Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64195
Volume:
10 |
5 |
May 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department Of Computer Science & Engineering
Guru Nanak Institute Of Technology
Department Of Computer Science & Engineering
Guru Nanak Institute Of Technology
Department Of Computer Science & Engineering
Guru Nanak Institute Of Technology
Department Of Computer Science & Engineering
Guru Nanak Institute Of Technology
Soil surface texture classification is an important aspect of agriculture and soil science because it influences soil properties such as water-holding capacity, aeration, and nutrient retention. Traditional soil texture classification methods generally depend on laboratory testing and images captured under controlled conditions, which are expensive, time-consuming, and difficult to apply in real-world agricultural environments. To overcome these limitations, this project proposes a scalable and efficient soil texture classification system using image processing techniques and Deep Neural Networks under Uncontrolled Field Conditions (UFC). The proposed system utilizes image segmentation, texture enhancement filters, and Convolutional Neural Networks (CNN) for accurate soil texture classification. Initially, image segmentation is performed to remove non-soil pixels from captured images. The segmented images are divided into smaller tiles to isolate relevant soil regions. Gabor filters are then applied to enhance hidden texture patterns within the soil images. Experimental analysis shows that Gabor filters perform better than Local Binary Patterns (LBP) for texture enhancement. Finally, the enhanced images are used to train CNN architectures such as VGG19 for classification purposes. The proposed framework is evaluated using various performance metrics and compared with existing soil texture classification methods. Among different CNN models, VGG19 achieved the best performance with high classification accuracy. The system provides a low-cost, scalable, and reliable solution for precision agriculture, soil management, environmental monitoring, and crop recommendation systems.
KEYWORDS
The Soil Texture Classification Using Deep Neural Networks project provides an efficient, scalable, and accurate solution for automated soil texture analysis under uncontrolled field conditions. The integration of image processing, Gabor filters, and CNN architectures such as VGG19 significantly improves classification accuracy compared to traditional soil analysis methods. The proposed framework reduces manual effort, minimizes laboratory dependency, and supports real-time agricultural applications. The system can be effectively used in precision agriculture, crop recommendation systems, environmental monitoring, and land management applications. The successful implementation of deep learning techniques demonstrates the potential of AI-based soil analysis systems for future smart agriculture solutions.
[1] A. Gerakis and B. Baer, “A computer program for soil textural classification,” Soil Sci. Soc. Amer. J., vol. 63, no. 4, pp. 807–808, Jul. 1999. [2] C. P. Fernandez-Illescas, A. Porporato, F. Laio, and I. Rodriguez-Iturbi, “The Eco hydrological role of soil texture in a water-limited ecosystem,” Water Resource. Res., vol. 37, no. 12, pp. 2863–2872, Dec. 2001. [3] Q. Xia, T. Rufty, and W. Shi, “Soil microbial diversity and composition: Links to soil texture and associated properties,” Soil Biol. Biochem., vol. 149, Oct. 2020. [4] K. Chakraborty and B. Mistri, “Importance of soil texture in sustenance of agriculture,” Eastern Geographer, vol. 21, no. 1, pp. 475–482, 2015. [5] K. H. Yusof et al., “Determination of soil texture using image processing technique,” in Proc. IEEE 18th Int. Colloq. Signal Process. Appl. (CSPA), 2022, pp. 178–181. [6] E.-O. Babalola, M. H. Asad, and A. Bais, “Soil Surface Texture Classification Using RGB Images Acquired Under Uncontrolled Field Conditions,” 2023. [7] R. Prabavathi and B. J. Chelliah, “An Optimized Hybrid Soil Texture Classification Model using Stacked Sparse Autoencoder,” 2023. [8] M. S. Natsir et al., “Classification of Soil Fertility Level Based on Texture with CNN Algorithm,” 2023. [9] V. Prabhavathi and P. Kuppusamy, “A study on Deep Learning based Soil Classification,” 2022. [10] P. Bandyopadhyay, S. Shrestha, and L. L. Nalley, “Application of precision agriculture to maize and soybean production in developing countries,” Precis. Agriculture., vol. 18, no. 3, pp. 350–369, 2017.
Publication Date
5/28/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...