An apparatus includes a detection unit configured to detect, from an image obtained by capturing a predetermined object, one or more indicated positions indicated by the predetermined object, an extraction unit configured to extract, from the image, feature information indicating a state of the predetermined object, the feature information being different from the indicated positions, a first recognition unit configured to recognize, based on a change in a positional relationship between two or more of the indicated positions, an operation to be input to the apparatus, a second recognition unit configured to, based on a change in the feature information, recognize an operation to be input to the apparatus, and an output unit configured to output either one of recognition results of the first recognition unit and the second recognition unit, the either one of recognition results being selected based on a shift of a number of the indicated positions.