A system described herein may allow for the enhanced identification of candidate images that are similar to a reference image. For example, a primary focus and one or more secondary foci may be identified in the reference image (where a “focus” corresponds to a visual feature of the reference image). Characteristics (e.g., size, shape, color, etc.) of the secondary foci may be identified. Positional relationships of the secondary foci to the primary focus may also be identified. Candidate images may be scored based on whether they include the primary focus and one or more secondary foci, as well as whether the secondary foci match the characteristics and/or positional relationships of corresponding secondary foci in the reference image.