The image recognition of urban greening tree species based on deep learning and CAMP-MKNet model

Sun, Xiaodong; Shi, Yongjun

doi:10.1016/j.ufug.2023.127970

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have employed complex techniques including computer vision, bilateral convolutional neural networks (CNNs), and machine learning methods, which can be challenging for ecologists to comprehend [5][6][7]. An efficient framework is crucial for species identification as it facilitates algorithmic development and automation in species recognition [8]. It should be capable in automation identification processes [9].…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Methodology for Plant Species Recognition Using Morphology of Leaves

Barhate,

Pathak,

Kumar Dubey

2023

AEJ

View full text Add to dashboard Cite

Plants play a crucial role in supporting all forms of life on Earth, not just humans but every living organism. Understanding the diverse range of plant species that surround us is essential due to their significance in various aspects of human life, including agriculture, the environment, medicine, cosmetics, and more. Advancements in machine learning and computer vision algorithms have opened possibilities for identifying different types of plant species, both within and across classes. Plant species detection typically involves several steps, such as image acquisition, feature extraction, categorization, and pre-processing. In this study, three datasets—namely Flavia, Swedish, and the intelligent computing laboratory (ICL) dataset—were chosen for experimentation purposes. For feature extraction, three different models were employed: k-nearest neighbour (KNN), naive Bayes (NB), and the visual geometry group (VGG)-16 model. These models were used to extract distinctive features such as shape, texture, venation, and margin from the plant images. A multiclass classification task was conducted to categorize the plant species. Among the models tested, the VGG-16 model consistently demonstrated superior performance in terms of accuracy. Specifically, when using the VGG-16 model, the obtained accuracies were 96.68% for the Flavia dataset, 97.65% for the Swedish dataset, and 96.11% for the ICL dataset.

show abstract