{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T14:26:34Z","timestamp":1774880794922,"version":"3.50.1"},"reference-count":17,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T00:00:00Z","timestamp":1550102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Representative input data are a necessary requirement for the assessment of machine-vision systems. For symmetry-seeing machines in particular, such imagery should provide symmetries as well as asymmetric clutter. Moreover, there must be reliable ground truth with the data. It should be possible to estimate the recognition performance and the computational efforts by providing different grades of difficulty and complexity. Recent competitions used real imagery labeled by human subjects with appropriate ground truth. The paper at hand proposes to use synthetic data instead. Such data contain symmetry, clutter, and nothing else. This is preferable because interference with other perceptive capabilities, such as object recognition, or prior knowledge, can be avoided. The data are given sparsely, i.e., as sets of primitive objects. However, images can be generated from them, so that the same data can also be fed into machines requiring dense input, such as multilayered perceptrons. Sparse representations are preferred, because the author\u2019s own system requires such data, and in this way, any influence of the primitive extraction method is excluded. The presented format allows hierarchies of symmetries. This is important because hierarchy constitutes a natural and dominant part in symmetry-seeing. The paper reports some experiments using the author\u2019s Gestalt algebra system as symmetry-seeing machine. Additionally included is a comparative test run with the state-of-the-art symmetry-seeing deep learning convolutional perceptron of the PSU. The computational efforts and recognition performance are assessed.<\/jats:p>","DOI":"10.3390\/sym11020227","type":"journal-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T11:54:13Z","timestamp":1550145253000},"page":"227","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Estimating Efforts and Success of Symmetry-Seeing Machines by Use of Synthetic Data"],"prefix":"10.3390","volume":"11","author":[{"given":"Eckart","family":"Michaelsen","sequence":"first","affiliation":[{"name":"Fraunhofer-IOSB, Gutleuthausstr. 1, 76375 Ettlingen, Germany"}]},{"given":"St\u00e9phane","family":"Vujasinovic","sequence":"additional","affiliation":[{"name":"Fraunhofer-IOSB, Gutleuthausstr. 1, 76375 Ettlingen, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2019,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Funk, C., and Liu, Y. (2017, January 22\u201329). Beyond Planar Symmetry: Modelling Human Perception of Reflection and Rotation Symmetry in the Wild. Proceedings of the IEEE ICCV 2017, Venice, Italy.","DOI":"10.1109\/ICCV.2017.92"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Loy, G., and Eklundh, J. (2006, January 7\u201313). Detecting Symmetry and Symmetric Constellations of Features. Proceedings of the ECCV, Graz, Austria.","DOI":"10.1007\/11744047_39"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Desolneux, A., Moisan, L., and Morel, J.-M. (2008). From Gestalt Theory to Image Analysis: A Probabilistic Approach, Springer.","DOI":"10.1007\/978-0-387-74378-3"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Michaelsen, E., and Meidow, J. (2019). Advances in Computer Vision and Pattern Recognition. Hierarchical Perceptual Grouping for Object Recognition, Springer.","DOI":"10.1007\/978-3-030-04040-6"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pizlo, Z., Li, Y., Sawada, T., and Steinman, R.M. (2014). Making a Machine that Sees Like Us, Oxford University Press.","DOI":"10.1093\/acprof:oso\/9780199922543.001.0001"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Grenander, U. (1993). General Pattern Theory, Oxford University Press.","DOI":"10.1093\/oso\/9780198536710.001.0001"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"566","DOI":"10.3390\/sym6030566","article-title":"Gestalt algebra\u2014A proposal for the formalization of gestalt perception and rendering","volume":"6","author":"Michaelsen","year":"2014","journal-title":"Symmetry"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1134\/S1054661814040154","article-title":"Simple gestalt algebra","volume":"24","author":"Michaelsen","year":"2014","journal-title":"Pattern Recognit. Image Anal."},{"key":"ref_9","unstructured":"Funk, C. (2019, January 31). Beyond Planar Symmetry, Architecture and weights of the Caffee model based on deep Lab V2. Available online: http:\/\/vision.cse.psu.edu\/research\/beyondPlanarSymmetry\/index.shtml."},{"key":"ref_10","unstructured":"Chen, L.C., Yang, Y., Wang, J., Xu, W., and Yuille, A.L. (July, January 26). Attention to Scale: Scale-aware Semantic Image Segmentation. Proceedings of the CVPR, Las Vegas, NV, USA."},{"key":"ref_11","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very Depp Convolutional Networks for Large-scale Image Recognition. Proceedings of the ICLR, San Diego, CA, USA."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1134\/S1054661812030066","article-title":"An accumulating interpreter for cognitive vision production systems","volume":"22","author":"Michaelsen","year":"2012","journal-title":"Pattern Recognit.Image Anal."},{"key":"ref_13","unstructured":"(2018, December 26). Symmetry Detection from Real World Images\u2014A Competition. Available online: http:\/\/vision.cse.psu.edu\/research\/symmComp\/index.shtml."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, J., Slota, G., Zheng, G., Wu, Z., Park, M., Lee, S., Rauschert, I., and Liu, Y. (2013, January 23\u201328). Symmetry Detection from Real World Images, Competition 2013: Summary and Results. Proceedings of the CVPR 2013, Portland, OR, USA.","DOI":"10.1109\/CVPRW.2013.155"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Funk, C., Lee, S., Oswald, M.R., Tsokas, S., Shen, W., Cohen, A., Dickinson, S., and Liu, Y. (2017, January 22\u201329). 2017 ICCV Challenge: Detecting Symmetry in the Wild. Proceedings of the IEEE ICCV 2017, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.198"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.isprsjprs.2016.02.002","article-title":"Algebraic reasoning for the enhancement of data-driven building reconstruction","volume":"114","author":"Meidow","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_17","unstructured":"Funk, C. Personal communication."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/11\/2\/227\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:32:11Z","timestamp":1760185931000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/11\/2\/227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,14]]},"references-count":17,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,2]]}},"alternative-id":["sym11020227"],"URL":"https:\/\/doi.org\/10.3390\/sym11020227","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,14]]}}}