The visual system is very efficient in encoding stimulus properties. To explore the underlying encoding strategies in the early stages of visual information processing, we presented participants with L-, T-, and X-junctions in a functional magnetic resonance imaging (fMRI) experiment. For each junction type, we manipulated the amount of configuration regularity (or degrees of constraint), ranging from a generic junction configuration to stimuli resembling an ‘L’ (i.e., a right angle L-junction), a ‘T’ (i.e., a right angle midpoint T-junction), or a ‘+’. We found that the response strength in the shape-selective lateral occipital area was consistently lower for a higher degree of regularity in the stimuli. In the second experiment, using multivoxel pattern analysis we further show that regularity is encoded in terms of the fMRI signal strength but not in the distributed pattern of responses. Finally, we found that the results of these experiments could not be accounted for by two well-known theoretical proposals for constructing stimulus interpretation, namely, the Structural Information Theory and the Minimal Model Theory, at least not without additional assumptions in those theories. Our results suggest that regularity plays an important role in stimulus encoding in the ventral visual processing stream.