Identifying and extracting bark key features of 42 tree species using convolutional neural networks and class activation mapping

Abstract

The significance of automatic plant identification has already been recognized by academia and industry. 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. Previous studies regarding bark identification have mostly contributed quantitatively to increasing classification accuracy. 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. 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. CNNs could identify the barks of 42 species with > 90% accuracy, and the overall accuracies showed a small difference between the two models. 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. 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. CNNs were also capable of predicting untrained species by 41.98% and 48.67% within the correct genus and family, respectively. Our methodologies and findings are potentially applicable to identify and visualize crucial traits of other plant organs.

Plant and Disease Recognition Based on PMF Pipeline Domain Adaptation Method: Using Bark Images as Meta-Dataset

“…To test the meta-trained model, we introduced several publicly available image datasets in agriculture and forestry [ 46 , 47 , 48 , 49 , 50 ] to explore the performance of the FSL model on datasets from the same domain or different domains. We processed these datasets into meta-datasets with the following steps: (1) Remove images with high similarity or ambiguous features.…”

Automated Identification of Tree Species by Bark Texture Classification Using Convolutional Neural Networks

“…Through this method of 3D based technology accuracy ranges between 83% and 100% is obtained for different tree species. Application of class activation mapping is seen in [13], where two convolutional neural networks with different architectures are proposed to classify 42 species of trees and achieve an accuracy above 90%. Class activation mapping(CAM) enables modifications in some parameters of CNN architecture and highlights the influential regions used for the prediction purpose.…”

CentralBark Image Dataset and Tree Species Classification Using Deep Learning

“…Some of these methods include Gabor filter banks as proposed by Chi et al [5]; co-occurrence matrices; histogram and auto-correlation methods, as applied by Wan et al [6]; and the Grey-Level Co-occurrence Matrix with Long Connection Length Emphasis, as employed by Song et al [7]. Newer studies, namely Kim et al [8], have used state-of-the-art computer-vision class activation mapping (CAM) to differentiate and classify bark patterns and further understand the nested groups of parameters in CNNs. Other studies have added color features, such as Wan et al [6], or utilized handcrafted features, such as the shape, color, structure, and orientation of bark with the help of Canny filters, hue histograms, and Gabor filters, as proposed by Ratajczak et al [9].…”