In this paper, a feature extraction method for offline signature verification is presented that harnesses the power of sparse representation (SR) in order to deliver state-of-the-art verification performance in several signature datasets like CEDAR, MCYT-75, GPDS, and UTSIG. Beyond the accuracy improvements, several major parameters associated with SR; such as selected configuration, dictionary size, sparsity level, and positivity priors are investigated. Besides, it is evinced that second-order statistics of the sparse codes is a powerful pooling function for the formation of the global signature descriptor. Also, a thorough evaluation of the effects of preprocessing is introduced by an automated algorithm in order to select the optimum thinning level. Finally, a segmentation strategy which employs a special form of spatial pyramid tailored to the problem of SR is presented along with the enhancing of the produced descriptor on meaningful areas of the signature as emerged from the binary robust invariant scalable key-point detection mechanism. The obtained state-of-the-art results on the most challenging signature datasets provide a strong indication toward the benefits of learned features, even in writer dependent scenarios with a unique model for each writer and only a few available reference samples of him/her.