| _version_ | 1866902285674610688 |
|---|---|
| author | Dipankar Das Uzzal Sharma Gypsy Nandi |
| author_facet | Dipankar Das Uzzal Sharma Gypsy Nandi |
| contents | <p>Precision farming and production optimization depend on accurate nutrient deficit <br>(ND) diagnosis. In order to diagnose various problems in okra leaves, this study <br>proposes a repeatable and comprehensible deep-learning pipeline that combines <br>segmentation, adaptive picture improvement, handcrafted deep feature fusion, and <br>a lightweight convolutional neural network (CNN) classifier. <br>By simultaneously adjusting Gaussian and Poisson noise weights, a Dual Adaptive <br>Weighted Kalman Filter (DAWKF) reduces noise in input images. Segmentation is <br>carried out via an Adaptive Weighted Optimizer with Otsu Thresholding (AWO-AOT) <br>using bio-inspired adaptive migration methods that improve local thresholds. Local <br>Binary Patterns (LBP), FAST, and SIFT descriptors are used in Adaptive Fused <br>Features (AFF), which feed a SIFT-guided CNN to learn spatial-texture <br>representations. <br>2,030 agronomist-verified okra-leaf photos from various field sources make up the <br>extended dataset. They are divided into 70/15/15 sections for training, validation, <br>and testing, and they are assessed using five-fold cross-validation. The suggested <br>framework outperformed BM3D and PSO-Otsu baselines with 98.6 ± 0.3% accuracy <br>and statistically significant gains (p < 0.05) in PSNR (+1.8 dB) and SSIM (+0.014). <br>Grad-CAM explainability studies revealed important symptom regions associated <br>with necrosis and leaf chlorosis. The technique provides a repeatable mechanism <br>for real-field agronomic decision assistance and is generalizable across lighting, <br>camera, and field conditions.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18066359 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | A Deep Learning Approach for Diagnosing Nutrient Deficiencies in Okra Leaves Dipankar Das Uzzal Sharma Gypsy Nandi <p>Precision farming and production optimization depend on accurate nutrient deficit <br>(ND) diagnosis. In order to diagnose various problems in okra leaves, this study <br>proposes a repeatable and comprehensible deep-learning pipeline that combines <br>segmentation, adaptive picture improvement, handcrafted deep feature fusion, and <br>a lightweight convolutional neural network (CNN) classifier. <br>By simultaneously adjusting Gaussian and Poisson noise weights, a Dual Adaptive <br>Weighted Kalman Filter (DAWKF) reduces noise in input images. Segmentation is <br>carried out via an Adaptive Weighted Optimizer with Otsu Thresholding (AWO-AOT) <br>using bio-inspired adaptive migration methods that improve local thresholds. Local <br>Binary Patterns (LBP), FAST, and SIFT descriptors are used in Adaptive Fused <br>Features (AFF), which feed a SIFT-guided CNN to learn spatial-texture <br>representations. <br>2,030 agronomist-verified okra-leaf photos from various field sources make up the <br>extended dataset. They are divided into 70/15/15 sections for training, validation, <br>and testing, and they are assessed using five-fold cross-validation. The suggested <br>framework outperformed BM3D and PSO-Otsu baselines with 98.6 ± 0.3% accuracy <br>and statistically significant gains (p < 0.05) in PSNR (+1.8 dB) and SSIM (+0.014). <br>Grad-CAM explainability studies revealed important symptom regions associated <br>with necrosis and leaf chlorosis. The technique provides a repeatable mechanism <br>for real-field agronomic decision assistance and is generalizable across lighting, <br>camera, and field conditions.</p> |
| title | A Deep Learning Approach for Diagnosing Nutrient Deficiencies in Okra Leaves |
| url | https://doi.org/10.5281/zenodo.18066359 |