This paper deals with monoscopic object extraction from digital imagery by least squares template matching. We present a globally enforced least squares template matching method, constrained by internal shape forces, for automatic precise geometric identification and registration of object outlines. This is a highly localized operation, and as such, it can be affected by gaps in the edge representation, occlusions, radiometric noise, and other artifacts. To bypass this problem, the method is extended to an object-wise global level by being performed simultaneously for the complete outline of a single object. The template matching least squares solutions for different edge segments along the outline of an object are tied together by using a geometric coherence condition which expresses the a priori acceptable shape behavior of this object. Finally, we discuss the use of the presented technique within a semi-automated monoplotting strategy for GIS object extraction.