{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T21:24:45Z","timestamp":1792272285388,"version":"4.4.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T00:00:00Z","timestamp":1590624000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T00:00:00Z","timestamp":1590624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2021,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The presented paper introduces a novel method for enabling appearance modifications for complex image objects. Qualitative visual object properties, quantified using appropriately derived visual attribute descriptors, are subject to alterations. We adopt a basic convolutional autoencoder as a framework for the proposed attribute modification algorithm, which is composed of the following three steps. The algorithm begins with the extraction of attribute-related information from autoencoder\u2019s latent representation of an input image, by means of supervised principal component analysis. Next, appearance alteration is performed in the derived feature space (referred to as \u2018attribute-space\u2019), based on appropriately identified mappings between quantitative descriptors of image attributes and attribute-space features. Finally, modified attribute vectors are transformed back to latent representation, and output image is reconstructed in the decoding part of an autoencoder. The method has been evaluated using two datasets: images of simple objects\u2014digits from MNIST handwritten-digit dataset and images of complex objects\u2014faces from CelebA dataset. In the former case, two qualitative visual attributes of digit images have been selected for modifications: slant and aspect ratio, whereas in the latter case, aspect ratio of face oval was subject to alterations. Evaluation results prove, both in qualitative and quantitative terms, that the proposed framework offers a promising tool for visual object editing.<\/jats:p>","DOI":"10.1007\/s00521-020-04976-7","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T10:02:57Z","timestamp":1590660177000},"page":"1079-1090","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Autoencoder-based image processing framework for object appearance modifications"],"prefix":"10.1007","volume":"33","author":[{"given":"Krzysztof","family":"\u015alot","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3527-7208","authenticated-orcid":false,"given":"Pawe\u0142","family":"Kapusta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacek","family":"Kucharski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,5,28]]},"reference":[{"key":"4976_CR1","doi-asserted-by":"crossref","unstructured":"Antipov G, Baccouche M, Dugelay J (2017) Face aging with conditional generative adversarial networks. arXiv:1702.01983","DOI":"10.1109\/ICIP.2017.8296650"},{"key":"4976_CR2","unstructured":"Baek K, Bang D, Shim H (2018) Editable generative adversarial networks: generating and editing faces simultaneously. arXiv:1807.07700"},{"issue":"7","key":"4976_CR3","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1016\/j.patcog.2010.12.015","volume":"44","author":"E Barshan","year":"2011","unstructured":"Barshan E, Ghodsi A, Azimifar Z, Zolghadri Jahromi M (2011) Supervised principal component analysis: visualization, classification and regression on subspaces and submanifolds. Pattern Recognit 44(7):1357\u20131371","journal-title":"Pattern Recognit"},{"key":"4976_CR4","unstructured":"Bengio Y, Thibodeau-Laufer E, Yosinski J (2013) Deep generative stochastic networks trainable by backprop. arXiv:1306.1091"},{"key":"4976_CR5","unstructured":"Bodnar C (2018) Text to image synthesis using generative adversarial networks. arXiv:1805.00676"},{"key":"4976_CR6","unstructured":"Brock A, Donahue J, Simonyan K (2018) Large scale GAN training for high fidelity natural image synthesis. arXiv:1809.11096"},{"key":"4976_CR7","unstructured":"Brock A, Lim T, Ritchie JM, Weston N (2016) Neural photo editing with introspective adversarial networks. arXiv:1609.07093"},{"key":"4976_CR8","unstructured":"Goodfellow IJ (2017) NIPS 2016 tutorial: Generative adversarial networks. arXiv:1701.00160"},{"key":"4976_CR9","unstructured":"Gorijala M, Dukkipati A (2017) Image generation and editing with variational info generative adversarial networks. arXiv:1701.04568"},{"key":"4976_CR10","unstructured":"Gregor K, Danihelka I, Graves A, Rezende D, Wierstra D (2015) Draw: a recurrent neural network for image generation. In: Proceedings of the 32nd international conference on machine learning, volume\u00a037 of proceedings of machine learning research, pp 1462\u20131471"},{"key":"4976_CR11","unstructured":"He\u00a0H, Yu PS, Wang C (2018) An introduction to image synthesis with generative adversarial nets. arXiv:1803.04469"},{"issue":"11","key":"4976_CR12","doi-asserted-by":"publisher","first-page":"5464","DOI":"10.1109\/TIP.2019.2916751","volume":"28","author":"Z He","year":"2019","unstructured":"He Z, Zuo W, Kan M, Shan S, Chen X (2019) Attgan: facial attribute editing by only changing what you want. IEEE Trans Image Process 28(11):5464\u20135478","journal-title":"IEEE Trans Image Process"},{"key":"4976_CR13","doi-asserted-by":"crossref","unstructured":"He Z, Zuo W, Kan M, Shan S, Chen X (2020) Attgan: facial attribute editing by only changing what you want\u2014Tensorflow implementation. https:\/\/github.com\/LynnHo\/AttGAN-Tensorflow","DOI":"10.1109\/TIP.2019.2916751"},{"key":"4976_CR14","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"4976_CR15","first-page":"1755","volume":"10","author":"DE King","year":"2009","unstructured":"King DE (2009) Dlib-ml: a machine learning toolkit. J Mach Learn Res 10:1755\u20131758","journal-title":"J Mach Learn Res"},{"key":"4976_CR16","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv:1312.6114"},{"key":"4976_CR17","unstructured":"Lample G, Zeghidour N, Usunier N, Bordes A, Denoyer L, Ranzato M (2017) Fader networks: manipulating images by sliding attributes. arXiv:1706.00409"},{"key":"4976_CR18","unstructured":"LeCun Y, Cortes C (2010) MNIST handwritten digit database"},{"key":"4976_CR19","doi-asserted-by":"crossref","unstructured":"Masci J, Meier U, Cire\u015fan D, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. In: Artificial neural networks and machine learning\u2014ICANN 2011, Lecture Notes in Computer Science, vol 6791, pp 52\u201359","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"4976_CR20","unstructured":"Mehri S, Kumar K, Gulrajani I, Kumar R, Jain S, Sotelo J, Courville AC, Bengio Y (2016) SampleRNN: an unconditional end-to-end neural audio generation model. arXiv:1612.07837"},{"key":"4976_CR21","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:1411.1784"},{"key":"4976_CR22","unstructured":"Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: a generative model for raw audio. arXiv:1609.03499"},{"key":"4976_CR23","unstructured":"Paulus R, Xiong C, Socher R (2017) A deep reinforced model for abstractive summarization. arXiv:1705.04304"},{"key":"4976_CR24","unstructured":"Perarnau G, van\u00a0de Weijer J, Raducanu B, \u00c1lvarez JM (2016) Invertible conditional gans for image editing. arXiv:1611.06355"},{"key":"4976_CR25","unstructured":"Pieters M, Wiering M (2018) Comparing generative adversarial network techniques for image creation and modification. arXiv:1803.09093"},{"key":"4976_CR26","unstructured":"Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434"},{"key":"4976_CR27","unstructured":"Reed S, Akata Z, Yan X, Logeswaran L, Schiele B, Lee H (2016) Generative adversarial text to image synthesis. arXiv:1605.05396"},{"key":"4976_CR28","unstructured":"Sotelo J, Mehri S, Kumar K, Santos JF, Kastner K, Courville AC (2017) Char2wav: end-to-end speech synthesis"},{"key":"4976_CR29","unstructured":"Sutskever I, Vinyals D, Le QV (2014) Sequence to sequence learning with neural networks. In: Proceedings of the 27th international conference on neural information processing systems, vol 2, NIPS\u201914, pp 3104\u20133112"},{"key":"4976_CR30","unstructured":"van\u00a0den Oord A\u00e4, Kalchbrenner N, Kavukcuoglu K (2015) Pixel recurrent neural networks. arXiv:1601.06759"},{"key":"4976_CR31","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the 32nd international conference on machine learning, volume\u00a037 of proceedings of machine learning research, pp 2048\u20132057"},{"key":"4976_CR32","doi-asserted-by":"crossref","unstructured":"Xu T, Zhang P, Huang Q, Zhang H, Gan Z, Huang X, He X (2017) AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. arXiv:1711.10485","DOI":"10.1109\/CVPR.2018.00143"},{"key":"4976_CR33","doi-asserted-by":"crossref","unstructured":"Yan X, Yang J, Sohn K, Lee H (2016) Attribute2Image: conditional image generation from visual attributes. In: European conference on computer vision","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"4976_CR34","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy CC, Tang X (2015) From facial parts responses to face detection: a deep learning approach. In: IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2015.419"},{"key":"4976_CR35","doi-asserted-by":"crossref","unstructured":"Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas D (2017) Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. arXiv:1612.03242","DOI":"10.1109\/ICCV.2017.629"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-04976-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-04976-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-04976-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,28]],"date-time":"2021-05-28T00:31:20Z","timestamp":1622161880000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-04976-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,28]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["4976"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-04976-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,28]]},"assertion":[{"value":"15 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest in relation to this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}