Table 1 Machine learning techniques to classify and extract relevant patterns from plant stresses and plant disease.

³³

YOLOV3, CV2,

RNN

Real-time plant leaf analysis with

Tiny-YOLOv3, outperforming

Faster R-CNN in speed and performance.

Tiny-YOLOv3 enhances leaf de-

tection over Faster R-CNN but

needs further research

³⁴

OpenCV,

K-means clustering, CART

Tomato yield ML model RGB cam-

era, no filter changes.

Threshold variability, tomato focus, and recall discrepancies

³⁵

RESNET, R-

CNN, SVM

DL survey in visual object detection, covering architectures, learning strategies.

interpretability issues, dataset

reliance, biases, and computational complexity

³⁶

YOLO, SSD,

LENET,

RESNET

Spotlights DCNNs’ superior object

detection, current/future DL trends. Review paper on DCNN-based and

traditional approaches.

High computational demands,

interpretability issues, and need for extensive labeled datasets.

³⁷

TORCH, TEN-

SORFLOW,

KERAS

Recent advancements in DL and CNN. Aims to clarify techniques and assess cutting-edge systems and

frameworks.

interpretability, dataset size, bi-

ases, and resource intensity.

Urges resolution for ethical and

efficient deployment