IJIGSP Vol. 17, No. 5, 8 Oct. 2025
Cover page and Table of Contents: PDF (size: 905KB)
PDF (905KB), PP.26-41
Views: 0 Downloads: 0
Agriculture, Soil Image, Soil Classification, CNN, ResNet50, InceptionV3, MobileNetV2, Machine Learning
Soil image classification plays a crucial role in agricultural and environmental practices. Traditional methods of soil classification often involve manual labor, which can be time-consuming and prone to human error. Recent advances in computer vision and machine learning have opened new horizons for automating this classification process. This research paper presents a comprehensive study and evaluates the performance of four convolutional neural network (CNN) architectures a custom CNN, ResNet50, InceptionV3, and MobileNetV2 on a custom soil image dataset comprising 1800 labelled images across four soil classes such as Black, Laterite, Red and White. The dataset created using smartphone camera to captured images under varying natural conditions. The objective of this work is to explore the effectiveness and accuracy of different machine learning algorithms used in categorizing soil types based on visual data. Each model’s performance is evaluated in terms of classification accuracy, precision, recall, and F1-score. Results indicate that ResNet50 achieves the highest accuracy 97.3%, followed closely by MobileNetV2 94.7%. The custom CNN, while computationally efficient, achieved 88.2%. We conclude that transfer learning with deep CNNs is highly effective for soil classification, and MobileNetV2 is a strong recommended for mobile applications. The comparative analysis demonstrates their effectiveness in distinguishing between different soil types, textures, and compositions. It also highlights how important it is to select the appropriate CNN architectures for certain tasks related to soil classification. This work belongs to the increasing collection of information at the interface between soil science and computer vision. It offers a strategy to apply sophisticated deep learning-based algorithms to assess soil type more reliably and effectively, serving as a springboard for future research in the field of soil image analysis and classification.
Girish D. Chate, S. S. Bhamare, "Classification of Soil Images Using Convolutional Neural Network", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.17, No.5, pp. 26-41, 2025. DOI:10.5815/ijigsp.2025.05.03
[1]D. Lal and B. Shukla, Principles of Soil Science, Himalaya Publishing House, 2014.
[2]A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105, 2012.Dfdf
[3]P. Sharma and S. Mukherjee, "Smartphone-based real-time soil classification using machine learning," Computers and Electronics in Agriculture, vol. 160, pp. 24–31, 2019.
[4]S. T. Dey, A. K. Sinha, and M. K. Ghosh, "Deep learning for soil classification: A review," Artificial Intelligence in Agriculture, vol. 5, pp. 107–118, 2021.
[5]K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 770–778.
[6]C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the Inception architecture for computer vision," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 2818–2826.
[7]M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted residuals and linear bottlenecks," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 4510–4520.
[8]R. Singh, A. Pandey, and S. Tripathi, "Soil texture classification using convolutional neural network," Procedia Computer Science, vol. 167, pp. 528–536, 2020.
[9]M. Ahmad, S. Hussain, F. Ahmed, and I. Mehmood, "Soil type classification using deep learning," Computers and Electronics in Agriculture, vol. 189, p. 106390, 2021.
[10]J. Pujari, R. Yakkundimath, and A. Byadgi, "Soil fertility prediction using machine learning and deep learning techniques," Procedia Computer Science, vol. 171, pp. 571–580, 2020.
[11]M. S. Hossain, R. R. Islam, and M. H. Kabir, "Deep learning-based soil classification using inception architectures," in Proc. Int. Conf. Sustainable Technologies for Industry 4.0 (STI), Dhaka, Bangladesh, 2019, pp. 1–5.
[12]B. Maji and C. Chakraborty, "MobileNet-based real-time soil classification on handheld devices," Journal of Ambient Intelligence and Humanized Computing, vol. 13, pp. 4075–4086, 2022.
[13]Girish D. Chate and S. S. Bhamare, “Comparative Analysis of Deep Learning Techniques for Soil Image Classification,” International Journal of Computer Sciences and Engineering, Vol.13, Issue.4, pp. 15-22, April 2025.
[14]J. Shorten and T. M. Khoshgoftaar, "A survey on image data augmentation for deep learning," Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019.
[15]Barman U, Choudhury RD (2020) Soil texture classification using multi-class support vector machine. Inf Process Agric 7(2):318–332.
[16]Chandan and Thakur R (2018) Recent Trends of Machine Learning in Soil Classification: A Review. International Journal of Computational Engineering Research, 25–32.
[17]Aziz MM, Ahmed DR, Ibrahim BF (2016) Determine the pH. of soil by using neural network based on Soil’s colour. Int J Advanced Res Comput Sci Software Eng 11:51–54.
[18]Barman U, Choudhury RD, Talukdar N, Deka P, Kalita I, Rahman N (2018) Predication of soil pH using HSI colour image processing and regression over Guwahati, Assam, India. Journal of Applied and Natural Science 10(2):805–809
[19]Ajdadi FR, Gilandeh YA, Mollazade K, Hasanzadeh RPR (2016) Application of machine vision for classification of soil aggregate size. Soil Tillage Res 162:8–17.
[20]Zhang X, Younan NH, King RL (2003) Soil texture classification using wavelet transform and Maximum Likelihood Approach. 7929–7931.
[21]Chung SO, Cho KH, Cho JW, Jung KY, Yamakawa T (2012) Soil texture classification algorithm using RGB characteristics of soil images. J Fac Agric Kyushu Univ 57:393–397.
[22]Sofou A, Evangelopoulos G, Maragos P (2005) Soil image segmentation and texture analysis: a computer vision approach. Geoscience and Remote Sensing Letters 2(4):394–398.
[23]Honawad PSK, Chinchali PSS, Pawar PK, Deshpande PP (2017) Soil Classification and Suitable Crop Prediction. 25–29
[24]de O. Morais PA, Souza DM, de M. Carvalho MT, Madari BE, de Oliveira AE (2019) Predicting soil texture using image analysis. Microchem. J. 146:455–463.
[25]Maniyath SR, Hebbar R, Akshatha KN, Architha LS, Rama Subramoniam S (2018) Soil color detection using Knn classifier. Proc. - 2018 Int. Conf. Des. Innov. 3Cs Comput. Commun.Control. ICDI3C 2018:52–55.
[26]Gurubasava,Mahantesh SD (2018) Analysis of Agricultural soil pHusingDigital Image Processing. 6, 1812–1816.
[27]Vinay Kumar, Binod Kumar Vimal, Rakesh Kumar, Rakesh Kumar, Mukesh Kumar, "Determination of soil pH by using digital image processing technique," Journal of Applied and Natural Science, vol. 6, no. 1, pp. 14-18, 2014.
[28]Pravat Kumar Shit, Gouri Sankar Bhunia, Ramkrishna Maiti, “Soil crack morphologyanalysis using image processing techniques” published Springer International PublishingSwitzerland 2015.
[29]K.Srunitha, S.Padmavathi, “Performance of SVM classifier for image-based soil classification”, IEEE, 2016.
[30]C.S.ManikandaBabu, M.Arun Pandian, “Determination of Physical and Chemical Characteristics of Soil Using Digital Image Processing”, International Journal of Emerging Technology in Computer Science & Electronics (IJETCSE) ISSN: 0976-1353 Volume 20 Issue 2 – FEBRUARY 2016.
[31]Umesh Kamble, Pravin Shingne, Roshan Kankrayane, Shreyas Somkuwar, Prof.Sandip Kamble, “Testing of Agriculture Soil by Digital Image Processing”, IJSRD - International Journal for Scientific Research & Development| Vol. 5, Issue 01, 2017 | ISSN (online): 2321-0613.
[32]Gurubasava, Mahantesh S.D, “Analysis of Agricultural soil pH using Digital Image Processing”, International Journal of Research in Advent Technology, Vol.6, No.8, August 2018 E-ISSN: 2321-9637.
[33]Priyanka Dewangan, Vaibhav Dedhe, “Soil Classification Using Image Processing and Modified SVM Classifier”, International Journal of Trend in Scientific Research and Development, Vol-2, Issue-6, Sep-Oct 2018 ISSN No: 2456-6470.
[34]Utpal Barman, Ridip Dev Choudhury, “Prediction of Soil pH using Smartphone based Digital Image Processing and Prediction”, https://doi.org/10.26782/jmcms.2019.04.00019ISSN (Online): 2454 -7190.
[35]T. Abimala 1, S. Flora Sashya 2, K. Sripriya,” Soil Classification & Crop Suggestion based on HSV, GLCM, Gabor Wavelet Techniques and Decision Tree Classifier in Image Processing”.
[36]Pavan Patil and Virendra Panpati, “Crop Prediction System using Machine Learning Algorithms", IRJET, Volume-07 Issue-02, Feb 2020.
[37]Mrs. N. Saranya, Ms. A. Mythili, “Classification of Soil and Crop Suggestion using Machine Learning Techniques”, Published by: International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181 Vol. 9 Issue 02, February-2020.
[38]Utpal Barman, Ridip Dev Choudhury, “Soil texture classification using multi class support vector machine”, https://doi.org/10.1016/j.inpa.2019.08.001.
[39]SkAlZaminur Rahman, Kaushik Chandra Mitra S.M. MohidulIslam (2018),"Soil classification using Machine Learning Methods and Crop Suggestion based on Soil Series”.
[40]Anna Chlingaryan, Salah Sukkarieh, Brett Whelan, "Machine learning approach for crop yield prediction and nitrogen status estimation in precision agriculture: A review”, Computers and Electronics in Agriculture, Volume 151, 2018, Pages 61-69, ISSN 0168-1699.
[41]Ashok Tatapudi, P Suresh Varma, "Prediction of Crops based on Environmental Factors using IoT & Machine Learning Algorithms”, International Journal of Innovative Technology and Exploring Engineering, ISSN: 2278-3075, Volume-9 Issue-1, November 2019.