AI-Driven Computer Vision Framework for Compositional Classification and Quality Assessment of Recovered Paper, TAPPICon26

The heterogeneous nature of recovered paper streams, ranging from fiber-rich to filler- and contaminant-heavy fractions, presents a significant challenge for quality control and furnish optimization. Conventional inspection methods are limited in their ability to capture the spatial and compositional heterogeneity that governs fiber performance and recyclability. This work presents a computer vision–based approach for classifying paper samples into visually distinguishable categories associated with compositional attributes, including cellulose-rich fibers, lignocellulosic fibers, ash-contents, and contamination-rich fractions. The model integrates imaging data with structured metadata describing the source, process conditions, and material characteristics, enabling a more comprehensive characterization of paper quality. By establishing relationships between observable visual patterns and specific material characteristics, this framework aims to support the development of automated, AI-assisted inspection systems. Ultimately, our approach enable real-time feedback and data-informed process optimization in paper recycling and manufacturing environments, contributing to improved consistency, reduced waste, and more sustainable production practices.

TAPPI conference proceedings and presentations, technical papers, and publication articles provide technical and management data and solutions on topics covering the Pulp, Paper, Tissue, Corrugated Packaging, Flexible Packaging, Nanotechnology and Converting Industries.

Simply select the quantity, add to your cart and your conference paper, presentation or article will be available for immediate download.