Lightweight AI identifies tree species from bark photos on smartphones
BarkNet-Lite: A Lightweight Texture and Colour Network with the BarkBD Benchmark for Bark-Based Tree Species Recognition in Bangladesh
Computer Vision and Pattern Recognition
Summary
Recognizing tree species helps keep track of forests and wildlife but usually needs expert knowledge. The authors created a large collection of bark photos from Bangladesh and built a small but smart computer program called BarkNet-Lite that can learn to recognize trees from these pictures without needing big pre-trained models. Their program performs almost as well as bigger models and works quickly on regular smartphones. They also confirmed the program makes its decisions by looking at bark patterns, not the background.
tree species recognitionbark texturemachine learningdeep neural networksmartphone imagingtexture analysiscolour pathwaytransfer learningGrad-CAMforest monitoring
Authors
Aroshi Ali, Saad Ahmed, Md. Khalid Syfullah
Abstract
Tree species recognition supports forest inventory and biodiversity monitoring but still depends on scarce taxonomic expertise. Bark is visible year-round at ground level, yet bark recognition has concentrated on temperate floras and on large ImageNet-pre-trained backbones. We address both gaps. First, we release BarkBD, a bark dataset for Bangladesh: 14,258 uncropped smartphone photographs of 20 native species across four districts and three weather conditions, with a fixed stratified split. Second, we propose BarkNet-Lite, a 2.96M-parameter network trained from random initialisation, pairing a multi-scale texture pathway with a parallel colour-aware pathway. Over five seeds it reaches 96.64+-0.66%accuracyunderstrict single-image inference, within 2.3 points of nine ImageNet-pre-trained backbones fine-tuned under an identical protocol and within one seed-level standard deviation of the smallest ofthem, andtransfers to public benchmarks (95.86% on BarkVN-50, 92.85% on BarkNet 1.0). Grad-CAM, validated by faithfulness and weight-randomisation checks, confirms its decisions rest on bark structure rather than background. The exported single-precision model classifies one photograph in 15.34ms on a commodity smartphone.