This work is devoted to an identity document recognition system design for use in mobile phones and tablets using the computational capabilities of the device itself. Key differences are discussed in relation to conservative cloud recognition systems which commonly use single images as an input by design. A mobile recognition system chart is presented which is constructed with computational limitations in mind and which is implemented in a commercial solution. An original approach designed to improve recognition precision and reliability using post-OCR results integration in video stream, as opposed to approaches which rely on frame image integration using "super-resolution" algorithms. An interactive feedback between the system and its operator is discussed, such as automatic video stream recognition stopping decision. Experimental results are presented for an implemented commercial system "Smart IDReader" designed for identity documents recognition.

The paper describes the problem of stopping the text field recognition process in a video stream, which is a novel problem, particularly relevant to real-time mobile document recognition systems. A decision-theoretic framework for this problem is provided, and similarities with existing stopping rule problems are explored. Following the theoretical works on monotone stopping rule problems, a strategy is proposed based on thresholding the estimation of the expected difference between consequent recognition results. The efficiency of this strategy is evaluated on an openly accessible dataset. The results show that this method outperforms the previously published methods based on identical results cluster size thresholding. Notes on future work include incorporation of recognition result confidence estimations in the proposed model and more precise evaluation of the observation cost.

Computed tomography is an important technique for non-destructive analysis of an object’s internal structure, relevant for scientific studies, medical applications, and industry. Pressing challenges emerging in the field of tomographic imaging include speeding up reconstruction, reducing the time required to obtain the X-ray projections, and reducing the radiation dose imparted to the object. In this paper, we introduce a model of a monitored reconstruction process, in which the acquiring of projections is interspersed with image reconstruction. This model allows to examine the tomographic reconstruction process as an anytime algorithm and consider a problem of finding the optimal stopping point, corresponding to the required number of X-ray projections for the currently scanned object. We outline the theoretical framework for the monitored reconstruction, propose ways of constructing stopping rules for various reconstruction quality metrics and provide their experimental evaluation. Due to stopping at different times for different objects, the proposed approach allows to achieve a higher mean reconstruction quality for a given mean number of X-ray projections. Conversely, fewer projections on average are used to achieve the same mean reconstruction quality.