Browsing Computer Science and Artificial Intelligence Lab (CSAIL) by Subject "color"

Now showing items 1-4 of 4

  • Data and Model-Driven Selection Using Color Regions 

    Unknown author (1992-02-01)
    A key problem in model-based object recognition is selection, namely, the problem of determining which regions in the image are likely to come from a single object. In this paper we present an approach that extracts ...

  • A Method for Computing Spectral Reflectance 

    Unknown author (1984-12-01)
    Psychophysical experiments show that the perceived colour of an object is relatively independent of the spectrum of the incident illumination and depends only on the surface reflectance. We demonstrate a possible ...

  • Role of color in face recognition 

    Unknown author (2001-12-13)
    One of the key challenges in face perception lies in determining the contribution of different cues to face identification. In this study, we focus on the role of color cues. Although color appears to be a salient attribute ...

  • What Makes a Good Feature? 

    Unknown author (1992-04-01)
    Using a Bayesian framework, we place bounds on just what features are worth computing if inferences about the world properties are to be made from image data. Previously others have proposed that useful features reflect ...