Saliency-Based Detection of Identy Documents Captured by Smartphones

Ngoc, Minh; Fabrizio, Jonathan; Géraud, Thierry

doi:10.1109/das.2018.17

Cited by 16 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ngoc et al 68 investigated the programmed separation of identity documents in smartphone pictures or videos using visual saliency (VS) to evaluate many VS styles and determine which one works well. To achieve this, the authors suggested a new VS system on a current distance fitting the possibility of scientific geomorphology.…”

Section: Id Document Classificationmentioning

confidence: 99%

An Intelligent Hybrid Model for Identity Document Classification

Khandan

2021

Preprint

View full text Add to dashboard Cite

Digitization, i.e., the process of converting information into a digital format, may provide various opportunities (e.g., increase in productivity, disaster recovery, and environmentally friendly solutions) and challenges for businesses. In this context, one of the main challenges would be to accurately classify numerous scanned documents uploaded every day by customers as usual business processes. For example, processes in banking (e.g., applying for loans) or the Government Registry of BDM (Births, Deaths, and Marriages) applications may involve uploading several documents such as a driver's license and passport. There are not many studies available to address the challenge as an application of image classification. Although some studies are available which used various methods, a more accurate model is still required. The current study has proposed a robust fusion model to define the type of identity documents accurately. The proposed approach is based on two different methods in which images are classified based on their visual features and text features. A novel model based on statistics and regression has been proposed to calculate the confidence level for the feature-based classifier. A fuzzy-mean fusion model has been proposed to combine the classifier results based on their confidence score. The proposed approach has been implemented using Python and experimentally validated on synthetic and real-world datasets. The performance of the proposed model is evaluated using the Receiver Operating Characteristic (ROC) curve analysis.

show abstract

Section: Id Document Classificationmentioning

confidence: 99%

An Intelligent Hybrid Model for Identity Document Classification

Khandan

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…As one more type of approaches saliency maps can be used, for example [15]. But this approach does not take into account such problem aspects as described in section 2.1.…”

Section: Related Workmentioning

confidence: 99%

“…Among the works specifically about price tags the approaches using HSV color space in [17] and neural networks in [18] can be mentioned. But the first work (also as [15]) does not take into account such problem aspects as described in section 2.1, and the second one (just as other tasks that use neural networks) needs large amount of markup for network training.…”

Section: Related Workmentioning

confidence: 99%

A low computational approach for price tag recognition

Aliev¹,

Nikolaev

Kunina³

et al. 2020

Twelfth International Conference on Machine Vision (ICMV 2019)

View full text Add to dashboard Cite

In this work we discuss the task of search, localization and recognition of price zone within a photograph of the price tag. The task is being addressed for the case when image is acquired by small-scale digital camera and calculation device has significant resource constraints. The proposed approach is based on Niblack binarization algorithm, analysis and clasterization of connected components in conditions of known price tag geometrical model. The algorithm was tested on a private dataset and has shown high quality.

show abstract

“…At the same time, an important aspect of identity document recognition systems is their low error tolerance -the cost of recognition mistakes are high, as the recognized data is then used for personal identification, government services, financial transactions and in other sensitive fields. The scope of computer vision problems related to identity documents recognition includes document detection and location [23], [24], document layout analysis [25], face detection [26], and, of course, text fields recognition [27]- [29]. Fig.…”

Section: Introductionmentioning

confidence: 99%