Abstract: An image is analyzed to locate an object appearing in the image. A contour of that object is extracted from the image and normalized. Based on the normalized contour, one or more summation invariant values are determined and compared to templates comprising one or more summation invariants for each of one or more target objects. The determined summation invariants for the extracted object are compared to summation invariants for the target objects. When the summation invariants for the extracted object sufficiently match the summation invariants determined from an image of a target object, the extracted object is recognized as that target object. The summation invariants can be semi-local summation invariants determined for each point along the normalized contour, based on a number of points neighboring that point on the normalized contour. The semi-local summation invariants are determined as a function of the x and y coordinates of those points.

Abstract: An image is analyzed to locate an object appearing in the image. A contour of that object is extracted from the image and normalized. Based on the normalized contour, one or more summation invariant values are determined and compared to templates comprising one or more summation invariants for each of one or more target objects. The determined summation invariants for the extracted object are compared to summation invariants for the target objects. When the summation invariants for the extracted object sufficiently match the summation invariants determined from an image of a target object, the extracted object is recognized as that target object. The summation invariants can be semi-local summation invariants determined for each point along the normalized contour, based on a number of points neighboring that point on the normalized contour. The semi-local summation invariants are determined as a function of the x and y coordinates of those points.