Surface reflectance and illumination level, which are confounded in the retinal image. must be disentangled by the visual system and a theory of lightness must explain how. Thus, a theory of surface lightness should also be a theory of perceived illumination and describe the relationship between them. Perceived illumination and perceived gray values have been measured using a new technique. Looking into a vision tunnel, observers saw two square apertures in the far wall, each revealing a patch of wall composed of two shades of gray. They adjusted the illumination level in one aperture to match that in the other. The stimuli placed in the apertures varied in luminance range. spatial frequency, and relative area. Results show that (a) illumination is matched for highest luminance (with no effect of spatial frequency). Combined with earlier findings that lightness is anchored by highest luminance, this supports Koffka's suggestion that lightness and perceived illumination are coupled in an invariant way. (b) Changes in the relative area of the light and dark shades produced complementary influences on perceived illumination and surface lightness. That is, when stimulus conditions evoke a conflict between anchoring the highest luminance at white and anchoring the largest area at white, enlarging the darker shade causes its lightness to increase and the perceived illumination to decrease by the same amount, further supporting Kafka. (c) These findings allow perceived illumination level to now be systematically incorporated into anchoring theory, which until this point has been solely a theory of surface lightness.
