{"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/domain-adaptation-for-ear-recognition-using","title":"Domain Adaptation for Ear Recognition Using Deep Convolutional Neural Networks","arxiv_id":"1803.07801","date":"2018-03-21","proceeding":null,"authors":["Fevziye Irem Eyiokur","Dogucan Yaman","Hazim Kemal Ekenel"],"abstract":"In this paper, we have extensively investigated the unconstrained ear\nrecognition problem. We have first shown the importance of domain adaptation,\nwhen deep convolutional neural network models are used for ear recognition. To\nenable domain adaptation, we have collected a new ear dataset using the\nMulti-PIE face dataset, which we named as Multi-PIE ear dataset. To improve the\nperformance further, we have combined different deep convolutional neural\nnetwork models. We have analyzed in depth the effect of ear image quality, for\nexample illumination and aspect ratio, on the classification performance.\nFinally, we have addressed the problem of dataset bias in the ear recognition\nfield. Experiments on the UERC dataset have shown that domain adaptation leads\nto a significant performance improvement. For example, when VGG-16 model is\nused and the domain adaptation is applied, an absolute increase of around 10\\%\nhas been achieved. Combining different deep convolutional neural network models\nhas further improved the accuracy by 4\\%. It has also been observed that image\nquality has an influence on the results. In the experiments that we have\nconducted to examine the dataset bias, given an ear image, we were able to\nclassify the dataset that it has come from with 99.71\\% accuracy, which\nindicates a strong bias among the ear recognition datasets.","url_abs":"http://arxiv.org/abs/1803.07801v1","url_pdf":"http://arxiv.org/pdf/1803.07801v1.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":"domain-adaptation-for-ear-recognition-using","repo_url":"https://github.com/iremeyiokur/multipie_ear_dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}