Fast Computation of RFD-Like Descriptors in Four Orientations

Abstract

RFD-like binary descriptors have been designed to be fast and demonstrate good quality in image-matching tasks. One of those descriptors, RFDoc, produces state-of-the art results when applied to document localization systems. However, the computational efficiency of such descriptors strongly depends on their implementation. In this study, we consider the computation of RFD-like descriptors for an 8bit single-channel image; provide a detailed implementation of the baseline algorithm; demonstrate its weak points; and propose four modifications. In those modifications, we investigate two ways to accelerate the descriptor computations: 1) compute common operations globally for the entire input image instead of computing them locally for every patch; or 2) use lookup tables to replace the most computationally demanding operations and minimize the number of conversions between integer and floating point types. Experiments on the document identification and localization task on the MIDV-2020 dataset have shown that the modifications with lookup tables are noticeably faster than the baseline, achieving a 2-2.6 times acceleration on x86 and ARM CPUs. Based on experimental results, modifications with global operations may outperform the baseline algorithm if there are many intersecting patches that require descriptor computation. We also demonstrated that one can use any of the proposed algorithms without loss of image-matching quality and without necessity to retrain the parameters of RFD-like descriptors. Finally, we propose an efficient way to compute the descriptors for four orientations of a patch, which is a important for document location systems. The proposed method reduces a common computation part for four orientations to a single run; thus, four descriptors are computed 3 times faster than the direct computation of the descriptors for four patches, as shown experimentally.

FARA: fast and accurate RFDoc descriptor approximation

“…RFDoc with fully precomputed gradient maps achieves the best performance and speed as was shown in [27], wherefore we include this method for comparison. In Table 1, we demonstrate the running time of the RFDoc, RFDoc with fully precomputed gradient maps via lookup table, FARA, and its vectorized version.…”

“…The RFDoc descriptor offers high quality, potential for fast feature matching, and straightforward inference, rendering it suitable for real-time on-device computation. The next improvement for RFD-like descriptors was proposed in Fast RFD [27] which offers various methods for fast RFD and RFDoc inference.…”