Research on Classification of Wild Fungi Based on Improved Resnet50 Network

Qian, Jiaxin; Yu, Pengfei; Li, Haiyan; Li, Hongsong

doi:10.1109/icivc52351.2021.9526929

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

Section: A Pendahuluanunclassified

“…Pada[17], ResNet50 digunakan untuk deteksi logo dan pengenalan merek dagang. Pada[18], ResNet50 digunakan untuk mengidentifikasi spesies jamur liar dan mengurangi terjadinya keracunan. Pada[19], ResNet50 digunakan untuk pengenalan ekspresi wajah dengan menambahkan tiga lapisan konvolusi sehingga fitur tingkat rendah dan tinggi dapat diekstraksi.Kontribusi dari penelitian ini adalah untuk melihat bagaimana metode fine tuning bekerja pada kedua model network, yaitu VGG16 dan ResNet50.…”

unclassified

See 1 more Smart Citation

Transfer learning pada Network VGG16 dan ResNet50

Muhammad

Arimurthy

Chahyati

2023

ijcs

View full text Add to dashboard Cite

Transfer Learning adalah prinsip yang digunakan pada neural network dengan tujuan membantu pelatihan pada data yang sedikit, mempercepat waktu dan meningkatkan performa pelatihan. Salah satu metode transfer learning adlaah fine tuning. Pada metode tersebut, melakukan pembekuan pada sejumlah layer pada model network yang dilatih sebelumnya dan melakukan pelatihan pada lapisan yang lainnya dan pada lapisan feature extractor. Pada penelitian ini akan dilihat salah satu metode transfer learning pada model network VGG6 dan ResNet50, yaitu fine tuning, dengan melakukan pembekuan dengan jumlah yang lapisan berbeda pada masng-masing model. Kemudian pada kedua model tersebut dilihat kinerja dan akurasinya pada saat pelatihan dan pengujian

show abstract

Section: A Pendahuluanunclassified

unclassified

Transfer learning pada Network VGG16 dan ResNet50

Muhammad

Arimurthy

Chahyati

2023

ijcs

View full text Add to dashboard Cite

show abstract

“…Because the categories contained in the training set and the test set are di erent, and the manifold structure of the image feature space and the semantic feature space is inconsistent, this type of method often has problems such as projection domain drift, mapping bias, and pivot points. To alleviate the above problems, this paper studies the problem of zero-sample image recognition of edible mushrooms with the help of category hierarchy relationship, graph convolutional neural network, and reversible generative model [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

A Small Sample Recognition Model for Poisonous and Edible Mushrooms based on Graph Convolutional Neural Network

Zhu

Pan

Wang

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The automatic identification of disease types of edible mushroom crops and poisonous crops is of great significance for improving crop yield and quality. Based on the graph convolutional neural network theory, this paper constructs a graph convolutional network model for the identification of poisonous crops and edible fungi. By constructing 6 graph convolutional networks with different depths, the model uses the training mechanism of graph convolutional networks to analyze the results of disease identification and completes the automatic extraction of the disease characteristics of the poisonous crops by overfitting problem. During the simulation, firstly, the relevant PlantVillage dataset is used to obtain the pretrained model, and the parameters are adjusted to fit the dataset. The network framework is trained and parameterized with prior knowledge learned from large datasets and finally synthesized by training multiple neural network models and using direct averaging and weighting to synthesize their predictions. The experimental results show that the graph convolutional neural network model that integrates multi-scale category relationships and dense links can use dense connection technology to improve the representation ability and generalization ability of the model, and the accuracy rate generally increases by 1%–10%. The average recognition rate is about 91%, which greatly promotes the ability to identify the diseases of poisonous crops.

show abstract

Image Classification of Wild Mushroom Using Swin Transformer by Object Positioning

Zhang

Yang

et al. 2023

2023 IEEE 3rd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA)

View full text Add to dashboard Cite

Research on Classification of Wild Fungi Based on Improved Resnet50 Network

Cited by 4 publications

References 4 publications

Transfer learning pada Network VGG16 dan ResNet50

Transfer learning pada Network VGG16 dan ResNet50

A Small Sample Recognition Model for Poisonous and Edible Mushrooms based on Graph Convolutional Neural Network

Image Classification of Wild Mushroom Using Swin Transformer by Object Positioning

Contact Info

Product

Resources

About