{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:08:24Z","timestamp":1760238504689,"version":"build-2065373602"},"reference-count":26,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,8,18]],"date-time":"2020-08-18T00:00:00Z","timestamp":1597708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>With the introduction of the Convolutional Neural Network (CNN) and other classical algorithms, facial and object recognition have made significant progress. However, in a situation where there are few label examples or the environment is not ideal, such as lighting conditions, orientations, and so on, performance is disappointing. Various methods, such as data augmentation and image registration, have been used in an effort to improve accuracy; nonetheless, performance remains far from human efficiency. Advancement in cognitive science has provided us with valuable insight into how humans achieve high accuracy in identifying and discriminating between different faces and objects. These researches help us understand how the brain uses the features in the face to form a holistic representation and subsequently uses it to discriminate between faces. Our objective and contribution in this paper is to introduce a computational model that leverages these techniques, being used by our brain, to improve robustness and recognition accuracy. The hypothesis is that the biological model, our brain, achieves such high efficiency in face recognition because it is using a two-step process. We therefore postulate that, in the case of a handwritten digit, it will be easier for a learning model to learn invariant features and to generate a holistic representation than to perform classification. The model uses a variational autoencoder to generate holistic representation of handwritten digits and a Neural Network(NN) to classify them. The results obtained in this research show the effectiveness of decomposing the recognition tasks into two specialize sub-tasks, a generator, and a classifier.<\/jats:p>","DOI":"10.3390\/make2030015","type":"journal-article","created":{"date-parts":[[2020,8,18]],"date-time":"2020-08-18T11:15:27Z","timestamp":1597749327000},"page":"271-282","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Digit Recognition Based on Specialization, Decomposition and Holistic Processing"],"prefix":"10.3390","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4563-8684","authenticated-orcid":false,"given":"Michael","family":"Joseph","sequence":"first","affiliation":[{"name":"Computer Science and Engineering Department, University of Bridgeport, Bridgeport, CT 06604, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9239-5035","authenticated-orcid":false,"given":"Khaled","family":"Elleithy","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering Department, University of Bridgeport, Bridgeport, CT 06604, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,8,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1080\/17470218.2013.828315","article-title":"The face inversion effect\u2014Parts and wholes: Individual features and their configuration","volume":"67","author":"Civile","year":"2014","journal-title":"Q. J. Exp. Psychol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1037\/h0027474","article-title":"Looking at upside-down faces","volume":"81","author":"Yin","year":"1969","journal-title":"J. Exp. Psychol."},{"key":"ref_3","first-page":"889","article-title":"Face perception: Domain specific, not process specific","volume":"44","author":"Yovel","year":"2004","journal-title":"Neuron"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1126\/science.831281","article-title":"From piecemeal to configurational representation of faces","volume":"195","author":"Carey","year":"1977","journal-title":"Science"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1708","DOI":"10.1016\/j.neuroimage.2006.07.045","article-title":"Developmental differences in the neural bases of the face inversion effect show progressive tuning of face-selective regions to the upright orientation","volume":"34","author":"Passarotti","year":"2007","journal-title":"Neuroimage"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1037\/0096-1523.22.4.904","article-title":"Inversion and processing of component and spatial\u2013relational information in faces","volume":"22","author":"Searcy","year":"1996","journal-title":"J. Exp. Psychol. Hum. Percept. Perform."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fodor, J.A. (1983). The Modularity of Mind, MIT Press.","DOI":"10.7551\/mitpress\/4737.001.0001"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2089","DOI":"10.1016\/0042-6989(94)00273-O","article-title":"The inverted face inversion effect in prosopagnosia: Evidence for mandatory, face-specific perceptual mechanisms","volume":"35","author":"Farah","year":"1995","journal-title":"Vis. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1080\/713755889","article-title":"When inverted faces are recognized: The role of configural information in face recognition","volume":"53","author":"Leder","year":"2000","journal-title":"Q. J. Exp. Psychol. Sect. A"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1016\/j.visres.2011.04.002","article-title":"The role of holistic processing in face perception: Evidence from the face inversion effect","volume":"51","author":"Taubert","year":"2011","journal-title":"Vis. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.cognition.2012.09.004","article-title":"Using regression to measure holistic face processing reveals a strong link with face recognition ability","volume":"126","author":"DeGutis","year":"2013","journal-title":"Cognition"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1016\/j.actpsy.2009.08.002","article-title":"Distinguishing the cause and consequence of face inversion: The perceptual field hypothesis","volume":"132","author":"Rossion","year":"2009","journal-title":"Acta Psychol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1080\/14640749308401045","article-title":"Parts and wholes in face recognition","volume":"46","author":"Tanaka","year":"1993","journal-title":"Q. J. Exp. Psychol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Schwaninger, A., Lobmaier, J.S., and Collishaw, S.M. (2002, January 22\u201324). Role of Featural and Configural Information in Familiar and Unfamiliar Face Recognition. Proceedings of the International Workshop on Biologically Motivated Computer Vision, T\u00fcbingen, Germany.","DOI":"10.1007\/3-540-36181-2_64"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1111\/j.0956-7976.2004.00753.x","article-title":"Impairment in holistic face processing following early visual deprivation","volume":"15","author":"Grand","year":"2004","journal-title":"Psychol. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Archana, T., and Venugopal, T. (2015, January 8\u201310). Face recognition: A template based approach. Proceedings of the 2015 International Conference on Green Computing and Internet of Things (ICGCIoT), Noida, India.","DOI":"10.1109\/ICGCIoT.2015.7380602"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_19","unstructured":"Jeong, C.-S., and Jeong, D.-S. (1999, January 15\u201317). Hand-written digit recognition using Fourier descriptors and contour information. Proceedings of the IEEE Region 10 Conference. TENCON 99.\u2019Multimedia Technology for Asia-Pacific Information Infrastructure\u2019(Cat. No. 99CH37030), Cheju Island, Korea."},{"key":"ref_20","unstructured":"Barczak, A., Johnson, M.J., and Messom, C.H. (2007, January 5\u20137). Revisiting moment invariants: Rapid feature extraction and classification for handwritten digits. Proceedings of the International Conference on Image and Vision Computing New Zealand (IVCNZ), Hamilton, ON, Canada."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1816","DOI":"10.1016\/j.patcog.2006.10.011","article-title":"A trainable feature extractor for handwritten digit recognition","volume":"40","author":"Lauer","year":"2007","journal-title":"Pattern Recognit."},{"key":"ref_22","first-page":"34","article-title":"The mnist database of handwritten digits","volume":"10","author":"LeCun","year":"1998","journal-title":"Lecun. Com\/Exdb\/Mnist"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ranzato, M.A., Huang, F.J., Boureau, Y.-L., and LeCun, Y. (2007, January 17\u201322). Unsupervised learning of invariant feature hierarchies with applications to object recognition. Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383157"},{"key":"ref_24","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational Bayes. arXiv."},{"key":"ref_25","unstructured":"Hadsell, R., Chopra, S., and LeCun, Y. (2006, January 17\u201322). Dimensionality reduction by learning an invariant mapping. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906), New York, NY, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Baldominos, A., Saez, Y., and Isasi, P. (2019). A survey of handwritten character recognition with mnist and emnist. Appl. Sci., 9.","DOI":"10.3390\/app9153169"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/15\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:02:30Z","timestamp":1760176950000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,18]]},"references-count":26,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["make2030015"],"URL":"https:\/\/doi.org\/10.3390\/make2030015","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2020,8,18]]}}}