{"corpus_id":36654576,"paper_sha":"7253ddde7529aacf145eadc5daf49a915b78f652","doi":"10.1109/SMC.2015.423","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2243756072,"dblp_id":"conf/smc/NgYCL15","acl_id":null,"title":"Will Wrinkle Estimate the Face Age?","year":2015,"publication_date":null,"venue":"IEEE International Conference on Systems, Man and Cybernetics","journal":{"name":"2015 IEEE International Conference on Systems, Man, and Cybernetics","pages":"2418-2423","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Conference"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science"],"reference_count":39,"citation_count":14,"influential_citation_count":1,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://figshare.com/articles/conference_contribution/Will_wrinkle_estimate_the_face_age_/9403685/1/files/17020346.pdf","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/7253ddde7529aacf145eadc5daf49a915b78f652","s2_open_access_license":"CCBYNCND","s2_open_access_status":"GREEN","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"The majority of current facial age estimation methods are based on appearance based features. However, wrinkle based research has not been widely addressed. In this paper, we propose a novel method based on multi-scale aging patterns (MAP). These directly extract the features from local patches without extensive geometric modelling. First, we locate facial landmarks by using the Face++ detector and then normalize the face by using a linear transformation. We define a face template which consists of ten predefined wrinkle regions. Then, for each region, we detect wrinkles and construct aging patterns by using the MAP. Finally, the age is estimated by implementing the sequential minimal optimization (SMO). The performance of the algorithms is assessed by using mean absolute error (MAE) on the benchmark database - FERET. We observe that MAP produces a lower MAE of 4.87 on FERET compared to the benchmark algorithms. Therefore, we conclude that wrinkle could be used as a feature on face age estimation. Future work would involve improvements of the algorithm by combining other descriptors such as non-wrinkle descriptor and appearance parameters.","claims":[{"public_id":"cl_10ef495bd1e3f84117c6b899ba855782","status":"active","text":"A novel wrinkle-based face age estimation method using multi-scale aging patterns is proposed.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_10ef495bd1e3f84117c6b899ba855782"},{"public_id":"cl_c8c9589aaabbe2c94896da4231b6e148","status":"active","text":"On the FERET benchmark database, multi-scale aging patterns achieves a mean absolute error of 4.87 and outperforms the benchmark algorithms.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_c8c9589aaabbe2c94896da4231b6e148"},{"public_id":"cl_937151eaebf96545f621c1ad5197ccdf","status":"active","text":"The method extracts features directly from local patches without extensive geometric modelling.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_937151eaebf96545f621c1ad5197ccdf"},{"public_id":"cl_eb3ab8788f9cff77c72dea1ced34b529","status":"active","text":"Wrinkle can be used as a feature for face age estimation.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_eb3ab8788f9cff77c72dea1ced34b529"}],"concepts":[{"public_id":"co_0a71838f4b7de6eea6d5dcb0638d7a83","status":"active","name":"wrinkle","description":"Facial lines or folds used as aging cues in the proposed approach.","types":["feature"],"aliases":["wrinkles"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_0a71838f4b7de6eea6d5dcb0638d7a83"},{"public_id":"co_15e41ee99bc3c89120ed47fb85ab655d","status":"active","name":"ten predefined wrinkle regions","description":"A face template partitioned into ten fixed regions where wrinkles are analyzed.","types":["template"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_15e41ee99bc3c89120ed47fb85ab655d"},{"public_id":"co_1b78f58e4a05579cffe9164efd17426d","status":"active","name":"local patches","description":"Small localized regions of a face image from which features are extracted.","types":["image region"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1b78f58e4a05579cffe9164efd17426d"},{"public_id":"co_1bf711d71d4d8344f3454e413ef2864c","status":"active","name":"mean absolute error","description":"An evaluation metric measuring the average absolute difference between predicted and true ages.","types":["evaluation metric"],"aliases":["MAE"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1bf711d71d4d8344f3454e413ef2864c"},{"public_id":"co_30e6b0de27d0591535e515f4c6077e5e","status":"active","name":"multi-scale aging patterns","description":"A wrinkle-based method for representing facial aging cues across multiple scales.","types":["method"],"aliases":["MAP"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_30e6b0de27d0591535e515f4c6077e5e"},{"public_id":"co_318cb12d426d66c322089bcf5deabc48","status":"active","name":"face age estimation","description":"The task of predicting a person's age from facial images.","types":["task"],"aliases":["facial age estimation"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_318cb12d426d66c322089bcf5deabc48"},{"public_id":"co_3d6b2fac4fdb12b2ccb2abb3f0b00847","status":"active","name":"linear transformation","description":"A normalization step applied to align the face geometry.","types":["transformation"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_3d6b2fac4fdb12b2ccb2abb3f0b00847"},{"public_id":"co_6abecfecb884090b63872f6e155810a4","status":"active","name":"FERET","description":"A benchmark face database used for evaluating age estimation performance.","types":["benchmark database"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6abecfecb884090b63872f6e155810a4"},{"public_id":"co_6b9e704731cd1f46a2bd11ed5162d313","status":"active","name":"sequential minimal optimization","description":"An optimization algorithm used to train the age estimation model.","types":["optimization algorithm"],"aliases":["SMO"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_6b9e704731cd1f46a2bd11ed5162d313"},{"public_id":"co_7fb4c62155edd6b32b653bb36592c38b","status":"active","name":"geometric modelling","description":"Explicit modeling of facial structure and shape relationships.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7fb4c62155edd6b32b653bb36592c38b"},{"public_id":"co_85d8069aacbb151a7ad649c3e0148b31","status":"active","name":"Face++ detector","description":"A facial landmark detection tool used to locate points on the face.","types":["tool"],"aliases":["Face++"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_85d8069aacbb151a7ad649c3e0148b31"}],"external_ids":{"DOI":"10.1109/SMC.2015.423","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2243756072,"DBLP":"conf/smc/NgYCL15","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://figshare.com/articles/conference_contribution/Will_wrinkle_estimate_the_face_age_/9403685/1/files/17020346.pdf","landing_url":"https://www.semanticscholar.org/paper/7253ddde7529aacf145eadc5daf49a915b78f652","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBYNCND","status":"GREEN","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":632221,"paper_uid":"905847be-6b33-4fe5-afe3-4681379618ce","canonical_identity":{"paper_id":632221,"paper_uid":"905847be-6b33-4fe5-afe3-4681379618ce","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/36654576"}