Identification of herbarium specimen sheet components from high-resolution images using deep learning

Herbarium collections remain essential in the age of community science

The past decade has yielded more biodiversity observations from community science than the past century of traditional scientific collection. This rapid influx of data is promising for overcoming critical biodiversity data shortfalls, but we also have vast untapped resources held in undigitized natural history collections. Yet, the ability of these undigitized collections to fill data gaps, especially compared against the constant accumulation of community science data, remains unclear. Here, we compare how well community science (iNaturalist) observations and digitized herbarium specimens represent the diversity, distributions, and modeling needs of vascular plants in Canada. We find that, despite having only a third as many records, herbarium specimens capture more taxonomic, phylogenetic, and functional diversity and more efficiently capture species' environmental niches. As such, the digitization of Canada's 7.3M remaining specimens has the potential to more than quintuple our ability to model biodiversity. In contrast, it would require over 27M more iNaturalist observations to produce similar benefits. Our findings indicate that digitizing Earth's remaining herbarium specimens is likely an efficient, feasible, and potentially critical investment when it comes to improving our ability to predict and protect biodiversity into the future.

Enhancing computer image recognition with improved image algorithms

Advances in computer image recognition have significantly impacted many industries, including healthcare, security and autonomous systems. This paper aims to explore the potential of improving image algorithms to enhance computer image recognition. Specifically, we will focus on regression methods as a means to improve the accuracy and efficiency of identifying images. In this study, we will analyze various regression techniques and their applications in computer image recognition, as well as the resulting performance improvements through detailed examples and data analysis. This paper deals with the problems related to visual image processing in outdoor unstructured environment. Finally, the heterogeneous patterns are converted into the same pattern, and the heterogeneous patterns are extracted from the fusion features of data modes. The simulation results show that the perception ability and recognition ability of outdoor image recognition in complex environment are improved.

A novel automated label data extraction and data base generation system from herbarium specimen images using OCR and NER

Digital extraction of label data from natural history specimens along with more efficient procedures of data entry and processing is essential for improving documentation and global information availability. Herbaria have made great advances in this direction lately. In this study, using optical character recognition (OCR) and named entity recognition (NER) techniques, we have been able to make further advancements towards fully automatic extraction of label data from herbarium specimen images. This system can be developed and run on a consumer grade desktop computer with standard specifications, and can also be applied to extracting label data from diverse kinds of natural history specimens, such as those in entomological collections. This system can facilitate the digitization and publication of natural history museum specimens around the world.