It is remarkable how well the human visual system can cope with changing viewpoints when it comes to recognising shapes. The state of the art in machine vision is still quite remote from solving such tasks. Nevertheless, a surge in invariance-based research has led to the development of methods for solving recognition problems still considered hard until recently. A nonmathematical account explains the basic philosophy and trade-offs underlying this strand of research. The principles are explained for the relatively simple case of planar-object recognition under arbitrary viewpoints. Well-known Euclidean concepts form the basis of invariance in this case. Introducing constraints in addition to that of planarity may further simplify the invariants. On the other hand, there are problems for which no invariants exist.
Get full access to this article
View all access options for this article.
References
1.
AllikJTuulmetsTVosP G, 1991“Size invariance in visual number discrimination”Psychological Research53290–295
2.
BiedermanI, 1987“Recognition-by-components: A theory of human image understanding”Psychological Review94115–147
3.
BiedermanICooperE E, 1991“Evidence for complete translational and reflectional invariance in visual object priming”Perception20585–593
4.
BrillMBarrettEPaytonP, 1992“Projective invariants for curves in two and three dimension”, in Geometric Invariance in Computer Vision Eds MundyJZissermanA (Cambridge, MA: MIT Press) pp 193–214
5.
CuttingJ E, 1983“Four assumptions about invariance in perception”Journal of Experimental Psychology: Human Perception and Performance9310–317
6.
CuttingJ E, 1986Perception with an Eye for Motion (Cambridge, MA: MIT Press)
7.
CuttingJ E, 1992“Beyond Gibson's legacies”International Journal of Psychology2715 (SY005.4)
8.
EfimovN, 1981Géométrie Supérieure (Moscow: Mir)
9.
FaugerasO, 1992“What can be seen in three dimensions with an uncalibrated stereo rig?”, in Proceedings of the Second European Conference on Computer Vision Ed. SandiniG (Berlin: Springer) p 563–578
10.
ForsythDMundyJZissermanARothwellC, 1992“Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders”, in Proceedings of the Second European Conference on Computer Vision Ed. SandiniG (Berlin: Springer) pp 639–648
11.
GibsonJ J, 1950The Perception of the Visual World (Boston, MA: Houghton Mifflin)
12.
HoffmanDRichardsW, 1984“Parts of recognition”Cognition1865–96
13.
HuttenlocherDUllmanS, 1987“Object recognition using alignment”, in Proceedings of the First International Conference on Computer Vision (Los Alamitos, CA: IEEE Computer Society Press) pp 102–111
14.
KoenderinkJvan DoornA, 1992“Affine structure from motion”Journal of the Optical Society of America A8377–385
15.
LoweD G, 1987“Three-dimensional object recognition from single two-dimensional images”Artificial Intelligence31355–395
16.
MohrRMorinLGrossoE, 1992“Relative positioning with uncalibrated cameras”, in Geometric Invariance in Computer Vision Eds MundyJZissermanA (Cambridge, MA: MIT Press) pp 440–460
17.
MoonsTPauwelsEVan GoolLOosterlinckA, 1993“Viewpoint invariant characterization of objects composed of different rigid parts: A mathematical framework”, in Geometry and Topology of Submanifoldsvolume 5 Eds DillenFVerstraelenL (Singapore: World Scientific)
18.
NazirT AO'ReganJ K, 1990“Some results on translation invariance in the human visual system”Spatial Vision581–100
19.
NiallK K, 1992“Projective invariance and the kinetic depth effect”Acta Psychologica81127–168
20.
NiallK KMacnamaraJ, 1990“Projective invariance and picture perception”Perception19637–660
21.
RothwellCForsythDZissermanAMundyJ, 1993“Extracting projective information from single views of 3D point sets”, in Proceedings of the Third International Conference on Computer Vision (Los Alamitos, CA: IEEE Computer Society Press) pp 573–582
22.
RothwellCZissermanAForsythDMundyJ, 1992a“Canonical frames for planar object recognition”, in Proceedings of the Second European Conference on Computer Vision Ed. SandiniG (Berlin: Springer) pp 757–772
23.
RothwellCZissermanAMundyJForsythD, 1992b“Efficient model library access by projectively invariant indexing functions”, in Proceedings of the Conference on Computer Vision and Pattern Recognition (Los Alamitos, CA: IEEE Computer Society Press) pp 109–114
24.
ShepardRCooperL, 1982Mental Images and their Transformations (Cambridge, MA: MIT Press)
25.
SternbergS, 1966“High-speed scanning in human memory”Science153652–654
26.
UllmanS, 1989“Aligning pictorial descriptions: An approach to object recognition”Cognition32193–254
27.
UngerleiderLMishkinM, 1982“The cortical visual systems”, in Analysis of Visual Behavior Eds IngleD JGoodaleM AMansfieldR J W (Cambridge, MA: MIT Press) pp 549–586
28.
VainaL, 1990“What and where in the human visual system: Two hierarchies of visual modules”Synthese8349–91
29.
Van DiestMVan GoolLMoonsTPauwelsE, 1994“Projective invariants for planar contour recognition”, in Proceedings of the Third European Conference on Computer Vision Ed. EklundhJ-O (Berlin: Springer) pp 527–534
30.
Van GoolLBrillMBarrettEMoonsTPauwelsE, 1992a“Semi-differential invariants for nonplanar curves”, in Applications of Invariance in Vision Eds MundyJZissermanA (Cambridge, MA: MIT Press) pp 293–309
31.
Van GoolLKempenaersPOosterlinckA, 1991“Recognition and semidifferential invariants”, in Proceedings of the Conference on Computer Vision and Pattern Recognition (Los Alamitos, CA: IEEE Computer Society Press) pp 454–460
32.
Van GoolLMoonsTPauwelsEOosterlinckA, 1992b“Semi-differential invariants”, in Applications of Invariance in Vision Eds MundyJZissermanA (Cambridge, MA: MIT Press) pp 157–192
33.
Van GoolLMoonsTPauwelsEWagemansJ, 1993a“Invariance from the Euclidean geometer's perspective”University of Leuven, technical report KUL/ESAT/MI2/9310
34.
Van GoolLMoonsTVan DiestMPauwelsE, 1993b“Matching perspective views of parallel plane structures”, in Proceedings of the NSF—Esprit Workshop on Applications of Invariance in Computer Vision II Eds MundyJZissermanA (Cambridge, MA: MIT Press) pp 351–363
35.
Van GoolLWagemansJVandeneedeJOosterlinckA, 1990“Similarity extraction and modelling”, in Proceedings of the Third International Conference on Computer Vision (Los Alamitos, CA: IEEE Computer Society Press) pp 530–534
36.
Van ZandtTTownsendJ, 1993“Self-terminating versus exhaustive processes in rapid visual and memory search: An evaluation review”Perception & Psychophysics53563–580
37.
VivianiPStucchiN, 1992“Biological movements look uniform: Evidence of motor—perceptual interactions”Journal of Experimental Psychology: Human Perception and Performance18603–623
38.
WagemansJ, 1992“Perceptual use of nonaccidental properties”Canadian Journal of Psychology46236–279
39.
WagemansJ, 1993“Skewed symmetry: A nonaccidental property used to perceive visual form”Journal of Experimental Psychology: Human Perception and Performance19364–380
40.
WagemansJVan GoolLDe TroyAFosterD HWoodJ R, 1993“Minimal information to determine affine shape equivalence”Perception (Supplement)22107–108
