Status Quo For Object Categorization
The recognition of object categories in images is a challenging problem in computer vision, especially when the number of categories is large. This is due to high intra class variability and the need for generalization across variations of objects within the same category. Objects within one category may look quite different. Even the same object may appear unalike under different viewpoint, scale, and illumination. Background clutter and partial occlusion add difficulties to recognition as well. Humans are able to recognize thousands of object types, whereas most of the existing object recognition systems are trained to recognize only a few, e.g., human face, car, simple objects, etc. Research has been very active on dealing with more categories and enabling incremental additions of new categories, and although the general problem remains unsolved, several multi-category objects detectors (number of categories around 20) for clustered scenes have been developed. One means is by feature sharing and boosting.
Read more about this topic: Boosting Methods For Object Categorization
Famous quotes containing the words status, quo and/or object:
“The influx of women into paid work and her increased power raise a woman’s aspirations and hopes for equal treatment at home. Her lower wage and status at work and the threat of divorce reduce what she presses for and actually expects.”
—Arlie Hochschild (20th century)
“Any woman who chooses to behave like a full human being should be warned that the armies of the status quo will treat her as something of a dirty joke. That’s their natural and first weapon. She will need her sisterhood.”
—Gloria Steinem (b. 1934)
“Parenthood is not an object of appetite or even desire. It is an object of will. There is no appetite for parenthood; there is only a purpose or intention of parenthood.”
—R.G. (Robin George)