Fine-grained classification of identity document types with only one example

Simon, Marcel; Rodner, Erik; Denzler, Joachim

doi:10.1109/mva.2015.7153149

Cited by 20 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Form images have been represented in a large variety of ways for classification tasks (see [5] for a survey). These representations include statistics of image connected components [37], BoVW [6,24,38], OCR features [2,32,33], pyramids of average gray-scale values [18,32], Viola-Jones features [34], Hidden Tree Markov Models [10], sequences of line segments [12,20], sequence of line gap ratios [28], run length histograms [16], Shape Context Features [22], and most recently learned features from Convolutional Neural Networks [17,21,38].…”

Section: Form Image Classificationmentioning

confidence: 99%

CONFIRM – Clustering of noisy form images using robust matching

Tensmeyer

Martinez

2019

Pattern Recognition

View full text Add to dashboard Cite

Identifying the type of a scanned form greatly facilitates processing, including automated field segmentation and field recognition. Contrary to the majority of existing techniques, we focus on unsupervised type identification, where the set of form types are not known apriori, and on noisy collections that contain very similar document types. This work presents a novel algorithm: CONFIRM (Clustering Of Noisy Form Images using Robust Matching), which simultaneously discovers the types in a collection of forms and assigns each form to a type. CONFIRM matches type-set text and rule lines between forms to create domain specific features, which we show outperform Bag of Visual Word (BoVW) features employed by the current state-of-the-art. To scale to large document collections, we use a bootstrap approach to clustering, where only a small subset of the data is clustered directly, while the rest of the data is assigned to clusters in linear time. We show that CONFIRM reduces average cluster impurity by 44% compared to the state-of-the art on 5 collections of historical forms that contain significant noise. We also show competitive performance on the relatively clean NIST tax form collection.

show abstract

Section: Form Image Classificationmentioning

confidence: 99%

CONFIRM – Clustering of noisy form images using robust matching

Tensmeyer

Martinez

2019

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Some systems already apply the visual based approach to document classification. The authors of [31] use global image descriptor with the assumption that the document is already localized and extracted. Paper [2] proposes a classification of scanned identity document into two classes using local descriptors.…”

Section: State Of the Artmentioning

confidence: 99%

Complex Document Classification and Localization Application on Identity Document Images

Awal¹,

Ghanmi²,

Sicre³

et al. 2017

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

This paper studies the problem of document image classification. More specifically, we address the classification of documents composed of few textual information and complex background (such as identity documents). Unlike most existing systems, the proposed approach simultaneously locates the document and recognizes its class. The latter is defined by the document nature (passport, ID, etc.), emission country, version, and the visible side (main or back). This task is very challenging due to unconstrained capturing conditions, sparse textual information, and varying components that are irrelevant to the classification, e.g. photo, names, address, etc.First, a base of document models is created from reference images. We show that training images are not necessary and only one reference image is enough to create a document model. Then, the query image is matched against all models in the base. Unknown documents are rejected using an estimated quality based on the extracted document. The matching process is optimized to guarantee an execution time independent from the number of document models. Once the document model is found, a more accurate matching is performed to locate the document and facilitate information extraction. Our system is evaluated on several datasets with up to 3042 real documents (representing 64 classes) achieving an accuracy of 96.6%.

show abstract

“…Although distinguishing between score 3 and 0 is rather easy, discriminating between the other classes can be hard and fine-details in the cell structure are necessary. Therefore, the Her2 scoring class is related to the area of fine-grained recognition [5,6,8] as well as texture classification [7]. The recently successful concept of bilinear features [1,5] of this area is used in this paper.…”

Section: Algorithm Overviewmentioning

confidence: 99%

Deep bilinear features for Her2 scoring in digital pathology

Rodner

Simon

Denzler

2017

Current Directions in Biomedical Engineering

Self Cite

View full text Add to dashboard Cite

Abstract:We present an automated approach for rating HER2 over-expressions in given whole-slide images of breast cancer histology slides. The slides have a very high resolution and only a small part of it is relevant for the rating.Our approach is based on Convolutional Neural Networks (CNN), which are directly modelling the whole computer vision pipeline, from feature extraction to classification, with a single parameterized model. CNN models have led to a significant breakthrough in a lot of vision applications and showed promising results for medical tasks. However, the required size of training data is still an issue. Our CNN models are pre-trained on a large set of datasets of nonmedical images, which prevents over-fitting to the small annotated dataset available in our case. We assume the selection of the probe in the data with just a single mouse click defining a point of interest. This is reasonable especially for slices acquired together with another sample. We sample image patches around the point of interest and obtain bilinear features by passing them through a CNN and encoding the output of the last convolutional layer with its second-order statistics.Our approach ranked second in the Her2 contest held by the University of Warwick achieving 345 points compared to 348 points of the winning team. In addition to pure classification, our approach would also allow for localization of parts of the slice relevant for visual detection of Her2 over-expression.

show abstract

Fine-grained classification of identity document types with only one example

Cited by 20 publications

References 16 publications

CONFIRM – Clustering of noisy form images using robust matching

CONFIRM – Clustering of noisy form images using robust matching

Complex Document Classification and Localization Application on Identity Document Images

Deep bilinear features for Her2 scoring in digital pathology

Contact Info

Product

Resources

About