InspectionV3: Enhancing Tobacco Quality Assessment with Deep Convolutional Neural Networks for Automated Workshop Management

2025-05-22

AI Summary

Tobacco processing facilities suffer from suboptimal baking quality, supply volatility, disordered scheduling, and inadequate quality inspection—leading to increased operational costs and declining product quality. Manual visual inspection is inefficient, inconsistent, and incapable of reliably distinguishing fine-grained leaf-grade attributes (e.g., color, maturity, moisture spots) across 20 discriminative features. To address these domain-specific challenges, we propose a customized multi-layer CNN architecture incorporating process-sensitive features, batch normalization, comprehensive image augmentation, and continual learning for seasonal adaptation. We curate a large-scale, expert-annotated dataset comprising 21,113 high-resolution images and deploy a lightweight edge inference system with real-time visualization analytics. Experimental results demonstrate state-of-the-art performance on fine-grained grading: 97% accuracy, 96% F1-score and AUC, and 95% precision, recall, and specificity—matching human expert performance and enabling fully automated, real-time quality assurance.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The problems that tobacco workshops encounter include poor curing, inconsistencies in supplies, irregular scheduling, and a lack of oversight, all of which drive up expenses and worse quality. Large quantities make manual examination costly, sluggish, and unreliable. Deep convolutional neural networks have recently made strides in capabilities that transcend those of conventional methods. To effectively enhance them, nevertheless, extensive customization is needed to account for subtle variations in tobacco grade. This study introduces InspectionV3, an integrated solution for automated flue-cured tobacco grading that makes use of a customized deep convolutional neural network architecture. A scope that covers color, maturity, and curing subtleties is established via a labelled dataset consisting of 21,113 images spanning 20 quality classes. Expert annotators performed preprocessing on the tobacco leaf images, including cleaning, labelling, and augmentation. Multi-layer CNN factors use batch normalization to describe domain properties like as permeability and moisture spots, and so account for the subtleties of the workshop. Its expertise lies in converting visual patterns into useful information for enhancing workflow. Fast notifications are made possible by real-time, on-the-spot grading that matches human expertise. Images-powered analytics dashboards facilitate the tracking of yield projections, inventories, bottlenecks, and the optimization of data-driven choices. More labelled images are assimilated after further retraining, improving representational capacities and enabling adaptations for seasonal variability. Metrics demonstrate 97% accuracy, 95% precision and recall, 96% F1-score and AUC, 95% specificity; validating real-world viability.

Problem

• Automating tobacco quality assessment to reduce manual inspection costs
• Addressing subtle tobacco grade variations with customized deep learning
• Enhancing workshop management via real-time grading and data analytics

Innovation

• Custom deep CNN for tobacco grading automation
• Real-time grading with human-expert accuracy
• Data-driven dashboards for workflow optimization