Melamine Faced Panels Defect Classification beyond the Visible Spectrum.

Cristhian Aguilera,Angel Sappa

doi:10.3390/s18113644

Abstract

In this work, we explore the use of images from different spectral bands to classify defects in melamine faced panels, which could appear through the production process. Through experimental evaluation, we evaluate the use of images from the visible (VS), near-infrared (NIR), and long wavelength infrared (LWIR), to classify the defects using a feature descriptor learning approach together with a support vector machine classifier. Two descriptors were evaluated, Extended Local Binary Patterns (E-LBP) and SURF using a Bag of Words (BoW) representation. The evaluation was carried on with an image set obtained during this work, which contained five different defect categories that currently occurs in the industry. Results show that using images from beyond the visual spectrum helps to improve classification performance in contrast with a single visible spectrum solution.

Highlights

Companies face the great challenge of being competitive worldwide, which is expressed in many cases in the creation of new and better products, and in the improvement and innovation in their production processes
This paper presents an exploratory study of the use of images beyond the visible spectrum for the classification of defects in melamine based boards, providing useful insights regarding the real applications of the technology
We evaluate the performance of each spectral band, using a feature descriptor learning approach together with a support vector machine classifier

Summary

Introduction

Companies face the great challenge of being competitive worldwide, which is expressed in many cases in the creation of new and better products, and in the improvement and innovation in their production processes. A key factor in the production chain is undoubtedly the quality control of their products. In this sense, it is increasingly necessary to incorporate new and better inspection processes of the final quality of their products. The market size of wood-based panels is expected to reach USD 174.55 billion by 2025, a 7% of compound annual growth rate [1]. Products such as particle boards, oriented chipboards and plywood boards, among others, provide a wide variety of possibilities that are used by the construction industry and furniture

Methods

Results

Conclusion