Segments Graph-Based Approach for Document Capture in a Smartphone Video Stream

Zhukovsky, Alexander; Nikolaev, Dmitry P.; Arlazarov, Vladimir V.; Postnikov, Vasiliy V.; Polevoy, Dmitry; Skoryukina, Natalya; Chernov, Timofey S.; Shemiakina, Julia; Mukovozov, Arseniy; Konovalenko, Ivan; Povolotsky, Mikhail

doi:10.1109/icdar.2017.63

Cited by 21 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The refined position of each border is calculated by the inverse FHT of the corresponding maximum at the FHT image. A similar quadrilateral refinement stage was used in [6,18].…”

Section: Quadrilateral Refiningmentioning

confidence: 99%

“…The third class of methods is based on document vertices detection [6,18,22]. Since there may be abundant false angles in the image, the Region Of Interest (ROI) is employed to improve the stability of the systems.…”

Section: Introductionmentioning

confidence: 99%

“…In [18], U-net is employed to estimate ROI, and in [22], a convolutional neural network (CNN) is used. In [6], ROI is not used. Authors search for angles in the entire image, however, the system with angle detection is complementary to the main method based on borders detection.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Advanced Hough-based method for on-device document localization

et al. 2021

View full text Add to dashboard Cite

The demand for on-device document recognition systems increases in conjunction with the emergence of more strict privacy and security requirements. In such systems, there is no data transfer from the end device to a third-party information processing servers. The response time is vital to the user experience of on-device document recognition. Combined with the unavailability of discrete GPUs, powerful CPUs, or a large RAM capacity on consumer-grade end devices such as smartphones, the time limitations put significant constraints on the computational complexity of the applied algorithms for on-device execution. In this work, we consider document location in an image without prior knowledge of the docu-ment content or its internal structure. In accordance with the published works, at least 5 systems offer solutions for on-device document location. All these systems use a location method which can be considered Hough-based. The precision of such systems seems to be lower than that of the state-of-the-art solutions which were not designed to account for the limited computational resources. We propose an advanced Hough-based method. In contrast with other approaches, it accounts for the geometric invariants of the central projection model and combines both edge and color features for document boundary detection. The proposed method allowed for the second best result for SmartDoc dataset in terms of precision, surpassed by U-net like neural network. When evaluated on a more challenging MIDV-500 dataset, the proposed algorithm guaranteed the best precision compared to published methods. Our method retained the applicability to on-device computations.

show abstract

“…The refined position of each border is calculated by the inverse FHT of the corresponding maximum at the FHT image. A similar quadrilateral refinement stage was used in [6,18].…”

Section: Quadrilateral Refiningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advanced Hough-based method for on-device document localization

et al. 2021

View full text Add to dashboard Cite

show abstract

“…If an object template is known and contains many static elements the object can be located and rectified simultaneously with local features [1,2]. In case of a rectangular object with a poor or unknown template we can detect its borders [3,4,5] and then calculate homogrpahy from the found quadrangle to a rectangular with known aspect ratio. However, this approach tends to misclassify inner segments as borders so rectified image may be stretched.…”

Section: Introductionmentioning

confidence: 99%

Fast projective image rectification for planar objects with Manhattan structure

Shemiakina

Konovalenko

Tropin

et al. 2020

Twelfth International Conference on Machine Vision (ICMV 2019)

Self Cite

View full text Add to dashboard Cite

This paper presents a method for metric rectification of planar objects that preserves angles and length ratios. An inner structure of an object is assumed to follow the laws of Manhattan World i.e. the majority of line segments are aligned with two orthogonal directions of the object. For that purpose we introduce the method that estimates the position of two vanishing points corresponding to the main object directions. It is based on an original optimization function of segments that estimates a vanishing point position. For calculation of the rectification homography with two vanishing points we propose a new method based on estimation of the camera rotation so that the camera axis is perpendicular to the object plane.The proposed method can be applied for rectification of various objects such as documents or building facades. Also since the camera rotation is estimated the method can be employed for estimation of object orientation (for example, during a surgery with radiograph of osteosynthesis implants). The method was evaluated on the MIDV-500 dataset containing projectively distorted images of documents with complex background. According to the experimental results an accuracy of the proposed method is better or equal to the-state-of-the-art if the background occupies no more than half of the image. Runtime of the method is around 3ms on core i7 3610qm CPU.

show abstract

“…Therefore, high quality should not be expected when they are obscured or are outside the frame. In [24] a combination of the contours and the vertices is used. And despite the fact that it makes the system more robust, the criticism of contour-based methods to such algorithms remains valid.…”

Section: Introductionmentioning

confidence: 99%

Approach for Document Detection by Contours and Contrasts

Tropin,

Ilyuhin,

Nikolaev

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper considers the task of arbitrary document detection performed on a mobile device. The classical contour-based approach often mishandles cases with occlusion, complex background, or blur. Region-based approach, which relies on the contrast between object and background, does not have limitations, however its known implementations are highly resource-consuming. We propose a modification of a countorbased method, in which the competing hypotheses of the contour location are ranked according to the contrast between the areas inside and outside the border. In the performed experiments such modification leads to the 40% decrease of alternatives ordering errors and 10% decrease of the overall number of detection errors. We updated state-of-the-art performance on the open MIDV-500 dataset and demonstrated competitive results with the state-of-the-art on the SmartDoc dataset.

show abstract

Segments Graph-Based Approach for Document Capture in a Smartphone Video Stream

Cited by 21 publications

References 14 publications

Advanced Hough-based method for on-device document localization

Advanced Hough-based method for on-device document localization

Fast projective image rectification for planar objects with Manhattan structure

Approach for Document Detection by Contours and Contrasts

Contact Info

Product

Resources

About