{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T12:10:32Z","timestamp":1772021432096,"version":"3.50.1"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Appl. Percept."],"published-print":{"date-parts":[[2006,10]]},"abstract":"<jats:p>Face recognition is one of the most important applied aspects of visual perception. To create an automated face-recognition system, the fundamental challenge is that of finding useful features. In this paper, we suggest a new class of image features that may be a useful addition to the set of representational tools for face-recognition tasks. Our proposal is motivated by the observation that rather than relying exclusively on traditional edge-based image representations, it may be useful to also employ region-based strategies that can compare noncontiguous image regions. The spatial homogeneity within regions allows for enhanced tolerance to geometric distortions and greater freedom in the choice of sample points. We first show that under certain circumstances, comparisons between spatially disjoint image regions are, on average, more valuable for recognition than features that measure local contrast. Second, we learn \u201coptimal\u201d sets of region comparisons for recognizing faces across varying pose and illumination. We propose a representational primitive---the dissociated dipole---that permits an integration of edge-based and region-based representations. This primitive is then evaluated using the FERET database of face images and then compared to established local and global algorithms.<\/jats:p>","DOI":"10.1145\/1190036.1190038","type":"journal-article","created":{"date-parts":[[2007,1,16]],"date-time":"2007-01-16T19:38:29Z","timestamp":1168976309000},"page":"354-375","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Region-based representations for face recognition"],"prefix":"10.1145","volume":"3","author":[{"given":"Benjamin J.","family":"Balas","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, Massachusetts"}]},{"given":"Pawan","family":"Sinha","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, Massachusetts"}]}],"member":"320","published-online":{"date-parts":[[2006,10]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1017\/S0952523800007331","article-title":"Contrast coding by cells in the cat's striate cortex: Monocular vs. binocular detection","volume":"12","author":"Anzai A.","year":"1995","journal-title":"Visual Neuroscience"},{"key":"e_1_2_1_2_1","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1037\/h0054663","article-title":"Some informational aspects of visual perception","volume":"61","author":"Attneave F.","year":"1954","journal-title":"Psychol. Rev."},{"key":"e_1_2_1_3_1","unstructured":"Balas B. and Sinha P. (in press). Receptive field structures for recognition. Neural Computation. 10.1162\/089976606775623315   Balas B. and Sinha P. (in press). Receptive field structures for recognition. Neural Computation. 10.1162\/089976606775623315"},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the SPIE, Vol 3299: Conference on Human Vision and Electronic Imaging III. 528--539","author":"Bartlett M."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.598228"},{"key":"e_1_2_1_6_1","doi-asserted-by":"crossref","first-page":"3327","DOI":"10.1016\/S0042-6989(97)00121-1","article-title":"The \u201cindependent components\u201d of natural scenes are edge filters","volume":"37","author":"Bell A. J.","year":"1997","journal-title":"Vision Research"},{"key":"e_1_2_1_7_1","first-page":"535","article-title":"A nonparametric statistical comparison of principal component and linear discriminant subspaces for face recognition","volume":"3","author":"Beveridge J. R.","year":"2001","journal-title":"Proc. IEEE Conf. CVPR"},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","article-title":"Recognition-by-components: A theory of human image understanding","volume":"94","author":"Biederman I.","year":"1987","journal-title":"Psychological Review"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/0010-0285(88)90024-2","article-title":"Surface vs. edge-based determinants of visual recognition","volume":"20","author":"Biederman I.","year":"1988","journal-title":"Cognitive Psychology"},{"key":"e_1_2_1_10_1","volume-title":"International Conference on Vision Systems. Springer-Verlag","author":"Bolme D."},{"key":"e_1_2_1_11_1","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1016\/0042-6989(94)00286-U","article-title":"Object representation by cores: Identifying and representing primitive spatial regions","volume":"35","author":"Burbeck C. A.","year":"1995","journal-title":"Vision Research"},{"key":"e_1_2_1_12_1","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1167\/5.9.1","article-title":"Accurate statistical tests for smooth classification images","volume":"5","author":"Chauvin A.","year":"2005","journal-title":"J. Vis."},{"key":"e_1_2_1_13_1","first-page":"254","article-title":"In search of illumination invariants Proc","volume":"2","author":"Chen H. F.","year":"2000","journal-title":"IEEE Conf. CVPR"},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1068\/p3393","article-title":"Comparison at a distance","volume":"32","author":"Danilova M. V.","year":"2003","journal-title":"Perception"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1152\/jn.1993.69.4.1091","article-title":"Spatiotemporal organization of simple-cell receptive fields in the cat's striate cortex. I. General characteristics and postnatal development","volume":"69","author":"Deangelis G. C.","year":"1993","journal-title":"J. Neurophysiology"},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1364\/JOSAA.2.001160","article-title":"Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters","volume":"2","author":"Daugman J. G.","year":"1985","journal-title":"J. Opt. Soc. Am. A"},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1037\/0021-9010.63.2.180","article-title":"Face recognition accuracy as a function of mode of representation","volume":"63","author":"Davies G.","year":"1978","journal-title":"Journal of Applied Psychology"},{"key":"e_1_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Field D. J. 1994. What is the goal of sensory coding&quest; Neural Computation 6 559--601. 10.1162\/neco.1994.6.4.559   Field D. J. 1994. What is the goal of sensory coding&quest; Neural Computation 6 559--601. 10.1162\/neco.1994.6.4.559","DOI":"10.1162\/neco.1994.6.4.559"},{"key":"e_1_2_1_19_1","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1016\/S0042-6989(01)00097-9","article-title":"Bubbles: A technique to reveal the use of information in recognition tasks","volume":"41","author":"Gosselin F.","year":"2001","journal-title":"Vision Research"},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1364\/JOSAA.4.002395","article-title":"Predicability and redundancy of natural images","volume":"4","author":"Kersten D.","year":"1987","journal-title":"Journal of the Optical Society of America A"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Kohly R. P. and Regan D. 2000. Coincidence detectors: Visual processing of a pair of lines and implications for shape discrimination.Vision Research 40 17 2291--2306.  Kohly R. P. and Regan D. 2000. Coincidence detectors: Visual processing of a pair of lines and implications for shape discrimination.Vision Research 40 17 2291--2306.","DOI":"10.1016\/S0042-6989(00)00090-0"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.210173"},{"key":"e_1_2_1_23_1","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1068\/p250355","article-title":"Line drawings of faces reduce configural processing","volume":"25","author":"Leder H.","year":"1996","journal-title":"Perception"},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1068\/p281171","article-title":"Matching person identity from facial line drawings","volume":"28","author":"Leder H.","year":"1999","journal-title":"Perception"},{"key":"e_1_2_1_25_1","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.1038\/nn1121","article-title":"Expert face processing requires visual input to the right hemisphere during infancy","volume":"6","author":"Le Grand R.","year":"2003","journal-title":"Nature Neuroscience"},{"key":"e_1_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Malik J. Belongie S. Shi J. and Leung T. K. 1999. Textons contours and regions: Cue integration in image segmentation ICCV. 918--925   Malik J. Belongie S. Shi J. and Leung T. K. 1999. Textons contours and regions: Cue integration in image segmentation ICCV. 918--925","DOI":"10.1109\/ICCV.1999.790346"},{"key":"e_1_2_1_27_1","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1016\/S0031-3203(99)00179-X","article-title":"Bayesian face recognition","volume":"333","author":"Moghaddam B.","year":"2000","journal-title":"Pattern Recognition"},{"key":"e_1_2_1_28_1","unstructured":"Nakayama K. He Z. J. and Shimojo S. 1995. Visual surface representation: A critical link between lower-level and higher-level vision. In An Invitation to Cognitive Science Visual Cognition S. M. Kosslyn and D. N. Oshershon Eds. MIT Press Cambridge MA.  Nakayama K. He Z. J. and Shimojo S. 1995. Visual surface representation: A critical link between lower-level and higher-level vision. In An Invitation to Cognitive Science Visual Cognition S. M. Kosslyn and D. N. Oshershon Eds. MIT Press Cambridge MA."},{"key":"e_1_2_1_29_1","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"Olshausen B. A.","year":"1996","journal-title":"Nature, London"},{"key":"e_1_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Olshausen B. A. and Field D. J. 1997. Sparse coding with an overcomplete basis set: A strategy employed by V1&quest; Vision Research 37 23 3311--3325.  Olshausen B. A. and Field D. J. 1997. Sparse coding with an overcomplete basis set: A strategy employed by V1&quest; Vision Research 37 23 3311--3325.","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"e_1_2_1_31_1","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.1364\/JOSAA.7.002032","article-title":"Contrast in complex images","volume":"7","author":"Peli E.","year":"1990","journal-title":"J. Opt. Soc. Am. A"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.879790"},{"key":"e_1_2_1_33_1","unstructured":"Sadr J. Mukherjee S. Thoresz K. and Sinha P. 2002. The fidelity of local ordinal encoding. In Advances in Neural Information Processing Systems 14. T. Dietterich S. Becker and Z. Ghahramani Eds. MIT Press. Cambridge MA.  Sadr J. Mukherjee S. Thoresz K. and Sinha P. 2002. The fidelity of local ordinal encoding. In Advances in Neural Information Processing Systems 14. T. Dietterich S. Becker and Z. Ghahramani Eds. MIT Press. Cambridge MA."},{"key":"e_1_2_1_34_1","unstructured":"Samaria F. and Harter A. 1994. Parametrisation of a stochastic model for human face identification. Paper presented at the 2nd IEEE Workshop on Applications of Computer Vision Sarasota FL.  Samaria F. and Harter A. 1994. Parametrisation of a stochastic model for human face identification. Paper presented at the 2nd IEEE Workshop on Applications of Computer Vision Sarasota FL."},{"key":"e_1_2_1_35_1","volume-title":"Proc. SPIE Electronic Imaging Symp. 4662","author":"Sinha P.","year":"2002"},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Sinha P. 2002b. Qualitative representations for recognition. Lecture Notes in Computer Science vol. 2525. Springer-Verlag New York 249--262.   Sinha P. 2002b. Qualitative representations for recognition. Lecture Notes in Computer Science vol. 2525. Springer-Verlag New York 249--262.","DOI":"10.1007\/3-540-36181-2_25"},{"key":"e_1_2_1_37_1","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1007\/3-540-36181-2_64","article-title":"Component and configural information in face recognition","volume":"2525","author":"Schwaninger A.","year":"2002","journal-title":"Lecture Notes Computer Science"},{"key":"e_1_2_1_38_1","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1111\/1467-9280.00472","article-title":"Show me the features&excl; Understanding recognition from the use of visual information","volume":"13","author":"Schyns P. G.","year":"2002","journal-title":"Psychological Science"},{"key":"e_1_2_1_39_1","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","article-title":"Eigenfaces for recognition","volume":"3","author":"Turk M. A.","year":"1991","journal-title":"Journal of Cognitive Neuroscience"},{"key":"e_1_2_1_40_1","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1038\/nn870","article-title":"Visual features of intermediate complexity and their use in classification","volume":"5","author":"Ullman S.","year":"2002","journal-title":"Nature Neuroscience"},{"key":"e_1_2_1_41_1","unstructured":"Viola P. and Jones M. 2001. Rapid object detection using a boosted cascade of simple features. Paper presented at the Accepted Conference on Computer Vision and Pattern Recognition.  Viola P. and Jones M. 2001. Rapid object detection using a boosted cascade of simple features. Paper presented at the Accepted Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.598235"},{"key":"e_1_2_1_43_1","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1068\/p3376","article-title":"Role of color in face recognition","volume":"31","author":"Yip A.","year":"2002","journal-title":"Perception"},{"key":"e_1_2_1_44_1","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1163\/156856801753253582","article-title":"The Gaussian derivative model for spatial-temporal vision: I. Cortical model","volume":"14","author":"Young R. A.","year":"2001","journal-title":"Spatial Vision"},{"key":"e_1_2_1_45_1","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1163\/156856801753253582","article-title":"The Gaussian derivative model for spatial-temporal vision: II. Cortical data","volume":"14","author":"Young R. A.","year":"2001","journal-title":"Spatial Vision"}],"container-title":["ACM Transactions on Applied Perception"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1190036.1190038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T17:51:31Z","timestamp":1672249891000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1190036.1190038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,10]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2006,10]]}},"alternative-id":["10.1145\/1190036.1190038"],"URL":"https:\/\/doi.org\/10.1145\/1190036.1190038","relation":{},"ISSN":["1544-3558","1544-3965"],"issn-type":[{"value":"1544-3558","type":"print"},{"value":"1544-3965","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,10]]},"assertion":[{"value":"2006-10-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}