Shahrood University of Technology Journal of AI and Data Mining 2322-5211 Articles in Press 2026 06 07 A Siamese Network Based on InceptionV3 with Custom Loss Functions for Document Image Quality Assessment (DIQA) 3804 10.22044/jadm.2026.16621.2788 EN Mohammad Hossein Khosravi Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran Journal Article 2025 08 04 Document Image Quality Assessment (DIQA) is critical for ensuring the reliability of downstream applications such as Optical Character Recognition (OCR), digital archiving, and automated document workflows. In this paper, we propose a deep learning-based DIQA framework using a Siamese neural network architecture with an InceptionV3 backbone. Our model leverages a composite loss function that combines linear regression loss with a monotonic ranking constraint to jointly optimize for score-level accuracy and perceptual consistency. Unlike prior works that rely on handcrafted features or narrow degradation types, our approach generalizes across diverse distortions commonly observed in scanned and photographed documents. Experimental results on the SOC and SmartDoc-QA datasets demonstrate that the proposed model exhibits a strong correlation with OCR accuracy, achieving SROCC values of 0.952 and 0.873, respectively, and outperforming several state-of-the-art DIQA methods.