{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/single-classifier-based-passive-system-for","title":"Single Classifier-based Passive System for Source Printer Classification using Local Texture Features","arxiv_id":"1706.07422","date":"2017-06-22","proceeding":null,"authors":["Sharad Joshi","Nitin Khanna"],"abstract":"An important aspect of examining printed documents for potential forgeries\nand copyright infringement is the identification of source printer as it can be\nhelpful for ascertaining the leak and detecting forged documents. This paper\nproposes a system for classification of source printer from scanned images of\nprinted documents using all the printed letters simultaneously. This system\nuses local texture patterns based features and a single classifier for\nclassifying all the printed letters. Letters are extracted from scanned images\nusing connected component analysis followed by morphological filtering without\nthe need of using an OCR. Each letter is sub-divided into a flat region and an\nedge region, and local tetra patterns are estimated separately for these two\nregions. A strategically constructed pooling technique is used to extract the\nfinal feature vectors. The proposed method has been tested on both a publicly\navailable dataset of 10 printers and a new dataset of 18 printers scanned at a\nresolution of 600 dpi as well as 300 dpi printed in four different fonts. The\nresults indicate shape independence property in the proposed method as using a\nsingle classifier it outperforms existing handcrafted feature-based methods and\nneeds much smaller number of training pages by using all the printed letters.","url_abs":"http://arxiv.org/abs/1706.07422v1","url_pdf":"http://arxiv.org/pdf/1706.07422v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"single-classifier-based-passive-system-for","repo_url":"https://github.com/Hedgehogues/HoChiMinh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}