Multi-Fusion Approach for Wood Microscopic Images Identification Based on Deep Transfer Learning

Zhu, Meng; Wang, Jincong; A-chuan, Wang; Ren, Hongxiang; Emam, Mahmoud

doi:10.3390/app11167639

Cited by 10 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of this method are better than other algorithms on FVC2002 DB1 data set and NIST SD4 data set [14]. Zhu M uses the Faster R-CNN algorithm with high detection accuracy to identify wood species to regulate the wood trade market, and the experimental results show that the Faster R-CNN algorithm can accurately identify microscopic images of wood in 77 [15]. Due to the superiority of Faster R-CNN algorithm over other algorithms in terms of detection accuracy.…”

Section: Introductionmentioning

confidence: 95%

Identification Method of Top Plate Pallet of Underground Roadways in Coal Mines Based on Improved Faster R-CNN

Ma,

Tian,

2024

Preprint

View full text Add to dashboard Cite

Pallets are an important feature in intelligent coal mine applications based on machine vision technology such as coal mine roadway roof monitoring and automatic equipment positioning, where whether pallets can be accurately identified is the key to such application technology. A roof pallet recognition method based on improved Faster R-CNN is designed. Firstly, the ResNet50 network with better feature extraction effect is selected to replace the VGG16 feature extraction network in the original Faster R-CNN model; Secondly, according to the aspect ratio of pallets and incomplete pallets, the candidate box size in the region suggestion network is optimized based on K-means++ clustering algorithm to fit the pallet size, so that the model can accurately locate the borders; finally, for the coal mine underground environment, low visibility and other problems that affect the pallet is difficult to be detected, the attention mechanism module is introduced in the feature extraction network ResNet50 to enhance the saliency of the pallet in the image and strengthen the attention of the network to the pallet, thus improving the efficiency and accuracy of pallet detection. In the simulated roadway, the AGV trolley is used to simulate the roadheader, and the tray image is collected by the airborne camera for the test. The proposed algorithm is compared with three classical algorithms. The experimental results show that the improved Faster R-CNN model has good robustness, and the average mean accuracy (mAP) of recognizing pallets is 92.53%, which is 7.59% higher than the original Faster R-CNN network.

show abstract

Section: Introductionmentioning

confidence: 95%

Identification Method of Top Plate Pallet of Underground Roadways in Coal Mines Based on Improved Faster R-CNN

Ma,

Tian,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…For these methods, the classifier algorithm requires complex data preprocessing to extract features to bring into the classifier for training. Although the use of CNN reduces the manual feature extraction process, low classification accuracy was often reported in many previous studies [20,21]. The application of traditional classifiers in combination with CNN for automatic recognition of tree species images has been less studied.…”

Section: Introductionmentioning

confidence: 99%

Leaves and Twigs Image Recognition Based on Deep Learning and Combined Classifier Algorithms

Sun

Zhou

et al. 2023

Forests

View full text Add to dashboard Cite

In recent years, the automatic recognition of tree species based on images taken by digital cameras has been widely applied. However, many problems still exist, such as insufficient tree species image acquisition, uneven distribution of image categories, and low recognition accuracy. Tree leaves can be used to differentiate and classify tree species due to their cognitive signatures in color, vein texture, shape contour, and edge serration. Moreover, the way the leaves are arranged on the twigs has strong characteristics. In this study, we first built an image dataset of 21 tree species based on the features of the twigs and leaves. The tree species feature dataset was divided into the training set and test set, with a ratio of 8:2. Feature extraction was performed after training the convolutional neural network (CNN) using the k-fold cross-validation (K-Fold–CV) method, and tree species classification was performed with classifiers. To improve the accuracy of tree species identification, we combined three improved CNN models with three classifiers. Evaluation indicators show that the overall accuracy of the designed composite model was 1.76% to 9.57% higher than other CNN models. Furthermore, in the MixNet XL CNN model, combined with the K-nearest neighbors (KNN) classifier, the highest overall accuracy rate was obtained at 99.86%. In the experiment, the Grad-CAM heatmap was used to analyze the distribution of feature regions that play a key role in classification decisions. Observation of the Grad-CAM heatmap illustrated that the main observation area of SE-ResNet50 was the most accurately positioned, and was mainly concentrated in the interior of small twigs and leaflets. Our research showed that modifying the training method and classification module of the CNN model and combining it with traditional classifiers to form a composite model can effectively improve the accuracy of tree species recognition.

show abstract

“…Zeng et al (2020) proposed a lightweight neural network based on MobilenetV2, which removed some redundant reverse residual blocks and reduced the channel expansion coefficient of the reverse residual block, greatly reducing the amount of calculation and parameters. Zhu et al. (2021) proposed a wood microscopic image classification method based on decomposition-aggregation network model, which combined image geometric transformation and Mixup data expansion technology.…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Sparse attention double-channel FCN network for numerical analysis tracheid features in larch

Zhang

Wang

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Understanding the macro-mechanical behavior of wood at the micro-scale is of great significance for the design of cell-wall-like composite materials and pulp papermaking. In order to predict tracheid mechanical properties and analyze its relationship with tracheid features, based on the FCN network model, a double-channel FCN network with sparse attention (D-SA-FCN) was designed by introducing the double-channel mechanism and the sparse attention mechanism. The features of tracheid of larch were extracted numerically and the data set was established by using the compression strength data, the gray level co-occurrence matrix, cell segmentation and geometric analysis. A feature analysis algorithm based on PCA and random forest was established to optimize the feature values. The training set accuracy of the D-SA-FCN network model reached 85.75% with the five-level mechanical property level according to the classification standard. The accuracy of the training model is 71.48% and 79.52% when the morphological and texture features are input respectively. The results show that texture features had a more significant impact on mechanics to a certain extent and the D-SA-FCN could reduce the computational complexity and improve the prediction accuracy.

show abstract

Multi-Fusion Approach for Wood Microscopic Images Identification Based on Deep Transfer Learning

Cited by 10 publications

References 12 publications

Identification Method of Top Plate Pallet of Underground Roadways in Coal Mines Based on Improved Faster R-CNN

Identification Method of Top Plate Pallet of Underground Roadways in Coal Mines Based on Improved Faster R-CNN

Leaves and Twigs Image Recognition Based on Deep Learning and Combined Classifier Algorithms

Sparse attention double-channel FCN network for numerical analysis tracheid features in larch

Contact Info

Product

Resources

About