“…Some research efforts have attempted to construct a part of object recognition programs, e.g., feature extractor [19], [20], [25], [42], [48], [50], edge detector [49] or interest point detector [22], [23], [26], while some researchers focus on construction of complete object recognition programs [5], [28], [34], [35], [38]. Also various image processing tasks have been studied, e.g., classification [19], [20], segmentation [31], [32], [35], [44], image retrieval [2], or texture analysis [4]. In this work, we focus on automatic construction of feature extraction programs (FEPs) for an image segmentation task.…”