• Richa Sarathe
• Kirti verma

Accurate land cover mapping from remotely sensed imagery is essential for sustainable environmental management, precision agriculture, urban development, and disaster assessment. However, variations in spectral characteristics, sensor noise, and inadequate spatial resolution often reduce the reliability of conventional classification techniques. This study presents a novel hybrid framework that integrates Quantization Index Modulation-Discrete Cosine Transform (QIM-DCT)-based image fusion with Particle Swarm Optimization-enabled Support Vector Machine (PSO-SVM) classification to improve land cover mapping accuracy. Initially, panchromatic and multispectral images undergo preprocessing to suppress noise and enhance image quality. Subsequently, QIM-DCT is employed to perform efficient image fusion by preserving both spectral fidelity and spatial details through optimized transform-domain coefficient selection. The fused image is then utilized to extract comprehensive spectral, textural, and statistical features that effectively characterize diverse land cover classes. To eliminate redundant information and enhance discriminative capability, feature selection is performed using Mutual Information (MI) and Maximal Information Coefficient (MIC). Finally, a PSO-optimized SVM classifier is developed to automatically determine the optimal kernel parameters and regularization coefficient, thereby improving classification performance and generalization capability. Experimental evaluation demonstrates that the proposed framework produces higher classification accuracy, superior feature representation, and enhanced robustness compared with conventional image fusion and machine learning approaches. The proposed method provides an efficient and reliable solution for high-precision land cover mapping from multisource remote sensing imagery.

Remote Sensing, Image Fusion, Land Use Land Cover, LULC Classification, QIM-DCT, MI-MIC, PSO-SVM, Machine Learning

"A Hybrid Image Fusion and Classification Model for Land Cover Mapping Using Machine Learning Algorithms ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 9, page no.c554-c565, September-2026, Available :http://www.jetir.org/papers/JETIR2609260.pdf

"A Hybrid Image Fusion and Classification Model for Land Cover Mapping Using Machine Learning Algorithms ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 9, page no. ppc554-c565, September-2026, Available at : http://www.jetir.org/papers/JETIR2609260.pdf