Search results

This research project focuses on developing techniques and technologies for automatically identifying human faces from images in the situations where face sample collections in the database as well as in the input query images are “as is”, i.e. no standard data collection environment is available. The developed method can also be used in other biometric applications.

The specific method presented in this paper is called scale independent identification (SII). SII allows direct “comparison” between two images in terms of whether the two objects (e.g. faces) in the two images are the same object (i.e. the same individual). SII is developed by extensively using the matrix computation theory and in particular, the singular value decomposition theory.

It is found that almost all the existing methods in the literature or technologies in the market require that a normalization in scale be done before any identification processing. However, it is also found that normalization in scale not only adds additional processing complexity, but also may reduce the identification accuracy. In addition, it is difficult to anticipate an “optimal” scale in advance. The developed SII complements the existing methods in all these aspects.

The only limitation which is also the limitation for many other biometric identification methods is that each object (e.g. individual in human face identification) must have a sufficient number of training samples collected before the method works well.

SII is particularly suitable in law enforcement and/or intelligence applications in which it is difficult or impossible to collect data in a standard, “clean” environment.

The SII method is new, and the paper should be interesting to researchers or engineers in this area, and should also be interesting to companies developing any biometrics‐based identification technologies as well as government agencies.

Since the development of the COVID-19 vaccinations, questions surrounding race have been prominent in the literature on vaccine uptake. Early in the vaccine rollout, public health officials were concerned with the relatively lower rates of uptake among certain racial/ethnic minority groups. We suggest that this may also be patterned by racial/ethnic residential segregation, which previous work has demonstrated to be an important factor for both health and access to health care.

In this study, we examine county-level vaccination rates, racial/ethnic composition, and residential segregation across the U.S. We compile data from several sources, including the American Community Survey (ACS) and Centers for Disease Control (CDC) measured at the county level.

We find that just looking at the associations between racial/ethnic composition and vaccination rates, both percent Black and percent White are significant and negative, meaning that higher percentages of these groups in a county are associated with lower vaccination rates, whereas the opposite is the case for percent Latino. When we factor in segregation, as measured by the index of dissimilarity, the patterns change somewhat. Dissimilarity itself was not significant in the models across all groups, but when interacted with race/ethnic composition, it moderates the association. For both percent Black and percent White, the interaction with the Black-White dissimilarity index is significant and negative, meaning that it deepens the negative association between composition and the vaccination rate.

The analysis is only limited to county-level measures of racial/ethnic composition and vaccination rates, so we are unable to see at the individual-level who is getting vaccinated.

We find that segregation moderates the association between racial/ethnic composition and vaccination rates, suggesting that local race relations in a county helps contextualize the compositional effects of race/ethnicity.