ON LEARNING TO RECOGNIZE 3-D OBJECTS FROM EXAMPLES

被引：10

作者：

EDELMAN, S

机构：

[1] Department of Applied Mathematics and Computer Science, Weizmann Institute of Science, Rehovot

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1993年 / 15卷 / 08期

关键词：

COMPLEXITY; LEARNING FROM EXAMPLES; OBJECT RECOGNITION; REPRESENTATION; VISION;

D O I：

10.1109/34.236244

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Previous results on nonlearnability of visual concepts relied on the assumption that such concepts are represented as sets of pixels [1]. This correspondence uses an approach developed by Haussler [2] to show that under an alternative, feature-based representation, recognition is PAC learnable from a feasible number of examples in a distribution-free manner.

引用

页码：833 / 837

页数：5

共 25 条

[1] SURFACE VERSUS EDGE-BASED DETERMINANTS OF VISUAL RECOGNITION
BIEDERMAN, I
JU, G
[J]. COGNITIVE PSYCHOLOGY, 1988, 20 (01) : 38 - 64
[2] LEARNABILITY AND THE VAPNIK-CHERVONENKIS DIMENSION
BLUMER, A
EHRENFEUCHT, A
HAUSSLER, D
WARMUTH, MK
[J]. JOURNAL OF THE ACM, 1989, 36 (04) : 929 - 965
[3] THE LIE TRANSFORMATION GROUP MODEL OF VISUAL-PERCEPTION
DODWELL, PC
[J]. PERCEPTION & PSYCHOPHYSICS, 1983, 34 (01): : 1 - 16
[4] A SELF-ORGANIZING MULTIPLE-VIEW REPRESENTATION OF 3D OBJECTS
EDELMAN, S
WEINSHALL, D
[J]. BIOLOGICAL CYBERNETICS, 1991, 64 (03) : 209 - 219
[5] EDELMAN S, 1991, CSTR10 WEIZM I SCI
[6] EDELMAN S, 1992, ANN STAT, V6, P37
[7] GOIROSI F, 1990, AI1164 MIT ART INT L
[8] GRIMSON WEL, 1981, IMAGES SURFACES
[9] HAUSSLER D, 1989, USCSCRL8930 U CAL
[10] 3-DIMENSIONAL OBJECT RECOGNITION FROM SINGLE TWO-DIMENSIONAL IMAGES
LOWE, DG
[J]. ARTIFICIAL INTELLIGENCE, 1987, 31 (03) : 355 - 395

← 1 2 3 →