Other methodologies, utilizing Red, Green, Blue (RGB) channel images, approached the problem as multi-class texture classification task consisted of two consecutive phases: representation and classification 22. 21 used a portable spectrometer to identify bark from tropical species. Prior to technological breakthroughs, taxonomists utilized these little-known bark traits as an auxiliary means of species identification. 20 visually inspected tropical trees and broadly categorized the patterns (e.g., deep/shallow fissured, scaly, and laminate). Limited studies on bark identification have focused on the terminology and description of visual patterns in the inner and outer bark 18. The challenges encountered in identification by leaves and flowers, have led several studies to exploit the benefit of using barks that persist throughout the season and are easy to access and process with their simple cylindrical shapes 17. Hence, owing to the non-rigid and three-dimensional nature of leaves and flowers, it is challenging to produce high-quality image data to train and evaluate machine learning models 16. However, the availability of these organs highly depends on the season, phenological changes, and height of the crown base, especially in tree species. In addition to conventional taxonomic approaches to identify plants, previous studies regarding automated plant identification have mainly focused on extracting visual features from either or both reproductive and vegetative organs 10, 11, 12, 13, 14, 15. Among the various fields where automation is being introduced, plant identification is one of the most vigorously studied areas with high demand owing to its easy accessibility, rich diversity, and increasing curiosity about natural creatures in urban life 9. Thus, an increasing number of studies propose automated identification systems based on rapidly advancing machine learning methods, to support both professionals and the public 4, 5, 6, 7, 8. There is also increasing concern that the number of professional and amateur taxonomists is persistently declining, and that the gap in taxonomic knowledge between professionals and the public is increasing 1, 2, 3. However, conventional identification workflows that manually distinguish key visual features are slow and error-prone because of the complexity and intraspecific variation in morphological traits 1. Species identification is a fundamental component in every discipline of biology to properly utilize, monitor, and protect highly diverse living organisms on Earth. Our methodologies and findings are potentially applicable to identify and visualize crucial traits of other plant organs. CNNs were also capable of predicting untrained species by 41.98% and 48.67% within the correct genus and family, respectively. The two models exhibited disparate quality in the diagnostic features: the old and less complex model showed more general and well-matching patterns, while the better-performing model with much deeper layers indicated local patterns less relevant to barks. Diagnostic keys matched with salient shapes, which were also easily recognized by human eyes, and were typified as blisters, horizontal and vertical stripes, lenticels of various shapes, and vertical crevices and clefts. CNNs could identify the barks of 42 species with > 90% accuracy, and the overall accuracies showed a small difference between the two models. Here, we trained two convolutional neural networks (CNNs) with distinct architectures using a large-scale bark image dataset and applied class activation mapping (CAM) aggregation to investigate diagnostic keys for identifying each species. However, ever since computer vision algorithms surpassed the identification ability of humans, an open question arises as to how machines successfully interpret and unravel the complicated patterns of barks. Previous studies regarding bark identification have mostly contributed quantitatively to increasing classification accuracy. There were several attempts to utilize leaves and flowers for identification however, bark also could be beneficial, especially for trees, due to its consistency throughout the seasons and its easy accessibility, even in high crown conditions. The significance of automatic plant identification has already been recognized by academia and industry.
0 Comments
Leave a Reply. |