Leaf Image Recognition Based on Bag of Features

Zhang, Yaonan; Cui, Jing; Wang, Zhaobin; Kang, Jianfang; Min, Yufang

doi:10.3390/app10155177

Cited by 28 publications

(15 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset created (MyDataset) is compared with four benchmark datasets which are: Flavia dataset, Swedish Leaf dataset, Mendeley Dataset (MD2020), and Folio dataset. Flavia dataset contains 1907 samples of 33 species of common native plants in Yangtze Delta, China [ 86 , 87 ]. All the leaf images in this dataset have no petioles.…”

Section: Methodsmentioning

confidence: 99%

A Novel Computer Vision Model for Medicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms

Oppong

Twum

Hayfron-Acquah

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Computer vision is the science that enables computers and machines to see and perceive image content on a semantic level. It combines concepts, techniques, and ideas from various fields such as digital image processing, pattern matching, artificial intelligence, and computer graphics. A computer vision system is designed to model the human visual system on a functional basis as closely as possible. Deep learning and Convolutional Neural Networks (CNNs) in particular which are biologically inspired have significantly contributed to computer vision studies. This research develops a computer vision system that uses CNNs and handcrafted filters from Log-Gabor filters to identify medicinal plants based on their leaf textural features in an ensemble manner. The system was tested on a dataset developed from the Centre of Plant Medicine Research, Ghana (MyDataset) consisting of forty-nine (49) plant species. Using the concept of transfer learning, ten pretrained networks including Alexnet, GoogLeNet, DenseNet201, Inceptionv3, Mobilenetv2, Restnet18, Resnet50, Resnet101, vgg16, and vgg19 were used as feature extractors. The DenseNet201 architecture resulted with the best outcome of 87% accuracy and GoogLeNet with 79% preforming the worse averaged across six supervised learning algorithms. The proposed model (OTAMNet), created by fusing a Log-Gabor layer into the transition layers of the DenseNet201 architecture achieved 98% accuracy when tested on MyDataset. OTAMNet was tested on other benchmark datasets; Flavia, Swedish Leaf, MD2020, and the Folio dataset. The Flavia dataset achieved 99%, Swedish Leaf 100%, MD2020 99%, and the Folio dataset 97%. A false-positive rate of less than 0.1% was achieved in all cases.

show abstract

Section: Methodsmentioning

confidence: 99%

A Novel Computer Vision Model for Medicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms

Oppong

Twum

Hayfron-Acquah

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Yangtze Delta of China with plants that are natural having species are represented by 1907 samples in the Flavia dataset [19][20]. There are no petioles on any of the leaf photos in this collection.…”

Section: A Flavia Datasetmentioning

confidence: 99%

A Review on Detection of Medical Plant Images

Rao

Kumar

Konda

2023

IJRITCC

View full text Add to dashboard Cite

Both human and non-human life on Earth depends heavily on plants. The natural cycle is most significantly influenced by plants. Because of the sophistication of recent plant discoveries and the computerization of plants, plant identification is particularly challenging in biology and agriculture. There are a variety of reasons why automatic plant classification systems must be put into place, including instruction, resource evaluation, and environmental protection. It is thought that the leaves of medicinal plants are what distinguishes them. It is an interesting goal to identify the species of plant automatically using the photo identity of their leaves because taxonomists are undertrained and biodiversity is quickly vanishing in the current environment. Due to the need for mass production, these plants must be identified immediately. The physical and emotional health of people must be taken into consideration when developing drugs. To important processing of medical herbs is to identify and classify. Since there aren't many specialists in this field, it might be difficult to correctly identify and categorize medicinal plants. Therefore, a fully automated approach is optimal for identifying medicinal plants. The numerous means for categorizing medicinal plants that take into interpretation based on the silhouette and roughness of a plant's leaf are briefly précised in this article.

show abstract

“…Mendeley medicinal leaf dataset consists of 1835 leaves that belong to 30 different species of plants, Roopashree and Anitha (2020). The Flavia dataset contains 1907 leaf images of 32 leaf species, and it is the most popular dataset in leaf recognition, Zhang et al (2020). D Leaf dataset consists of 1290 leaves that belong to 43 plant species, Tan et al (2018).…”

Section: Data Setsmentioning

confidence: 99%

A Color Space Blending With Deep Learning Networks in the Identification of Plant Leaves

Elizabeth¹,

Baulkani²

2022

PLANT ARCHIVES

View full text Add to dashboard Cite

Color is an important feature in applications like the detection of plants and diseases in plants. Deep learning networks utilize optimizers towards improving the accuracy of classification. Color space is treated as an extra dimension with which the image could be better classified. Hence a particular blending of classifier, optimizer and color space is expected to provide enhanced accuracy of classification. There are very rare cases of studies having examined the effect of color space with deep learning networks. Hence, it is motivated to study the role of color spaces. Leaf datasets available in literature have been utilized. Of the few tried networks, Inception V3 is found to perform better with optimizer Adam. Color space XYZ performed better than RGB in the above combination. It has also been tried to obtain majority voting among various optimizer combinations. This solution is also better with XYZ color space. Among the various datasets utilized, consistent performance has been observed with Flavia data set yielding superior classification accuracy.

show abstract

Leaf Image Recognition Based on Bag of Features

Cited by 28 publications

References 53 publications

A Novel Computer Vision Model for Medicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms

A Novel Computer Vision Model for Medicinal Plant Identification Using Log-Gabor Filters and Deep Learning Algorithms

A Review on Detection of Medical Plant Images

A Color Space Blending With Deep Learning Networks in the Identification of Plant Leaves

Contact Info

Product

Resources

About