{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T08:48:45Z","timestamp":1768812525810,"version":"3.49.0"},"reference-count":27,"publisher":"World Scientific Pub Co Pte Lt","issue":"03","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Comp. Intel. Appl."],"published-print":{"date-parts":[[2004,9]]},"abstract":"<jats:p> For face recognition from video streams speed and accuracy are vital aspects. The first decision whether a preprocessed image region represents a human face or not is often made by a feed-forward neural network (NN), e.g. in the Viisage-FaceFINDER<jats:sup>\u00ae<\/jats:sup> video surveillance system. We describe the optimisation of such a NN by a hybrid algorithm combining evolutionary multi-objective optimisation (EMO) and gradient-based learning. The evolved solutions perform considerably faster than an expert-designed architecture without loss of accuracy. We compare an EMO and a single objective approach, both with online search strategy adaptation. It turns out that EMO is preferable to the single objective approach in several respects. <\/jats:p>","DOI":"10.1142\/s1469026804001288","type":"journal-article","created":{"date-parts":[[2004,12,17]],"date-time":"2004-12-17T06:17:03Z","timestamp":1103264223000},"page":"237-253","source":"Crossref","is-referenced-by-count":28,"title":["EVOLUTIONARY MULTI-OBJECTIVE OPTIMISATION OF NEURAL NETWORKS FOR FACE DETECTION"],"prefix":"10.1142","volume":"04","author":[{"given":"STEFAN","family":"WIEGAND","sequence":"first","affiliation":[{"name":"Institut f\u00fcr Neuroinformatik,  Ruhr-Universit\u00e4t Bochum, 44780 Bochum, Germany"}]},{"given":"CHRISTIAN","family":"IGEL","sequence":"additional","affiliation":[{"name":"Institut f\u00fcr Neuroinformatik,  Ruhr-Universit\u00e4t Bochum, 44780 Bochum, Germany"}]},{"given":"UWE","family":"HANDMANN","sequence":"additional","affiliation":[{"name":"Viisage Technology AG, 44801 Bochum, Germany"}]}],"member":"219","published-online":{"date-parts":[[2011,11,20]]},"reference":[{"key":"rf3","first-page":"301","volume":"42","author":"Lades M.","journal-title":"IEEE Trans. Comput."},{"key":"rf4","doi-asserted-by":"publisher","DOI":"10.1145\/954339.954342"},{"key":"rf5","doi-asserted-by":"publisher","DOI":"10.1016\/S0262-8856(99)00032-3"},{"key":"rf8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-5184-0"},{"key":"rf9","volume-title":"Multi-Objective Optimization using Evolutionary Algorithms","author":"Deb K.","year":"2001"},{"key":"rf10","doi-asserted-by":"publisher","DOI":"10.1162\/089976603322385126"},{"key":"rf12","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"rf13","volume":"30","author":"Zhang G. P.","journal-title":"IEEE Trans. Syst. Man Cybernet. \u2014 Part C"},{"key":"rf14","doi-asserted-by":"publisher","DOI":"10.1109\/34.982883"},{"key":"rf15","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.2001.0921"},{"key":"rf16","doi-asserted-by":"publisher","DOI":"10.1109\/18.661502"},{"key":"rf17","unstructured":"R.\u00a0Caruana, S.\u00a0Lawrence and C. L.\u00a0Giles, Advances in Neural Information Processing Systems\u00a013 (MIT Press, Denver, Colorado, 2001)\u00a0pp. 402\u2013408."},{"key":"rf18","unstructured":"S.\u00a0Nolfi, The Handbook of Brain Theory and Neural Networks, 2nd edn., ed. M. A.\u00a0Arbib (MIT Press, 2002)\u00a0pp. 415\u2013418."},{"key":"rf19","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/5.784219","volume":"87","author":"Yao X.","journal-title":"Proc. IEEE"},{"key":"rf20","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4937.001.0001","volume-title":"Neural Smithing","author":"Reed R. D.","year":"1999"},{"key":"rf21","unstructured":"A.\u00a0Stahlberger and M.\u00a0Riedmiller, Advances in Neural Information Processing Systems\u00a09, eds. M. C.\u00a0Mozer, M. I.\u00a0Jordan and T.\u00a0Petsche (The MIT Press, 1997)\u00a0pp. 655\u2013661."},{"key":"rf22","doi-asserted-by":"publisher","DOI":"10.1109\/34.655647"},{"key":"rf23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-60743-1","volume-title":"Neurale Netze: Optimierung durch Lernen und Evolution","author":"Braun H.","year":"1997"},{"key":"rf25","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00700-7"},{"key":"rf26","doi-asserted-by":"publisher","DOI":"10.1016\/0920-5489(94)90017-5"},{"key":"rf27","unstructured":"L.\u00a0Prechelt, Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science\u00a01524, eds. G. B.\u00a0Orr and K.R.\u00a0M\u00fcller (Springer-Verlag, 1999)\u00a0pp. 57\u201369."},{"key":"rf28","volume-title":"Evolutionary Computation: Toward a New Philosophy of Machine Intelligence","author":"Fogel D. B.","year":"1995"},{"key":"rf29","volume-title":"Evolutionary Algorithms for Multiobjective Optimization: Methods and Applications","author":"Zitzler E.","year":"1999"},{"key":"rf30","doi-asserted-by":"publisher","DOI":"10.1109\/4235.771166"},{"key":"rf31","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(02)00628-8"},{"key":"rf32","doi-asserted-by":"publisher","DOI":"10.1007\/s005000050009"},{"key":"rf35","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.810758"}],"container-title":["International Journal of Computational Intelligence and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1469026804001288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T20:27:20Z","timestamp":1565123240000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S1469026804001288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,9]]},"references-count":27,"journal-issue":{"issue":"03","published-online":{"date-parts":[[2011,11,20]]},"published-print":{"date-parts":[[2004,9]]}},"alternative-id":["10.1142\/S1469026804001288"],"URL":"https:\/\/doi.org\/10.1142\/s1469026804001288","relation":{},"ISSN":["1469-0268","1757-5885"],"issn-type":[{"value":"1469-0268","type":"print"},{"value":"1757-5885","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004,9]]}}}