Contact Us

For Marketing, Sales and Subscriptions Inquiries
2637 E Atlantic Blvd #43110
Pompano Beach, FL 33062

Conference List

Journal of Forests

June 2021, Volume 8, 1, pp 61-70

Classification and Recognition of Urban Tree Defects in a Small Dataset using Convolutional Neural Network, Resnet-50 Architecture, and Data Augmentation

Arjun Dixit


Yeong Nain Chi

Arjun Dixit 1 ,

Yeong Nain Chi 1 
  1. Department of Agriculture, Food and Resource Sciences, University of Maryland Eastern Shore Princess Ann, MD, USA. 1

Pages: 61-70

DOI: 10.18488/journal.101.2021.81.61.70

Share :

Article History:

Received: 22 January, 2021
Revised: 16 February, 2021
Accepted: 05 March, 2021
Published: 08 April, 2021


Identifying hazard trees in urban setup is a time-consuming and tedious task and therefore concerned organizations and homeowner associations may not identify and fix such hazard trees in time. The purpose of this study was to identify the type of defects in the trees with the use of convolutional neural networks. This technology could speed up the process of identifying hazard trees. The study used the Image Processing Toolbox of MATLAB 2019a to process and classifies the images into one of the seven most prominent types of tree defects. The CNN used for this classification was ResNet-50. The Tree Defects dataset was prepared from images from publicly available sources. Further, the accuracy of the classification of these images into each of the defect categories was tested by obtaining a confusion matrix. The performance of ResNet-50 architecture was compared on three more publicly available and common research datasets Caltech101, Flower, and Dogs. The novel Tree Defects dataset was very small and had only 298 images. For its effectiveness on smaller datasets, ResNet-50 architecture was used along with data augmentation of tree defects images by rotating them 90-degrees clockwise and anti-clockwise. The effect of the proportion of the training dataset on model performance was also evaluated by training the model on 70%, 80%, and 90% of the total images in the dataset. The augmented Tree Defects dataset had 894 images. The model performance improves by 43.56% on the augmented Tree Defects dataset. The augmented model achieved the highest classification accuracy of 91.48%.
Contribution/ Originality
This study is one of the very few studies that have investigated the ways to find an image classification model that delivers high accuracy on smaller datasets. Mostly, a machine learning model is believed to perform better on vast datasets but building large datasets is costly and time-consuming.


Convolutional neural network, MATLAB, Image classification, Urban tree defect identification, Deep learning, ResNet-50, Small dataset, Data augmentation.


[1]          L. G. Nachtigall, R. M. Araujo, and G. R. Nachtigall, "Classification of apple tree disorders using convolutional neural networks," presented at the 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), 2016.

[2]          H. Al Hiary, A. S. Bani, M. Reyalat, M. Braik, and Z. ALRahamneh, "Fast and accurate detection and classification of plant diseases," International Journal of Computer Applications, vol. 17, pp. 31–38, 2011. Available at:

[3]          W. Tan, C. Zhao, and H. Wu, "Intelligent alerting for fruit-melon lesion image based on momentum deep learning," Multimedia Tools and Applications, vol. 75, pp. 16741–16761, 2015. Available at:

[4]          T. He, Y. Liu, Y. Yu, Q. Zhao, and Z. Hu, "Application of deep convolutional neural network on feature extraction and detection of wood defects," Measurement, vol. 152, p. 107357, 2020. Available at:

[5]          A. Albert, J. Kaur, and M. C. Gonzalez, "Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale," in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2017, pp. 1–10.

[6]          M. A. F. Azlah, L. S. Chua, F. R. Rahmad, F. I. Abdullah, and S. R. Wan Alwi, "Review on techniques for plant leaf classification and recognition," Computers, vol. 8, p. 77, 2019. Available at:

[7]          A. Khosla, J. Nityananda, Y. Bangpeng, and L. Fei-Fei, "Novel dataset for fine-grained image categorization," presented at the First Workshop on Fine-Grained Visual Categorization (FGVC), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, 2011.

[8]          L. Fei-Fei, R. Fergus, and P. Perona, "Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories," presented at the 2004 Conference on Computer Vision and Pattern Recognition Workshop, 2005.

[9]          A. Kaushik, "Understanding ResNet50 architecture. OpenGenus IQ: Learn Computer Science. Retrieved from:," 2020.

[10]        P. Nahar, S. Tanwani, and N. S. Chaudhari, "Fingerprint classification using deep neural network model Resnet50," International Journal of Research and Analytical Reviews, vol. 5, pp. 1521–1535, 2018.

[11]        A. Sachan, "Detailed guide to understand and implement ResNets. CV-Tricks.Com. Retrieved from:," 2019.

[12]        J. Vogt, R. J. Hauer, and B. C. Fischer, "The costs of maintaining and not maintaining the urban forest: A review of the urban forestry and arboriculture literature," Arboriculture & Urban Forestry, vol. 41, pp. 293-323, 2015.

[13]        R. W. Klein, A. K. Koeser, R. J. Hauer, G. Hansen, and F. J. Escobedo, "Risk assessment and risk perception of trees: A review of literature relating to arboriculture and urban forestry," Arboriculture & Urban Forestry, vol. 45, pp. 23-33, 2019. Available at:

[14]        M. A. van Haaften, M. P. M. Meuwissen, C. Gardebroek, and J. Kopinga, "Trends in financial damage related to urban tree failure in the Netherlands," Urban Forestry & Urban Greening, vol. 15, pp. 15–21, 2016. Available at:


Google Scholor ideas Microsoft Academic Search bing Google Scholor


This work is supported by the USDA National Institute of Food and Agriculture, McIntire Stennis project [Accession No. 1019401].

Competing Interests:

The authors declare that they have no competing interests.


All authors contributed equally to the conception and design of the study.

Related Article

( 1 ) Characterization and Classification of Cropland-Soils Affected by Erosion in Igbudu Ikwo, Southeastern Nigeria
( 2 ) Classification and Recognition of Urban Tree Defects in a Small Dataset using Convolutional Neural Network, Resnet-50 Architecture, and Data Augmentation
( 4 ) Urban Area - Review of Protective Forest Management
( 5 ) Suitability of Temperate and Tropical Crossbred Dairy Cattle under Peri-Urban Production System in Bangladesh
( 7 ) Tree Species Diversity and Productivity Relationship in the Central Region of Bangladesh
( 8 ) Chemical Analysis of Acacia Ehrenbergiana (Salam) Tree Fruits (Seed and Pods) As Dry Season Supplement For Livestock in Arid and Semi –Arid Lands of Sudan
( 9 ) A Suction Trap for Sampling Aphids and Aphidophagous Insects in Pecan Trees
( 10 ) Variation of Wood Density in Tropical Rainforest Trees
( 11 ) Diversity and Growth Characteristics of Tree Species in the Botanical Gardens, University of Ibadan, Nigeria
( 12 ) Sooty Mold on Lemon Trees - First Recording from El-Beida City, Libya
( 13 ) Carbon Sequestration Assessment of Selected Campus Champion Trees
( 16 ) Small-Scale Milk Processing, Utilization and Marketing of Traditional Dairy Products in Bahir Dar Zuria and Mecha Districts, Northwestern Ethiopia
( 17 ) Comparative Analysis of Technical Efficiencies of Smallholder Vegetable Farmers with and Without Credit Access in Swazil and the Case of the Hhohho Region
( 18 ) Investigating Constraints to Poultry Management Practices among Smallholder Farmers in Benue State, Nigeria
( 21 ) Storage Stability of Intermediate Moisture Cauliflower Brassica Oleracea, Var, Botrytis Cabbage Brassica Oleracea, Var, Capitata Using Radiation as Hurdle Technology
( 22 ) Maximizing the Productivity of Olives by Using Some Materials and Its Impacts on the Quality Indices of Picual Olive Oil
( 23 ) Description of Immature Stages of the Brown Dog Tick Rhipicephalus Sanguineus (Acari: Ixodidae) Using Scanning Electron Microscopy
( 24 ) Effect of Using Different Pre-Storage Warming Times on Hatchability of White Hisex Breeders’ Eggs
( 25 ) Effect of Temperature and Time on the Physical Properties of Bread Produced from Wheat – Cocoyam Flour Using Response Surface Methodology
( 26 ) Runoff Response to Climate Variability: An Analysis of Thika River Basin in Kenya Using Hydrological Simulation Model (Hysim)
( 27 ) Forecasting Goat Milk Production in Turkey Using Artificial Neural Networks and Box-Jenkins Models
( 28 ) Modelling and Optimization of Rice (Oryza sativa L.) Paddy Pre-Treatments for Optimum Chemical Property using Response Surface Methodology