COLOR CONSTANT COLOR INDEXING

被引:353
作者
FUNT, BV
FINLAYSON, GD
机构
[1] School of Computing Science, Simon Fraser University, Vancouver, B.C.
基金
美国国家科学基金会; 加拿大自然科学与工程研究理事会;
关键词
COLOR INDEXING; COLOR CONSTANCY; RETINEX; OBJECT RECOGNITION;
D O I
10.1109/34.391390
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Objects can be recognized on the basis of their color alone by color indexing, a technique developed by Swain and Ballard [15] which involves matching color-space histograms. Color indexing fails, however, when the incident illumination varies either spatially or spectrally. Although this limitation might be overcome by preprocessing with a color constancy algorithm, we instead propose histogramming color ratios. Since the ratios of color RGB triples from neighboring locations are relatively insensitive to changes in the incident illumination, this circumvents the need for color constancy preprocessing. Results of tests with the new color-constant-color-indexing algorithm on synthetic and real images show that it works very well even when the illumination varies spatially in its intensity and color.
引用
收藏
页码:522 / 529
页数:8
相关论文
共 17 条
[1]   THE PROBABILISTIC PEAKING EFFECT OF VIEWED ANGLES AND DISTANCES WITH APPLICATION TO 3-D OBJECT RECOGNITION [J].
BENARIE, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (08) :760-774
[2]  
BINFORD TO, 1989, UNCERTAINTY ARTIFICI, V3, P73
[3]  
BRIMSON WEL, 1990, P INT C COMPUTER VIS, P334
[4]   VIEW VARIATION OF POINT-SET AND LINE-SEGMENT FEATURES [J].
BURNS, JB ;
WEISS, RS ;
RISEMAN, EM .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (01) :51-68
[5]   SPACE AND TIME-BOUNDS ON INDEXING 3-D MODELS FROM 2-D IMAGES [J].
CLEMENS, DT ;
JACOBS, DW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (10) :1007-1017
[6]   RANDOM SAMPLE CONSENSUS - A PARADIGM FOR MODEL-FITTING WITH APPLICATIONS TO IMAGE-ANALYSIS AND AUTOMATED CARTOGRAPHY [J].
FISCHLER, MA ;
BOLLES, RC .
COMMUNICATIONS OF THE ACM, 1981, 24 (06) :381-395
[7]  
Forstner W., 1987, P ISPRS INT C FAST P, P281
[8]  
FORSTNER W, 1993, COMPUTER ROBOT VISIO, V2, pCH16
[9]   INVARIANT DESCRIPTORS FOR 3-D OBJECT RECOGNITION AND POSE [J].
FORSYTH, D ;
MUNDY, JL ;
ZISSERMAN, A ;
COELHO, C ;
HELLER, A ;
ROTHWELL, C .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (10) :971-991
[10]  
GRIMSON W, 1992, P EUROPEAN C COMPUTE, P291