{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T06:41:31Z","timestamp":1698043291628},"reference-count":14,"publisher":"Wiley","issue":"14","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":5923,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp; Computers in Japan"],"published-print":{"date-parts":[[1991,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In many pattern recognition tasks (e.g., handwritten letters), it is essential to recognize a given pattern invariantly with translation, rotation, and other spatial transformations to which the pattern might be subjected. The Fourier transform method is a well\u2010known method for translation invariant pattern recognition in which the Fourier spectrum of an image is used as an invariant feature.<\/jats:p><jats:p>This paper shows experimentally that a three\u2010layer neural network learns to have a similar capability to that of the Fourier transform method by means of the back propagation learning, during which a set of random dot patterns are repeatedly presented with various positions. Specifically, each unit in the middle layer of the resultant network detects a particular frequency component contained in the given image; and, using the information, the output layer generates an output pattern which is invariant to translation of the image.<\/jats:p>","DOI":"10.1002\/scj.4690221406","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T20:26:09Z","timestamp":1183839969000},"page":"80-89","source":"Crossref","is-referenced-by-count":5,"title":["Back\u2010propagation learning of neural networks for translation invariant pattern recognition"],"prefix":"10.1002","volume":"22","author":[{"given":"Jianqiang","family":"Yi","sequence":"first","affiliation":[]},{"given":"Shuichi","family":"Kurogi","sequence":"additional","affiliation":[]},{"given":"Kiyotoshi","family":"Matsuoka","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2007,3,21]]},"reference":[{"key":"e_1_2_1_2_2","unstructured":"M.Umeda.Shape and image recognition by neural networks. A Collection of Applications of Neural Networks (Eds. S. Amari and A. Mori). Torikeppusu pp.73\u201385(1989)."},{"key":"e_1_2_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/29.1638"},{"key":"e_1_2_1_4_2","first-page":"401","article-title":"MADALINE RULE II: A training algorithm for neural networks","volume":"1","author":"Winter R.","year":"1988","journal-title":"IEEE ICNN88"},{"key":"e_1_2_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"e_1_2_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(82)90024-3"},{"key":"e_1_2_1_7_2","first-page":"365","article-title":"Performance of back\u2010propagation for rotation invariant pattern recognition","volume":"4","author":"Yang H.","year":"1987","journal-title":"IEEE ICNN87"},{"key":"e_1_2_1_8_2","volume-title":"Learning internal representation by error propagation. Parallel Distributed Processing","author":"Rumelhart D. E.","year":"1986"},{"key":"e_1_2_1_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_1_10_2","unstructured":"H.Taketani K.Okazaki H.Mitsumoto S.Tamura H.Kawai andY.Fukui.Detection and normalization of pattern location by neural network. Papers of Technical Group on Pattern Recognition and Understanding I.E.I.C.E. PRU89\u201393 (1989)."},{"key":"e_1_2_1_11_2","doi-asserted-by":"publisher","DOI":"10.1364\/AO.15.001795"},{"issue":"4","key":"e_1_2_1_12_2","first-page":"590","article-title":"Measurement of the angle of rotated images using Fourier transform","volume":"73","author":"Kurogi S.","year":"1990","journal-title":"Trans. I.E.I.C.E."},{"key":"e_1_2_1_13_2","first-page":"641","article-title":"Capabilities of three\u2010layered perceptrons","volume":"1","author":"Irei B.","year":"1988","journal-title":"IEEE ICN88"},{"key":"e_1_2_1_14_2","doi-asserted-by":"crossref","unstructured":"H.Midorikawa.The face pattern identification by back\u2010propagation learning procedures. Proc. INNS First Annual Meeting p.515 (1988).","DOI":"10.1016\/0893-6080(88)90537-0"},{"key":"e_1_2_1_15_2","unstructured":"T.Nagano.Spatial frequency responses of the human visual system. Circulars of the Electrotechnical Laboratory 193(1977)."}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690221406","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690221406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T01:20:34Z","timestamp":1698024034000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690221406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":14,"journal-issue":{"issue":"14","published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1002\/scj.4690221406"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690221406","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1991,1]]}}}