Much effort has recently been invested in developing methods for determining the ancestral origin of chromosomal segments in admixed individuals. Motivations for this task are the study of population history such as bottleneck effects and migration, the assessment of population stratification for adequate adjustment of association studies, and the enhancement of mapping by admixture linkage disequilibrium (MALD). In this article, we present a novel framework for the inference of ancestry at each chromosomal location. The uniqueness of our method stems from the ability to incorporate complex probability models that account for linkage-disequilibrium in the ancestral populations. We provide an inference algorithm that is polynomial in the number of markers even though the underlying problem seems to be inherently exponential in nature. We demonstrate the validity of our model and conclude that, with sufficient ancestral haplotypes, this framework can provide higher accuracy in inferring ancestral origin.