pose or illumination of the face images. We provide experimental results on two unconstrained datasets - IJB-A and IJB-C. 

Long-term surveillance applications often involve having to re-identify individuals over several days or weeks. The task is made even more challenging with the lack of sufficient visibility of the subjects faces. We address this problem by modeling the wardrobe of individuals using discriminative features and labels extracted from their clothing information from video sequences. In contrast to previous person re-id works, we exploit that people typically own a limited amount of clothing and that knowing a person's wardrobe can be used as a soft-biometric to distinguish identities. We a) present a new dataset consisting of more than 70,000 images recorded over 30 days of 25 identities; b) model clothing features using CNNs that minimize intra-garments variations while maximizing inter-garments differences; and c) build a reference wardrobe model that captures each persons set of clothes that can be used for re-id. We show that these models open new perspectives to long-term person re-id problem using clothing information.