{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T07:03:21Z","timestamp":1773903801679,"version":"3.50.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T00:00:00Z","timestamp":1625270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T00:00:00Z","timestamp":1625270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s11042-021-11092-8","type":"journal-article","created":{"date-parts":[[2021,7,3]],"date-time":"2021-07-03T07:02:52Z","timestamp":1625295772000},"page":"29601-29615","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Learning image by-parts using early and late fusion of auto-encoder features"],"prefix":"10.1007","volume":"80","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6709-6591","authenticated-orcid":false,"given":"Seba","family":"Susan","sequence":"first","affiliation":[]},{"given":"Jatin","family":"Malhotra","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,3]]},"reference":[{"key":"11092_CR1","unstructured":"Bengio Y (2012) Deep learning of representations for unsupervised and transfer learning. In Proceedings of ICML workshop on unsupervised and transfer learning, pp. 17\u201336"},{"key":"11092_CR2","doi-asserted-by":"crossref","unstructured":"Bengio Y, Lamblin P, Popovici D, Larochelle H (2007) Greedy layer-wise training of deep networks. In Advances in neural information processing systems, pp. 153\u2013160","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"11092_CR3","doi-asserted-by":"crossref","unstructured":"Cheng K, Tahir R, Eric LK, Li M (2020) An analysis of generative adversarial networks and variants for image synthesis on MNIST dataset. Multimed Tools Appl:1\u201328","DOI":"10.1007\/s11042-019-08600-2"},{"issue":"3","key":"11092_CR4","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"11092_CR5","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3389\/fncom.2015.00099","volume":"9","author":"PU Diehl","year":"2015","unstructured":"Diehl PU, Cook M (2015) Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front Comput Neurosci 9:99","journal-title":"Front Comput Neurosci"},{"issue":"9","key":"11092_CR6","doi-asserted-by":"publisher","first-page":"10","DOI":"10.5120\/18229-9167","volume":"104","author":"R Ebrahimzadeh","year":"2014","unstructured":"Ebrahimzadeh R, Jampour M (2014) Efficient handwritten digit recognition based on histogram of oriented gradients and SVM. International Journal of Computer Applications 104(9):10\u201313","journal-title":"International Journal of Computer Applications"},{"key":"11092_CR7","doi-asserted-by":"publisher","first-page":"104802","DOI":"10.1016\/j.knosys.2019.06.010","volume":"182","author":"X Gao","year":"2019","unstructured":"Gao X, Zhou C, Chao F, Yang L, Lin C-M, Xu T, Shang C, Shen Q (2019) A data-driven robotic Chinese calligraphy system using convolutional auto-encoder and differential evolution. Knowl-Based Syst 182:104802","journal-title":"Knowl-Based Syst"},{"key":"11092_CR8","unstructured":"Geng Q, Lu F, Huang X, Wang S, Cheng X, Zhou Z, Yang R (2018) Part-level car parsing and reconstruction from single street view. arXiv preprint arXiv:1811.10837"},{"key":"11092_CR9","doi-asserted-by":"crossref","unstructured":"Hassan T, Khan HA (2015) Handwritten bangla numeral recognition using local binary pattern. In 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), pp. 1\u20134. IEEE, 2015.","DOI":"10.1109\/ICEEICT.2015.7307371"},{"key":"11092_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11092_CR11","doi-asserted-by":"crossref","unstructured":"Hosmer Jr DW, Lemeshow S, Sturdivant RX (2013) Applied logistic regression 398. John Wiley & Sons","DOI":"10.1002\/9781118548387"},{"key":"11092_CR12","doi-asserted-by":"crossref","unstructured":"Hou B, Yan R (2019) Convolutional auto-encoder model for finger-vein verification. IEEE Trans Instrum Meas","DOI":"10.1109\/MeMeA.2018.8438719"},{"key":"11092_CR13","unstructured":"https:\/\/github.com\/JMalhotra7\/Learning-image-by-parts-using-early-and-late-fusion-of-auto-encoder-features [Last accessed on 27th Dec 2020]"},{"key":"11092_CR14","doi-asserted-by":"crossref","unstructured":"Izonin I, Tkachenko R, Kryvinska N, Tkachenko P (2019) Multiple linear regression based on coefficients identification using non-iterative SGTM Neural-Like Structure. In International Work-Conference on Artificial Neural Networks, pp. 467\u2013479. Springer, Cham","DOI":"10.1007\/978-3-030-20521-8_39"},{"issue":"8","key":"11092_CR15","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan A, Sohail A, Zahoora U, Qureshi AS (2020) A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review 53(8):5455\u20135516","journal-title":"Artificial Intelligence Review"},{"key":"11092_CR16","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pp. 1097\u20131105"},{"key":"11092_CR17","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.jvcir.2016.11.003","volume":"41","author":"C-CJ Kuo","year":"2016","unstructured":"Kuo C-CJ (2016) Understanding convolutional neural networks with a mathematical model. J Vis Commun Image Represent 41:406\u2013413","journal-title":"J Vis Commun Image Represent"},{"issue":"11","key":"11092_CR18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"11092_CR19","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neucom.2016.12.038","volume":"234","author":"W Liu","year":"2017","unstructured":"Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE (2017) A survey of deep neural network architectures and their applications. Neurocomputing 234:11\u201326","journal-title":"Neurocomputing"},{"key":"11092_CR20","doi-asserted-by":"crossref","unstructured":"Liu X, Wang X, Matwin S (2018) Interpretable deep convolutional neural networks via meta-learning. In 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20139. IEEE","DOI":"10.1109\/IJCNN.2018.8489172"},{"key":"11092_CR21","doi-asserted-by":"crossref","unstructured":"Loey M, El-Sawy A, EL-Bakry H (2017) Deep learning autoencoder approach for handwritten arabic digits recognition. arXiv preprint arXiv:1706.06720.","DOI":"10.1007\/978-3-319-48308-5_54"},{"key":"11092_CR22","doi-asserted-by":"crossref","unstructured":"Lorenz D, Bereska L, Milbich T, Ommer B (2019) Unsupervised part-based disentangling of object shape and appearance. arXiv preprint arXiv:1903.06946","DOI":"10.1109\/CVPR.2019.01121"},{"key":"11092_CR23","unstructured":"Malinowski M, Doersch C (2018) The visual QA devil in the details: The impact of early fusion and batch norm on clevr. arXiv preprint arXiv:1809.04482"},{"key":"11092_CR24","doi-asserted-by":"crossref","unstructured":"Malowany D, Guterman H (2020) Biologically inspired visual system architecture for object recognition in autonomous systems. arXiv preprint arXiv:2002.03472","DOI":"10.3390\/a13070167"},{"key":"11092_CR25","doi-asserted-by":"crossref","unstructured":"Masci J, Meier U, Cire\u015fan D, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In International Conference on Artificial Neural Networks, pp. 52\u201359. Springer, Berlin, Heidelberg","DOI":"10.1007\/978-3-642-21735-7_7"},{"issue":"8","key":"11092_CR26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0134254","volume":"10","author":"MD McDonnell","year":"2015","unstructured":"McDonnell MD, Tissera MD, Vladusich T, van Schaik A, Tapson J (2015) Fast, simple and accurate handwritten digit classification by training shallow neural network classifiers with the \u2018extreme learning machine\u2019algorithm. PLoS One 10(8):e0134254","journal-title":"PLoS One"},{"key":"11092_CR27","doi-asserted-by":"crossref","unstructured":"Palvanov A, Cho YI (2018) Comparisons of Deep Learning Algorithms for MNIST in Real-Time Environment. Int J Fuzzy Log Intell 18(2):126\u2013134","DOI":"10.5391\/IJFIS.2018.18.2.126"},{"issue":"12","key":"11092_CR28","doi-asserted-by":"publisher","first-page":"1728","DOI":"10.1016\/j.patrec.2010.05.024","volume":"31","author":"J Park","year":"2010","unstructured":"Park J, Lee G, Kim E, Lim J, Kim S, Yang H, Lee M, Hwang S (2010) Automatic detection and recognition of Korean text in outdoor signboard images. Pattern Recogn Lett 31(12):1728\u20131739","journal-title":"Pattern Recogn Lett"},{"key":"11092_CR29","doi-asserted-by":"crossref","unstructured":"Safdari R, Moin M-S (2016) A hierarchical feature learning for isolated Farsi handwritten digit recognition using sparse autoencoder. In 2016 Artificial Intelligence and Robotics (IRANOPEN), pp. 67\u201371. IEEE, 2016.","DOI":"10.1109\/RIOS.2016.7529492"},{"key":"11092_CR30","unstructured":"Schott L, Rauber J, Bethge M, Brendel W (2018) Towards the first adversarially robust neural network model on MNIST. arXiv preprint arXiv:1805.09190"},{"issue":"10","key":"11092_CR31","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1016\/S0031-3203(01)00203-5","volume":"35","author":"M Shi","year":"2002","unstructured":"Shi M, Fujisawa Y, Wakabayashi T, Kimura F (2002) Handwritten numeral recognition using gradient and curvature of gray scale image. Pattern Recogn 35(10):2051\u20132059","journal-title":"Pattern Recogn"},{"key":"11092_CR32","doi-asserted-by":"crossref","unstructured":"Snoek, Cees GM, Worring M, Smeulders AWM (2005) Early versus late fusion in semantic video analysis. In Proceedings of the 13th annual ACM international conference on Multimedia, pp. 399\u2013402. ACM","DOI":"10.1145\/1101149.1101236"},{"key":"11092_CR33","doi-asserted-by":"crossref","unstructured":"\u0160pa\u0148hel, Jakub, Jakub Sochor, Roman Jur\u00e1nek, Adam Herout, Luk\u00e1\u0161 Mar\u0161\u00edk, and Pavel Zem\u010d\u00edk (2017) Holistic recognition of low quality license plates by cnn using track annotated data. In 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE, 2017.","DOI":"10.1109\/AVSS.2017.8078501"},{"issue":"2","key":"11092_CR34","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s12559-016-9445-1","volume":"9","author":"MW Spratling","year":"2017","unstructured":"Spratling MW (2017) A hierarchical predictive coding model of object recognition in natural images. Cognitive computation 9(2):151\u2013167","journal-title":"Cognitive computation"},{"key":"11092_CR35","unstructured":"Srivastava, Rupesh K, Greff K, Schmidhuber J (2015) Training very deep networks. In Advances in neural information processing systems, pp. 2377\u20132385"},{"issue":"1","key":"11092_CR36","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.patrec.2005.07.003","volume":"27","author":"J Sung","year":"2006","unstructured":"Sung J, Bang S-Y, Choi S (2006) A Bayesian network classifier and hierarchical Gabor features for handwritten numeral recognition. Pattern Recogn Lett 27(1):66\u201375","journal-title":"Pattern Recogn Lett"},{"key":"11092_CR37","doi-asserted-by":"crossref","unstructured":"Susan S, Devi KMR (2019) Text area segmentation from document images by novel adaptive thresholding and template matching using texture cues. Pattern Analysis and Applications:1\u201313","DOI":"10.1007\/s10044-019-00811-5"},{"key":"11092_CR38","doi-asserted-by":"crossref","unstructured":"Susan S, Kadyan P (2013) A supervised fuzzy eye pair detection algorithm. In 2013 5th International Conference and Computational Intelligence and Communication Networks, pp. 306\u2013310. IEEE","DOI":"10.1109\/CICN.2013.70"},{"key":"11092_CR39","doi-asserted-by":"crossref","unstructured":"Susan S, Kakkar G (2015) Decoding facial expressions using a new normalized similarity index. In 2015 Annual IEEE India Conference (INDICON), pp. 1\u20136. IEEE","DOI":"10.1109\/INDICON.2015.7443608"},{"key":"11092_CR40","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.patrec.2019.04.023","volume":"125","author":"S Susan","year":"2019","unstructured":"Susan S, Keshari J (2019) Finding significant keywords for document databases by two-phase maximum entropy partitioning. Pattern Recogn Lett 125:195\u2013205","journal-title":"Pattern Recogn Lett"},{"key":"11092_CR41","doi-asserted-by":"crossref","unstructured":"Susan S, Malhotra J (2019) CNN Pre-initialization by minimalistic part-learning for handwritten numeral recognition. International Conference on Mining Intelligence and Knowledge Exploration:320\u2013329. Springer, Cham","DOI":"10.1007\/978-3-030-66187-8_30"},{"key":"11092_CR42","doi-asserted-by":"crossref","unstructured":"Susan S, Malhotra J (2020) Learning interpretable hidden state structures for handwritten numeral recognition. In 2020 4th International Conference on Computational Intelligence and Networks (CINE), pp. 1\u20136. IEEE","DOI":"10.1109\/CINE48825.2020.234394"},{"issue":"5","key":"11092_CR43","doi-asserted-by":"publisher","first-page":"268","DOI":"10.14429\/djlit.40.05.16336","volume":"40","author":"S Susan","year":"2020","unstructured":"Susan S, Malhotra J (2020) Recognising devanagari script by deep structure learning of image quadrants. DESIDOC J Libr Inf Technol 40(5):268\u2013271","journal-title":"DESIDOC J Libr Inf Technol"},{"key":"11092_CR44","doi-asserted-by":"crossref","unstructured":"Susan S, Singh V (2011) On the discriminative power of different feature subsets for handwritten numeral recognition using the box-partitioning method. In 2011 Annual IEEE India Conference, pp. 1\u20135. IEEE","DOI":"10.1109\/INDCON.2011.6139383"},{"key":"11092_CR45","doi-asserted-by":"crossref","unstructured":"Susan S, Ranjan R, Taluja U, Rai S, Agarwal P (2019) Neural net optimization by weight-entropy monitoring. In Computational intelligence: theories, applications and future directions-volume II, pp. 201\u2013213. Springer, Singapore","DOI":"10.1007\/978-981-13-1135-2_16"},{"key":"11092_CR46","doi-asserted-by":"crossref","unstructured":"Tkachenko R, Izonin I (2018) Model and principles for the implementation of neural-like structures based on geometric data transformations. In International Conference on Computer Science, Engineering and Education Applications, pp. 578\u2013587. Springer, Cham","DOI":"10.1007\/978-3-319-91008-6_58"},{"key":"11092_CR47","doi-asserted-by":"crossref","unstructured":"Tkachenko R, Tkachenko P, Izonin I, Tsymbal Y (2018) Learning-based image scaling using neural-like structure of geometric transformation paradigm. In Advances in Soft Computing and Machine Learning in Image Processing, pp. 537\u2013565. Springer, Cham","DOI":"10.1007\/978-3-319-63754-9_25"},{"key":"11092_CR48","doi-asserted-by":"crossref","unstructured":"Wang M, Chen Y, Wang X (2014) Recognition of handwritten characters in chinese legal amounts by stacked autoencoders. In 2014 22nd International Conference on Pattern Recognition, pp. 3002\u20133007. IEEE","DOI":"10.1109\/ICPR.2014.518"},{"key":"11092_CR49","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1016\/j.neucom.2015.10.035","volume":"174","author":"Y Wang","year":"2016","unstructured":"Wang Y, Xie Z, Xu K, Dou Y, Lei Y (2016) An efficient and effective convolutional auto-encoder extreme learning machine network for 3d feature learning. Neurocomputing 174:988\u2013998","journal-title":"Neurocomputing"},{"issue":"1","key":"11092_CR50","first-page":"012097","volume":"428","author":"Y Wang","year":"2020","unstructured":"Wang Y, Li F, Sun H, Li W, Cheng Z, Wu X, Wang H, Wang P (2020) Improvement of MNIST Image Recognition Based on CNN. In IOP Conference Series: Earth and Environmental Science 428(1):012097. IOP Publishing","journal-title":"In IOP Conference Series: Earth and Environmental Science"},{"key":"11092_CR51","doi-asserted-by":"crossref","unstructured":"Xie L, Wang J, Wei Z, Wang M, Tian Q (2016) Disturblabel: regularizing cnn on the loss layer. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4753\u20134762","DOI":"10.1109\/CVPR.2016.514"},{"key":"11092_CR52","unstructured":"Xu X (2013) Receipt digitizing method for retail customers. U.S. Patent Application 13\/507,291, filed March 7, 2013."},{"key":"11092_CR53","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy CC, Shum KW, Tang X (2015) Deep representation learning with target coding. In Twenty-Ninth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v29i1.9796"},{"issue":"6","key":"11092_CR54","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1007\/s12559-018-9598-1","volume":"10","author":"Z-X Yang","year":"2018","unstructured":"Yang Z-X, Tang L, Zhang K, Wong PK (2018) Multi-view cnn feature aggregation with elm auto-encoder for 3d shape recognition. Cogn Comput 10(6):908\u2013921","journal-title":"Cogn Comput"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11092-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11092-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11092-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,5]],"date-time":"2023-11-05T16:24:24Z","timestamp":1699201464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11092-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,3]]},"references-count":54,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["11092"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11092-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,3]]},"assertion":[{"value":"12 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The two authors are with the Department of Information Technology, Delhi Technological University, New Delhi, India.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}