Ensemble-Based Bounding Box Regression for Enhanced Knuckle Localization.

The knuckle creases present on the dorsal side of the human hand can play significant role in identifying the offenders of serious crime, especially when evidence images of more recognizable biometric traits, such as the face, are not available. These knuckle creases, if localized appropriately, can result in improved identification ability. This is attributed to ambient inclusion of the creases and minimal effect of background, which lead to quality and discerning feature extraction. This paper presents an ensemble approach, utilizing multiple object detector frameworks, to localize the knuckle regions in a functionally appropriate way. The approach leverages from the individual capabilities of the popular object detectors and provide a more comprehensive knuckle region localization. The investigations are completed with two large-scale public hand databases which consist of hand-dorsal images with varying backgrounds and finger positioning. In addition to that, effectiveness of the proposed approach is also tested with a novel proprietary unconstrained multi-ethnic hand dorsal dataset to evaluate its generalizability. Several novel performance metrics are tailored to evaluate the efficacy of the proposed knuckle localization approach. These metrics aim to measure the veracity of the detected knuckle regions in terms of their relation with the ground truth. The comparison of the proposed approach with individual object detectors and a state-of-the-art hand keypoint detector clearly establishes the outperforming nature of the proposed approach. The generalization of the proposed approach is also corroborated through the cross-dataset framework.

Enhanced near-infrared periocular recognition through collaborative rendering of hand crafted and deep features.

Periocular recognition leverage from larger feature region and lesser user cooperation, when compared against the traditional iris recognition. Moreover, in the current scenario of Covid-19, where majority of people cover their faces with masks, potential of recognizing faces gets reduced by a large extent, calling for wide applicability of periocular recognition. In view of these facts, this paper targets towards enhanced representation of near-infrared periocular images, by combined use of hand-crafted and deep features. The hand-crafted features are extracted through partitioning of periocular image followed by obtaining the local statistical properties pertaining to each partition. Whereas, deep features are extracted through the popular convolutional neural network (CNN) ResNet-101 model. The extensive set of experiments performed with a benchmark periocular database validates the promising performance of the proposed method. Additionally, investigation of cross-spectral matching framework and comparison with state-of-the-art, reveal that combination of both types of features employed could prove to be extremely effective.

Modifying Randles circuit for analysis of polyoxometalate layer-by-layer films.

Multilayer films with anionic phosphomolybidic acid (PMo(12)) clusters have been fabricated via the electrostatic layer-by-layer (LbL) method. The charged mass transport phenomena of these thin films have been studied using cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS) with [Fe(CN)(6)](3-/4-) and [Ru(NH(3))(6)](3+/2+) as the redox probes. By adding a film resistance and a film capacitance to the conventional Randles equivalent circuit, we can calculate the diffusion coefficient values that help understand the microscopic nature of the thin films. When the negatively charged probe [Fe(CN)(6)](3-/4-) was used, lower diffusion coefficients were obtained for multilayers deposited from higher ionic strength solutions. This relationship was less obvious when the positively charged probe [Ru(NH(3))(6)](3+/2+) was used, in which the electrostatic attraction between PMo(12) clusters and the probe ions complicates the mass-transfer process. It is believed that the addition of salt to dipping solutions increases the tortuosity of the films so the mass transport takes longer paths, inducing lower diffusion coefficients. Higher PMo(12) loading causes lower diffusion coefficients due to the polyoxometalate clusters blocking the paths for charged probe ions.

Electrochemical analysis of conducting polymer thin films.

Polyelectrolyte multilayers built via the layer-by-layer (LbL) method has been one of the most promising systems in the field of materials science. Layered structures can be constructed by the adsorption of various polyelectrolyte species onto the surface of a solid or liquid material by means of electrostatic interaction. The thickness of the adsorbed layers can be tuned precisely in the nanometer range. Stable, semiconducting thin films are interesting research subjects. We use a conducting polymer, poly(p-phenylene vinylene) (PPV), in the preparation of a stable thin film via the LbL method. Cyclic voltammetry and electrochemical impedance spectroscopy have been used to characterize the ionic conductivity of the PPV multilayer films. The ionic conductivity of the films has been found to be dependent on the polymerization temperature. The film conductivity can be fitted to a modified Randle's circuit. The circuit equivalent calculations are performed to provide the diffusion coefficient values.

Preparation parameter development for layer-by-layer assembly of Keggin-type polyoxometalates.

Polyoxometalates possess many useful properties for electrochemical catalysis. These molecule-size clusters can be assembled into thin films through the layer-by-layer method. In this study, we determined a cluster concentration range within which layer-by-layer (LbL) films have been successfully fabricated. We also find the influence of salt added to the deposition solutions. In an attempt to understand the self-assembly process at the molecular level, thermodynamic arguments, derived from complexation between nanoscale particles and oppositely charged polyelectrolyte chains, have been employed to interpret the adsorption of polyoxometalate clusters onto a cationic polymer layer. The scaling results describe the contact mode between a polymer chain and a cluster. The assembly can be visualized with assistance by understanding the contact between the polymer chain and the cluster.