Scientia Silvae Sinicae ›› 2023, Vol. 59 ›› Issue (8): 133-140.doi: 10.11707/j.1001-7488.LYKX20210891
Yujie Miao,Shiping Zhu*,Jing Pu,Junxian Li,Lingkai Ma,Hua Huang
Received:
2021-12-18
Online:
2023-08-25
Published:
2023-10-16
Contact:
Shiping Zhu
CLC Number:
Yujie Miao,Shiping Zhu,Jing Pu,Junxian Li,Lingkai Ma,Hua Huang. Recognition of Furniture Wood Image Species Based on Convolutional Neural Networks[J]. Scientia Silvae Sinicae, 2023, 59(8): 133-140.
Table 1
Number of different wood image data"
检测类别 Detection category | 木材种类Wood species | 总数Total |
素材图像Wood images coated without wood wax oil | 红橡Quercus spp. | 724 |
榄仁木Terminalia spp. | 724 | |
栾叶苏Hymenaea cunrbaril | 739 | |
水曲柳Fraxinus mandshurica | 727 | |
涂饰木蜡油的木材图像Wood images coated with wood wax oil | 红橡Quercus spp. | 486 |
榄仁木Terminalia spp. | 480 |
Table 2
Learning results of different network models based on wood images coated without wood wax oil"
模型 Model | 一次迭代用时 Time in one iteration/s | 模型大小 The model size/M | 训练集 准确率 Training set accuracy (%) | 验证集 准确率 Validation set accuracy (%) |
SVM | 0.16 | — | 100.00 | 70.84 |
ANN | 1.58 | — | 100.00 | 76.33 |
AlexNet | 21.69 | 217 | 98.26 | 82.61 |
ResNet34 | 74.13 | 81.3 | 96.21 | 90.45 |
MobileNetV2 | 49.69 | 8.73 | 99.58 | 85.71 |
MobileNetV3 | 43.35 | 16.2 | 99.79 | 89.25 |
Table 3
Comparison of learning results of different parameter conditions in MobileNetV3 structure based on wood images coated without wood wax oil"
编号 No. | 学习方法 Learning method | 数据集划分比例 Partition ratio of the data set | 学习率 Learning rate | 一次迭代用时 Time in one iteration/s | 训练损失 Loss of training | 训练集准确率 Training set accuracy (%) | 验证集准确率 Validation set accuracy (%) |
1 | 全新学习 (训练集扩充) Transfer learning was not used (extended training set) | 6∶2∶2 | 0.01 | 45.78 | 0.065 2 | 97.99 | 87.93 |
2 | 0.001 | 44.45 | 0.005 3 | 99.79 | 89.25 | ||
3 | 0.000 1 | 43.35 | 0.005 9 | 99.78 | 83.86 | ||
4 | 2∶6∶2 | 0.01 | 14.51 | 0.015 0 | 99.44 | 82.08 | |
5 | 0.001 | 14.47 | 0.004 3 | 99.91 | 82.43 | ||
6 | 0.000 1 | 14.61 | 0.004 6 | 99.91 | 79.27 | ||
7 | 迁移学习 (训练集扩充) Transfer learning (extended training set) | 6∶2∶2 | 0.01 | 44.51 | 0.033 2 | 99.12 | 92.03 |
8 | 0.001 | 43.49 | 0.000 3 | 100.00 | 96.91 | ||
9 | 0.000 1 | 43.69 | 0.000 1 | 100.00 | 98.13 | ||
10 | 2∶6∶2 | 0.01 | 14.49 | 0.018 8 | 99.44 | 86.26 | |
11 | 0.001 | 14.49 | 0.000 5 | 100.00 | 91.13 | ||
12 | 0.000 1 | 14.53 | 0.000 1 | 100.00 | 91.70 | ||
13 | 迁移学习 (训练集未扩充) Transfer learning (the training set was not extended) | 6∶2∶2 | 0.01 | 10.86 | 0.031 4 | 98..97 | 90.05 |
14 | 0.001 | 10.88 | 0.000 1 | 100.00 | 95.54 | ||
15 | 0.000 1 | 10.91 | 0.000 1 | 100.00 | 96.56 | ||
16 | 2∶6∶2 | 0.01 | 3.64 | 0.039 4 | 98.97 | 78.65 | |
17 | 0.001 | 3.66 | 0.003 9 | 1 | 89.35 | ||
18 | 0.000 1 | 3.65 | 0.000 5 | 100.00 | 89.81 |
Table 5
Confusion matrix and classification performance of model"
样本集 Sample set | 预测类别 Prediction category | 分类性能 Classification performance | ||||||
红橡 Quercus spp. | 榄仁木 Terminalia spp. | 栾叶苏 Hymenaea cunrbaril | 水曲柳 Fraxinus mandshurica | 准确率 Precision(%) | 召回率 Recall(%) | F1(%) | ||
红橡Quercus spp. | 138 | 0 | 0 | 0 | 100.00 | 95.17 | 97.79 | |
榄仁木Terminalia spp. | 0 | 140 | 0 | 1 | 99.29 | 96.55 | 97.92 | |
栾叶苏Hymenaea cunrbaril | 5 | 3 | 133 | 7 | 89.86 | 89.86 | 89.86 | |
水曲柳Fraxinus mandshurica | 2 | 2 | 15 | 138 | 87.89 | 94.52 | 91.21 |
鲍 烈, 王曼韬, 刘江川, 等. 基于卷积神经网络的小麦产量预估方法. 浙江农业学报, 2020, 32 (12): 2244- 2252.
doi: 10.3969/j.issn.1004-1524.2020.12.16 |
|
Bao L, Wang M T, Liu J C, et al. Estimation method of wheat yield based on convolution neural network. Acta Agriculturae Zhejiangensis, 2020, 32 (12): 2244- 2252.
doi: 10.3969/j.issn.1004-1524.2020.12.16 |
|
陈宏伟, 宋魁彦. 木蜡油涂饰对家具表面视觉特性的影响研究. 家具与室内装饰, 2021, (4): 43- 45.
doi: 10.16771/j.cn43-1247/ts.2021.04.012 |
|
Chen H W, Song K Y. Research on the influence of wood wax coating on the visual characteristics of furniture surface. Furniture & Interior Design, 2021, (4): 43- 45.
doi: 10.16771/j.cn43-1247/ts.2021.04.012 |
|
陈龙现, 葛浙东, 罗 瑞, 等. 基于CNN的木材内部CT图像缺陷辨识. 林业科学, 2018, 54 (11): 127- 133.
doi: 10.11707/j.1001-7488.20181118 |
|
Chen L X, Ge Z D, Luo R, et al. Identification of CT image defects in wood based on convolution neural network. Scientia Silvae Sinicae, 2018, 54 (11): 127- 133.
doi: 10.11707/j.1001-7488.20181118 |
|
崔明光. 2019. 基于卷积神经网络的木材缺陷识别方法研究. 长春: 长春工业大学. | |
Cui M G. 2019. Research on wood defect recognition method based on convolutional neural network. Changchun: Changchun University of Technology.[in Chinese] | |
李 楠. 2018. 一种基于卷积神经网络的轻量级木材图像识别模型研究. 杭州: 浙江农林大学. | |
Li N. 2018. Research on lightweight wood image recognition model based on convolutional neural network. Hangzhou: Zhejiang A&F University.[in Chinese] | |
李鑫然, 李书琴, 刘 斌. 基于改进Faster R_CNN的苹果叶片病害检测模型. 计算机工程, 2021, 47 (11): 298- 304. | |
Li X R, Li S Q, Liu B. Apple leaf diseases detection model based on improved Faster R_CNN. Computer Engineering, 2021, 47 (11): 298- 304. | |
刘 英, 周晓林, 胡忠康, 等. 基于优化卷积神经网络的木材缺陷检测. 林业工程学报, 2019, 4 (1): 115- 120. | |
Liu Y, Zhou X L, Hu Z K, et al. Wood defect recognition based on optimized convolution neural network algorithm. Journal of Forestry Engineering, 2019, 4 (1): 115- 120. | |
吴茂贵, 郁明敏, 杨本法, 等. 2019. Python深度学习: 基于PyTorch. 北京: 机械工业出版社, 307. | |
Wu M G, Yu M M, Yang B F, et al. 2019. Python deep learning: based on PyTorch. Beijing: China Machine Press, 307.[in Chinese] | |
张瑞青, 李张威, 郝建军, 等. 基于迁移学习的卷积神经网络花生荚果等级图像识别. 农业工程学报, 2020, 36 (23): 171- 180.
doi: 10.11975/j.issn.1002-6819.2020.23.020 |
|
Zhang R Q, Li Z W, Hao J J, et al. Image recognition of peanut pod grades based on transfer learning with convolutional neural network. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36 (23): 171- 180.
doi: 10.11975/j.issn.1002-6819.2020.23.020 |
|
赵 畅, 黄艳辉, 卿兰庭. 木蜡油及其在木质家具中的应用进展. 林产工业, 2016, 43 (10): 11- 14.
doi: 10.3969/j.issn.1001-5299.2016.10.003 |
|
Zhao C, Huang Y H, Qing L T. Hard wax oil and progress of its application in wooden furniture. China Forest Products Industry, 2016, 43 (10): 11- 14.
doi: 10.3969/j.issn.1001-5299.2016.10.003 |
|
Barmpoutis P, Dimitropoulos K, Barboutis I, et al. Wood species recognition through multidimensional texture analysis. Computers and Electronics in Agriculture, 2018, 144, 241- 248.
doi: 10.1016/j.compag.2017.12.011 |
|
Fabijańska A, Danek M, Barniak J. Wood species automatic identification from wood core images with a residual convolutional neural network. Computers and Electronics in Agriculture, 2021, 181 (1): 105941. | |
Geus A R, da Silva S F, Gontijo A B, et al. An analysis of timber sections and deep learning for wood species classification. Multimedia Tools and Applications, 2020, 79 (45/46): 34513- 34529. | |
Han D M, Liu Q G, Fan W G. A new image classification method using CNN transfer learning and web data augmentation. Expert Systems with Applications, 2018, 95, 43- 56.
doi: 10.1016/j.eswa.2017.11.028 |
|
He K M, Zhang X Y, Ren S Q, et al. 2016. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. IEEE, 770-778. | |
He T, Lu Y, Jiao L C, et al. Developing deep learning models to automate rosewood tree species identification for CITES designation and implementation. Holzforschung, 2020, 74 (12): 1123- 1133.
doi: 10.1515/hf-2020-0006 |
|
Howard A, Sandler M, Chen B, et al. 2020. Searching for MobileNetV3. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South). IEEE, 1314-1324. | |
Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2012, 60 (6): 84- 90. | |
Martins J, Oliveira L S, Nisgoski S, et al. A database for automatic classification of forest species. Machine Vision and Applications, 2013, 24 (3): 567- 578.
doi: 10.1007/s00138-012-0417-5 |
|
Nisgoski S, de Oliveira A A, de Muñiz G I B. Artificial neural network and SIMCA classification in some wood discrimination based on near-infrared spectra. Wood Science and Technology, 2017, 51 (4): 929- 942.
doi: 10.1007/s00226-017-0915-8 |
|
Sandler M, Howard A, Zhu M L, et al. 2018. MobileNetV2: inverted residuals and linear bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. IEEE, 4510-4520. | |
Souza D V, Santos J X, Vieira H C, et al. An automatic recognition system of Brazilian flora species based on textural features of macroscopic images of wood. Wood Science and Technology, 2020, 54 (4): 1065- 1090.
doi: 10.1007/s00226-020-01196-z |
|
Wheeler E A, Baas P. Wood identification-a review. IAWA Journal, 1998, 19 (3): 241- 264.
doi: 10.1163/22941932-90001528 |
|
Zhao P, Cao J. Wood species identification using spectral reflectance feature and optimal illumination radian design. Journal of Forestry Research, 2016, 27 (1): 219- 224.
doi: 10.1007/s11676-015-0171-4 |
|
Zhao P. Robust wood species recognition using variable color information. Optik - International Journal for Light and Electron Optics, 2013, 124 (17): 2833- 2836.
doi: 10.1016/j.ijleo.2012.08.058 |
[1] | Jiandong Qi,Zhongtian Ma,Dehuai Zhang,Yun Tian. Wildlife Image Recognition in Miyun District Based on BS-ResNeXt-50 [J]. Scientia Silvae Sinicae, 2023, 59(8): 112-122. |
[2] | Quanfei Huang,Yanhui Huang,Ying Liu,Xinyu Lin. Preparation and Finishing Properties of Environmentally-Friendly and Fast-Drying Wood Wax Oil [J]. Scientia Silvae Sinicae, 2023, 59(7): 137-144. |
[3] | Yingwu Mao,Ying Guo,Wangfei Zhang,Yong Su,Yuan Guan. Tree Species Classification by Combining LiDAR, Hyperspectral Data and 3D-CNN Method [J]. Scientia Silvae Sinicae, 2023, 59(3): 73-83. |
[4] | Tongtong Li,Sujuan Guo,Yanhua Li. Identification of Chestnut Varieties Based on Digital Analysis of Leaf Morphology [J]. Scientia Silvae Sinicae, 2023, 59(3): 115-126. |
[5] | Huimin Feng,Kun Jin. Voiceprint Recognition of Male Nomascus hainanus Based on Convolutional Neural Network [J]. Scientia Silvae Sinicae, 2023, 59(1): 119-127. |
[6] | Wei Yue,Shiming Li,Zengyuan Li,Qingwang Liu,Yong Pang,Lin Si. Identification of Dominant Tree Species Based on Multi-Temporal Sentinel-2 Images and SNIC Segmentation Algorithm [J]. Scientia Silvae Sinicae, 2022, 58(9): 60-69. |
[7] | Nannan Yang,Yan Bai,Suyi Jiang,Chunmei Yang,Kaihong Xu. Recognition Method of Plate and Wood Based on ALexNet Optimaization [J]. Scientia Silvae Sinicae, 2022, 58(3): 149-158. |
[8] | Xin Peng,Hantang Wang,Chunhui Guo,Zhende Yang,Jing Zhou,Xue Wang,Zhirou Ding. EST-SSR Development and Cryptic Species Identification of the Invasive Gall-Causing Pest Leptocybe invasa (Hymenopetra: Eulophidae) [J]. Scientia Silvae Sinicae, 2021, 57(9): 140-151. |
[9] | Tuo He,Shoujia Liu,Yang Lu,Yonggang Zhang,Lichao Jiao,Yafang Yin. iWood: An Automated Wood Identification System for Endangered and Precious Tree Species Using Convolutional Neural Networks [J]. Scientia Silvae Sinicae, 2021, 57(9): 152-159. |
[10] | Yuequ Chen,Qingzhen Liu,Limei Li,Yang Zhang,Jiao Han,Yong'an Zhang. Screening and Identification of Antagonistic Streptomyces for Biocontrol of Poplar Canker [J]. Scientia Silvae Sinicae, 2021, 57(7): 92-100. |
[11] | Ziyu Zhao,Xiaoxia Yang,Hui Guo,Zhedong Ge,Yucheng Zhou. Recognition Method of Wood Macro- and Micro-Structure Based on Convolution Neural Network [J]. Scientia Silvae Sinicae, 2021, 57(6): 134-143. |
[12] | Lili Ren,Jing Tao,Haiwei Wu,Shixiang Zong,Chuanzhen Wang,De Hua,Juan Shi,Yizhou Liu,Youqing Luo. The First Discovery and Infective Characteristics of A Major Invasive Pest Hylurgus ligniperda (Coleoptera: Scolytidae) in China [J]. Scientia Silvae Sinicae, 2021, 57(5): 140-150. |
[13] | Qionglian Wan,Lianchun Wang,Quan Wang,Xingping Xu,Fan Su,Jing Zhao,Hong Cai. Molecular Identification and Disease Investigation of Trema levigata Witches'-Broom Phytoplasma [J]. Scientia Silvae Sinicae, 2021, 57(5): 195-201. |
[14] | Yutong Yang,Qingshuo Zhang,Yunlin Fu,Jing Sun. Components, Stability and Antioxidant Activity of Pigment from Dalbergia bariensis Heartwood [J]. Scientia Silvae Sinicae, 2021, 57(3): 126-134. |
[15] | Bo Liu,Yuejin Fu,Xingxia Ma,Yun Lu,Lin Wang. Relationship between Wood Species Selection and Biological Diseases of Ancient Building Wooden Components in Severe Wood Biological Diseases Area [J]. Scientia Silvae Sinicae, 2021, 57(12): 108-121. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||