We introduce "contour stencils" as a simple method for detecting the local orientation of image contours and apply this detection to image zooming. Our approach is motivated by the total variation along curves: small total variation along a candidate curve suggests that this curve is a good approximation to the contours. Furthermore, a relationship is shown between interpolation error and total variation. The contour stencil detection is used to develop two image zooming methods. The first one, "contour stencil interpolation," is simple and computationally efficient, yet competitive in a comparison against existing methods. The second method approaches zooming as an inverse problem, using a graph regularization where the graph is determined by contour stencil detection. Both methods extend naturally to vector-valued data and are demonstrated for grayscale and color images.