In this paper we formulate a novel AND/OR graph representation capable of describing the different configurations of deformable articulated objects such as horses. The representation makes use of the summarization principle so that lower level nodes in the graph only pass on summary statistics to the higher level nodes. The probability distributions are invariant to position, orientation, and scale. We develop a novel inference algorithm that combined a bottom-up process for proposing configurations for horses together with a top-down process for refining and validating these proposals.The algorithm was applied to the tasks of detecting, segmenting and parsing horses (to the best of our knowledge, no computer vision algorithms are capable of solving all these tasks). We demonstrate that the algorithm is fast and achieves the state of the art performance (by evaluations on a challenging public dataset). Our approach can be applied to a range of other problems in machine intelligence.