Comparing Inception V3, VGG 16, VGG 19, CNN, and ResNet 50: A Case Study on Early Detection of a Rice Disease

Abstract

Rice production has faced numerous challenges in recent years, and traditional methods are still being used to detect rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The public dataset consists of 2000 images; about 1200 images belong to the leaf blast class, and 800 to the healthy leaf class. The modified connection-skipping ResNet 50 had the highest accuracy of 99.75% with a loss rate of 0.33, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. Furthermore, ResNet 50 achieved a validation accuracy of 99.69%, precision of 99.50%, F1-score of 99.70, and AUC of 99.83%. In conclusion, the study demonstrated a superior performance and disease prediction using the Gradio web application.

New Trends and Challenges in Precision and Digital Agriculture

“…In order to obtain more precise and accurate results, efforts are being made to improve existing machine learning methods. The ResNet50 model, Faster RCNN, and Focal Voxel R-CNN have been used to diagnose rice blight, detect defects in groundnut crops, and detect obstacles by automated agricultural machinery, respectively [42][43][44]. Diagnosing agricultural crop diseases or detecting obstacles in real time is not possible without advanced visual technologies.…”

Transformative Impact of Deep Learning in Stock Market Decision-Making: A Comparative Study of Convolutional Neural Networks

“…The utilization of VGG19 [Shah, 2023] in organizational decision-making for the stock market revolves around its ability to analyze visual data, such as stock charts, market graphs, and news articles with embedded images. By leveraging transfer learning techniques, pre-trained VGG19 models can be fine-tuned to extract relevant features from financial visuals, aiding in trend analysis, pattern recognition, and sentiment analysis.…”

“…Integrating VGG19 [Shah, 2023] into organizational decision-making processes for the stock market offers several benefits. Firstly, it enables the automation of image analysis tasks, reducing manual effort and processing time.…”

“…Secondly, VGG19's deep architecture allows for the extraction of intricate patterns and subtle nuances from visual data, providing a more nuanced understanding of market dynamics. Additionally, the incorporation of VGG19 [Shah, 2023] enhances decision-making accuracy by leveraging its state-of-the-art image classification capabilities.…”

Ensemble Transfer Learning for Hand-sign Digit Image Classification

“…Notably, it stands out as a valuable tool for tackling classification problems associated with limited data. In our research, we focus on two renowned pretrained models, VGG19 and ResNet50, which have been extensively used for transfer learning in image classification tasks [13][14][15][16][17][18]. These models have exhibited remarkable success on extensive image datasets and are well-suited for extracting vital high-level information from hand-sign digit images [18].…”