Cross-modality face recognition is an emerging topic due to the wide-spread usage of different sensors in day-to-day life applications. The development of face recognition systems relies greatly on existing databases for evaluation and obtaining training examples for data-hungry machine learning algorithms. However, currently, there is no publicly available face database that includes more than two modalities for the same subject. In this work, we introduce the Tufts Face Database that includes images acquired in various modalities: photograph images, thermal images, near infrared images, a recorded video, a computerized facial sketch, and 3D images of each volunteer's face. An Institutional Research Board protocol was obtained and images were collected from students, staff, faculty, and their family members at Tufts University. The database includes over 10,000 images from 113 individuals from more than 15 different countries, various gender identities, ages, and ethnic backgrounds. The contributions of this work are: 1) Detailed description of the content and acquisition procedure for images in the Tufts Face Database; 2) The Tufts Face Database is publicly available to researchers worldwide, which will allow assessment and creation of more robust, consistent, and adaptable recognition algorithms; 3) A comprehensive, up-to-date review on face recognition systems and face datasets.

Thermal imaging is a process of using infrared radiation and thermal energy to collect information about objects. It is superior to visible imaging for its ability to operate in darkness and tolerate illumination variations. In addition, it has potential to penetrate smoke, aerosol, dust, and mist, which are critical inhibitors for visible imaging applications, including semantic segmentation. Unfortunately, current state-of-the-art image semantic segmentation methods (i) mainly concentrate on visible spectrum images, which do not adequately capture the context of corresponding pixels, particularly edge details in thermal images, and (ii) accept a trade-off between higher accuracy and lower speed, or vice-versa. Here, a novel end-to-end trainable convolutional neural network architecture, feature transverse network (FTNet), has been proposed to solve the aforementioned problems. FTNet captures and optimizes feature representation at the multi-scale resolution, thereby improving the capability to process high-resolution images and producing quality output with a lower computational cost. Extensive computer experimentations were conducted on publicly available benchmarking thermal datasets, including SODA, MFNet, and SCUT-Seg, to demonstrate the effectiveness of the proposed FTNet compared to state-of-the-art methods. This comparison includes multiple aspects, including the quantitative accuracy and speed of the various approaches. The source code is available at https://github.com/shreyaskamathkm/FTNet.

Image restoration techniques process degraded images to highlight obscure details or enhance the scene with good contrast and vivid color for the best possible visibility. Poor illumination condition causes issues, such as high-level noise, unlikely color or texture distortions, nonuniform exposure, halo artifacts, and lack of sharpness in the images. This article presents a novel end-to-end trainable deep convolutional neural network called the deep perceptual image enhancement network (DPIENet) to address these challenges. The novel contributions of the proposed work are: 1) a framework to synthesize multiple exposures from a single image and utilizing the exposure variation to restore the image and 2) a loss function based on the approximation of the logarithmic response of the human eye. Extensive computer simulations on the benchmark MIT-Adobe FiveK and user studies performed using Google high dynamic range, DIV2K, and low light image datasets show that DPIENet has clear advantages over state-of-the-art techniques. It has the potential to be useful for many everyday applications such as modernizing traditional camera technologies that currently capture images/videos with under/overexposed regions due to their sensors limitations, to be used in consumer photography to help the users capture appealing images, or for a variety of intelligent systems, including automated driving and video surveillance applications.

Biometric based authentication, particularly for fingerprint authentication systems play a vital role in identifying an individual. The existing fingerprint authentication systems depend on specific points known as minutiae for recognizing an individual. Designing a reliable automatic fingerprint authentication system is still very challenging, since not all fingerprint information is available. Further, the information obtained is not always accurate due to cuts, scars, sweat, distortion and various skin conditions. Moreover, the existing fingerprint authentication systems do not utilize other significant minutiae information, which can improve the accuracy. Various local feature detectors such as Difference-of-Gaussian, Hessian, Hessian Laplace, Harris Laplace, Multiscale Harris, and Multiscale Hessian have been extensively used for feature detection. However, these detectors have not been employed for detecting fingerprint image features. In this article, a versatile local feature fingerprint matching scheme is proposed. The local features are obtained by exploiting these local geometric detectors and SIFT descriptor. This scheme considers local characteristic features of the fingerprint image, thus eliminating the issues caused in existing fingerprint feature based matching techniques. Computer simulations of the proposed algorithm on specific databases show significant improvements when compared to existing fingerprint matchers, such as minutiae matcher, hierarchical matcher and graph based matcher. Computer simulations conducted on the Neurotechnology database demonstrates a very low Equal Error Rate (EER) of 0.8%. The proposed system a) improves the accuracy of the fingerprint authentication system, b) works when the minutiae information is sparse, and c) produces satisfactory matching accuracy in the case when minutiae information is unavailable. The proposed system can also be employed for partial fingerprint authentication.

Fingerprint is one of the most widely used biometric in law enforcement. However, low-quality fingerprint images can drastically degrade the performance of automated fingerprint identification systems (AFIS). AFIS can be substantially advanced by: 1) establishing a metric to evaluate the image quality accurately and 2) utilizing this metric to enable an automated enhancement process. This paper offers a novel localized quality measure (LQM) to evaluate the quality of fingerprint images, and a genetic localized quality measure enhancement (LQME) algorithm, which is tailored to iteratively enhance poor-quality fingerprint images. In addition, a method is introduced to automatically choose the enhancement algorithm's parameters based on the proposed measure such that it yields the best enhancement result. The presented LQM measure uses fingerprint image characteristics, which include sharpness, contrast, orientation certainty level, symmetry features, and imprints of friction ridge structure (minutiae) information. The FVC2004 Set B database containing fingerprint images from four different sensors and a total of 240 images (80 from each sensor) is used to evaluate the performance of the presented algorithms and methods. The computer simulations demonstrate that the LQM measure is useful in predicting the quality of the fingerprint images captured from various devices. Furthermore, the experiments show that LQME can recover retrievable-corrupt fingerprint regions.

Thermal image super-resolution (SR) addresses the limited spatial resolution of infrared sensors, improving the visibility of fine details and supporting applications such as inspection, monitoring, and detection. This capability is particularly valuable in resource-constrained environments where sensor cost, storage, computational resources, and communication bandwidth limit high-resolution thermal imaging. Unlike interpolation, which estimates missing pixels from local image structure, SR aims to recover high-frequency spatial details while mitigating degradations such as blur, noise, and aliasing. This paper presents a comprehensive review of thermal-image SR, covering thermal imaging characteristics, publicly available datasets, evaluation metrics, and representative classical and deep learning methods. It also introduces a demosaicking-inspired deep fusion framework for single-image thermal SR. The proposed approach generates complementary reconstruction candidates using three conventional methods: bilinear interpolation, Malvar–He–Cutler symmetry-based demosaicking, and Menon-based interpolation. A lightweight FusionNet combines these outputs with an RLKA-Net reconstruction by learning spatially adaptive, pixel-wise fusion weights. Experiments on a thermal building-inspection dataset of 306 images demonstrate that FusionNet achieves a PSNR of 37.69 dB and an SSIM of 0.9746, outperforming the individual classical and deep-learning methods. Additionally, a quaternion-based FusionNet reduces model parameters by approximately 75% while maintaining comparable performance, and a higher-capacity quaternion variant slightly surpasses the real-valued model. The paper concludes by discussing remaining challenges and future directions for robust thermal-image SR in real-world applications.