Konstantin Bulatov

Document image rectification problem is crucial in document analysis. Most of the current state-of-the-art methods addressing it are data-driven and rely on neural network approaches. However, despite satisfactory rectifications, such methods’ time performance is poor, making them unsuitable for mobile on-device acquisition. The present work concentrates on a specific (but common) case of document physical distortion – the documents with a single crease.We investigate the properties of a surface comprised of two planes captured by a pinhole camera. Namely, we provide the methods to obtain the transformation between such an image and the template image having successfully localized the document in a frame. It can be utilized in on-device recognition systems: it takes only 3 ms to estimate transformation parameters and about a quarter of a second to rectify an image on a smartphone CPU. We propose a novel dataset FDI-AC containing 200 real images of documents with a single crease in different positions. We conduct experiments comparing our approach with current state-of-the-art setting a baseline performance on FDI-AC. These experiments show that the proposed algorithm outperforms image rectification transformer network GeoTr in rectification accuracy and time performance.

Monitored tomographic reconstruction (MTR) is a potentially powerful tool for dose and time reduction in computed tomography scanning. We are the first to study the issue of practical implementation of MTR protocols in current-generation real-life instruments. We propose an empirical quantitative model for calculating acquisition and reconstruction times. It is demonstrated that projection acquisition order has a significant impact on the time and dose of tomographic experiments. The new alternative acquisition most suitable for MTR protocols is proposed. To estimate the restrictions and scope of applicability for MTR four typical commercial setups are studied within a proposed model. We construct an experimental stand for achieving a real-time reconstruction, together with validation of the proposed acquisition time model. We demonstrate that real-time reconstruction may be implemented without slowing down an acquisition process. An optimization of reconstruction from partial data is proposed, which allowed the production of 385 and 440 reconstructions for standard and proposed acquisition orders correspondingly during a single acquisition of 512 projections. The results of the study demonstrate that with proposed optimizations MTR can be effectively utilized for practical applications using the current generation of existing setups in industrial and nano tomography fields.

This paper considers a scientific school of synthesis of samples and creation of datasets, which is a part of the family of scientific schools associated with image processing and analysis, originating from the work of a team led by Prof. V.L. Arlazarov in the 1970s. As part of the work of the school, the researchers have obtained important fundamental and applied results as well as set new research tasks. Over the years of the school’s existence the scientific team has developed several algorithms and systems for the synthesis and augmentation of image samples. Moreover, they have created and published more than ten open annotated image datasets, including the unique MIDV dataset family that contains synthesized images of identity documents and is the first in the world to allow a full open comparison of recognition systems for such documents.

This paper focuses on the computational optimization of RANSAC. We describe the Parallel Efficient Sample Consensus (PESAC) framework that allows efficient utilization of SIMD extensions and provides memory locality due to a special way of storing the input sequence of correspondences and generating a batch of samples per one main loop iteration. It is inspired by the USAC framework and has a block structure capable of implementing most modern RANSAC-based methods. We enhance it with individual blocks of sample and model restrictors that are aimed at the rejection of “bad” samples and model hypothesis before time-consuming model computation and verification blocks. We also provide a detailed description implementing 2D homography estimation problem in PESAC and benchmark the running time on the MIDV-2020 dataset of identity documents. Comparing to naive implementation, we accelerated our framework by 122 times for the document classification task (with a 6 % increase in accuracy) and by 18 times for document tracking (with a 46 % decrease in tracking failure rate) by using both restrictors and vector processing. This version also outperformed a number of USAC implementations from OpenCV-4.6.0 in runtime and accuracy of estimation (3 times faster, 6 % greater accuracy for the classification task, and 2 times faster, 33 % lower failure rate for tracking if comparing with USAC_MAGSAC).

Text recognition has benefited considerably from deep learning research, as well as the preprocessing methods included in its workflow. Identity documents are critical in the field of document analysis and should be thoroughly researched in relation to this workflow. We propose to examine the link between deep learning-based binarization and recognition algorithms for this sort of documents on the MIDV-500 and MIDV-2020 datasets. We provide a series of experiments to illustrate the relation between the quality of the collected images with respect to the binarization results, as well as the influence of its output on final recognition performance. We show that deep learning-based binarization solutions are affected by the capture quality, which implies that they still need significant improvements. We also show that proper binarization results can improve the performance for many recognition methods. Our retrained U-Net-bin outperformed all other binarization methods, and the best result in recognition was obtained by Paddle Paddle OCR v2.

One of the challenges present in the field of tomographic imaging is the reduction of the radiation dose imparted to the object. Monitored reconstruction is one of the approaches to reduce the dose by means of dynamic stopping of the scanning process. In this paper, analysis was performed for the RSRE-based stopping rules for monitored reconstruction, using the previously analyzed RSRE-based reconstruction quality metrics, a widely-used PSNR metric, as well as quality metrics designed to mimic human perception, such as SSIM and ISSIM. It was shown that the unnormalized RSRE-based stopping rule performs better than the baseline for SSIM, ISSIM, and PSNR, and that for the latter the best result was achieved using the stopping rule designed for the reconstruction quality metric normalized to the Radon invariant. The stopping rules were compared with a synthetic a-posteriori “perfect” stopping rule and it was shown that the RSRE-based stopping rules closely approach the perfect stopping rule for the RSRE metric normalized on the Radon invariant, as well as for the ISSIM metric.