Improved algorithm of ID card detection by a priori knowledge of the document aspect ratio

Tropin, Daniil V.; Konovalenko, Ivan; Skoryukina, Natalya; Nikolaev, Dmitry P.; Arlazarov, Vladimir V.

doi:10.1117/12.2587029

Cited by 9 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our algorithm is comparable to the systems proposed in [9,10]: they use the same device and CPU mode when measuring the running time for the MIDV-500 subset. The list of methods ordered by the execution time is as follows: 67 ms / frame [9], 88 ms / frame [10], 102 ms / frame for the proposed system.…”

Section: Discussionmentioning

confidence: 99%

Section: Problems and Corresponding Metricsmentioning

confidence: 99%

“…To evaluate the system's performance when localizing the quadrilateral of the outer boundaries of the document, the metrics of quality based on the maximum discrepancy between the vertices are used [8,9]. The index introduced by Tropin et al in [9] is the best way to evaluate the system in our case. This index is based on the maximum discrepancy between the corresponding vertices of the resulting quadrilateral of the system and the ground-truth quadrilateral in the coordinate system of the resulting quadrilateral of the system.…”

Section: Problems and Corresponding Metricsmentioning

confidence: 99%

“…In [7] and in [8], high-frequency structures filtering system is used to overcome the FP problem. In [9], the quadrilaterals are formed by straight lines gained by no filtered edges. Since the ratio of sides is known, not only the standard method with the intersection of four sides is employed, but also the triples of sides are used to form a quadrilateral.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we propose the on-device document localization system, which also takes a Hough-based approach. We will use the modifications proposed in [9,10] to make the system more reliable in terms of FP and BV problems. The proposed method allowed for the second best result for SmartDoc dataset in terms of precision, surpassed only by a U-net like neural network.…”

Section: Introductionmentioning

confidence: 99%

See 4 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

Section: Discussionmentioning

confidence: 99%

Section: Problems and Corresponding Metricsmentioning

confidence: 99%

Section: Problems and Corresponding Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Advanced Hough-based method for on-device document localization

et al. 2021

View full text Add to dashboard Cite

show abstract

RFDoc: Memory Efficient Local Descriptors for ID Documents Localization and Classification

Matalov¹,

Limonova²,

Skoryukina³

et al. 2021

Document Analysis and Recognition – ICDAR 2021

View full text Add to dashboard Cite

Memory Efficient Local Features Descriptor for Identity Document Detection on Mobile and Embedded Devices

Matalov¹,

Limonova²,

Skoryukina³

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a data-driven approach to training a memory-efficient local feature descriptor for identity documents location and classification on mobile and embedded devices. The proposed algorithm for retrieving a dataset of patches is based on the specifics of document detection in smartphone camera-captured images with a template matching approach. The retrieved dataset of patches relevant to the domain, which includes splits for features training, features selection, and testing, is made public. We train a binary descriptor using the retrieved dataset of patches, each bit of the descriptor relies on a single computationally-efficient feature. To estimate the influence of different feature spaces on the descriptor performance, we perform descriptor training experiments using gradient-based and intensitybased features. Extensive experiments in identity document location and classification benchmarks showed that the resulting 128 and 192-bit descriptors which use gradient-based features outperformed a state-ofthe-art 512-bit BEBLID descriptor for arbitrary keypoints matching in all cases except the cases of extreme projective distortions, being significantly more efficient in cases of low lighting. The 64-bit gradient-based descriptor obtained within the approach showed better quality than 128 and 256-bit BinBoost descriptors in scanned document images. To evaluate the influence of the descriptor size on the matching speed, we propose a model based on the required number of processor instructions for computing the Hamming distance between a pair of descriptors on various energy-efficient processor architectures.

show abstract

Improved algorithm of ID card detection by a priori knowledge of the document aspect ratio

Cited by 9 publications

References 0 publications

Advanced Hough-based method for on-device document localization

Advanced Hough-based method for on-device document localization

RFDoc: Memory Efficient Local Descriptors for ID Documents Localization and Classification

Memory Efficient Local Features Descriptor for Identity Document Detection on Mobile and Embedded Devices

Contact Info

Product

Resources

About