Aproximación experimental al uso de métricas objetivas para la estimación de calidad cromática en la digitalización de patrimonio documental gráfico

Abstract

This work aims to provide a critical examination of different approaches to creating models of automated quality control systems for digital images in digitization projects for photographic heritage collections. After conducting a psychometric experiment with four human experts, we demonstrate that it is not possible to talk about commonly used, simplistic models based on continuous acceptance ranges for colour metrics on an isolated basis. This study demonstrates that a model based on a rule-based, machine-learning system employing metrics (CIE 1976 or CIEDE 2000) along with the colour perceptual attributes of hue, saturation and lightness, emulates the image quality experts with a high degree of efficacy, above 85%.