Image quality assessment for video stream recognition systems

Recognition and machine vision systems have long been widely used in many disciplines to automate various processes of life and industry. Input images of optical recognition systems can be subjected to a large number of different distortions, especially in uncontrolled or natural shooting conditions, which leads to unpredictable results of recognition systems, making it impossible to assess their reliability. For this reason, it is necessary to perform quality control of the input data of recognition systems, which is facilitated by modern progress in the field of image quality evaluation. In this paper, we investigate the approach to designing optical recognition systems with built-in input image quality estimation modules and feedback, for which the necessary definitions are introduced and a model for describing such systems is constructed. The efficiency of this approach is illustrated by the example of solving the problem of selecting the best frames for recognition in a video stream for a system with limited resources. Experimental results are presented for the system for identity documents recognition, showing a significant increase in the accuracy and speed of the system under simulated conditions of automatic camera focusing, leading to blurring of frames.

[1]  シャオハン・ワン,et al.  Client-side filtering of the card of ocr image , 2014 .

[2]  G. Awcock,et al.  Applied Image Processing , 1995 .

[3]  Yinglin Wang,et al.  Robust Automatic Focus Algorithm for Low Contrast Images Using a New Contrast Measure , 2011, Sensors.

[4]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[5]  Nicholas Omoregbe,et al.  Design of a Face Recognition System for SecurityControl , 2015 .

[6]  Jonathan G. Fiscus,et al.  A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[7]  Dmitry P. Nikolaev,et al.  Smart IDReader: Document Recognition in Video Stream , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[8]  Dmitry P. Nikolaev,et al.  Complex approach to long-term multi-agent mapping in low dynamic environments , 2015, International Conference on Machine Vision.

[9]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Dmitry P. Nikolaev,et al.  Generalization of the Viola-Jones method as a decision tree of strong classifiers for real-time object recognition in video stream , 2015, Other Conferences.

[11]  Shahram Shirani,et al.  Subjective and Objective Quality Assessment of Image: A Survey , 2014, ArXiv.

[12]  Lina J. Karam,et al.  Understanding how image quality affects deep neural networks , 2016, 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX).

[13]  Elena G. Kuznetsova,et al.  Russian License Plate Segmentation Based On Dynamic Time Warping , 2017, ECMS.

[14]  David S. Doermann,et al.  Document Image Quality Assessment: A Brief Survey , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[15]  A. Asadpour,et al.  Design and application of industrial machine vision systems , 2007 .

[16]  Oleg Slavin,et al.  N-Grams Algorithm Application for the Correction of Recognition Results , 2016 .

[17]  Konstantin B. Bulatov,et al.  Reducing Overconfidence In Neural Networks By Dynamic Variation of Recognizer Relevance , 2015, ECMS.