Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks

Abstract

BackgroundThe current state-of-the-art for field wood identification to combat illegal logging relies on experienced practitioners using hand lenses, specialized identification keys, atlases of woods, and field manuals. Accumulation of this expertise is time-consuming and access to training is relatively rare compared to the international demand for field wood identification. A reliable, consistent and cost effective field screening method is necessary for effective global scale enforcement of international treaties such as the Convention on the International Trade in Endagered Species (CITES) or national laws (e.g. the US Lacey Act) governing timber trade and imports.ResultsWe present highly effective computer vision classification models, based on deep convolutional neural networks, trained via transfer learning, to identify the woods of 10 neotropical species in the family Meliaceae, including CITES-listed Swietenia macrophylla, Swietenia mahagoni, Cedrela fissilis, and Cedrela odorata. We build and evaluate models to classify the 10 woods at the species and genus levels, with image-level model accuracy ranging from 87.4 to 97.5%, with the strongest performance by the genus-level model. Misclassified images are attributed to classes consistent with traditional wood anatomical results, and our species-level accuracy greatly exceeds the resolution of traditional wood identification.ConclusionThe end-to-end trained image classifiers that we present discriminate the woods based on digital images of the transverse surface of solid wood blocks, which are surfaces and images that can be prepared and captured in the field. Hence this work represents a strong proof-of-concept for using computer vision and convolutional neural networks to develop practical models for field screening timber and wood products to combat illegal logging.

North American Hardwoods Identification Using Machine-Learning

“…The InceptionV4_ResNetV2 convolutional neural network (CNN) model used in this study to classify 10 North American hardwoods species and was based on the work of [11]. The reason for using this CNN model was due to its image classification performance on the ImageNet dataset (0.953 top-5 accuracy in 1000 classes) and due to the smaller number of trainable parameters (3 times less) compared to prior research that used VGG16 architecture [12]. High definition images of the wood samples were resized to 299 × 299 × 3 (width × height × color-channels), which was the default input size for this CNN.…”

Maize-PAS: Automated Maize Phenotyping Analysis Software using Deep Learning

“…A deep-learning-based convolutional neural network (CNN) and Long Short Term Memory (LSTM) framework aiming at plant classification is proposed and shows its benefits over hand-crafted image analysis [13]. To combat illegal logging, a series of CNN classification models are presented to identify the woods of 10 species in [14]. Based on CNN, a pipeline to detect regions containing flowering panicles and estimate heading date of paddy rice is introduced in [15].…”

Res-WGAN: Image Classification for Plant Small-scale Datasets

“…This task requires a great deal of expertise; thus, classification becomes more difficult when rare plants are involved. Recently, remarkable progress has been made toward identifying various categories of plant images based on deep learning [2][3][4][5]. Convolutional neural network (CNN) is a typical classification model [6].…”