{"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/bringing-cartoons-to-life-towards-improved","title":"Bringing Cartoons to Life: Towards Improved Cartoon Face Detection and Recognition Systems","arxiv_id":"1804.01753","date":"2018-04-05","proceeding":null,"authors":["Saurav Jha","Nikhil Agarwal","Suneeta Agarwal"],"abstract":"Given the recent deep learning advancements in face detection and recognition\ntechniques for human faces, this paper answers the question \"how well would\nthey work for cartoons'?\" - a domain that remains largely unexplored until\nrecently, mainly due to the unavailability of large scale datasets and the\nfailure of traditional methods on these. Our work studies and extends multiple\nframeworks for the aforementioned tasks. For face detection, we incorporate the\nMulti-task Cascaded Convolutional Network (MTCNN) architecture and contrast it\nwith conventional methods. For face recognition, our two-fold contributions\ninclude: (i) an inductive transfer learning approach combining the feature\nlearning capability of the Inception v3 network and the feature recognizing\ncapability of Support Vector Machines (SVMs), (ii) a proposed Hybrid\nConvolutional Neural Network (HCNN) framework trained over a fusion of pixel\nvalues and 15 manually located facial keypoints. All the methods are evaluated\non the Cartoon Faces in the Wild (IIIT-CFW) database. We demonstrate that the\nHCNN model offers stability superior to that of Inception+SVM over larger input\nvariations, and explore the plausible architectural principles. We show that\nthe Inception+SVM model establishes a state-of-the-art F1 score on the task of\ngender recognition of cartoon faces. Further, we introduce a small database\nhosting location coordinates of 15 points on the cartoon faces belonging to 50\npublic figures of the IIIT-CFW database.","url_abs":"http://arxiv.org/abs/1804.01753v2","url_pdf":"http://arxiv.org/pdf/1804.01753v2.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":"bringing-cartoons-to-life-towards-improved","repo_url":"https://github.com/Saurav0074/Cartoon-Face-Detection-and-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"face-detection","task_name":"Face Detection"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}