CONFIRM – Clustering of noisy form images using robust matching

Tensmeyer, Chris; Martinez, Tony

doi:10.1016/j.patcog.2018.10.004

Cited by 7 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tensmeyer and Martinez applied an unsupervised clustering based approach to cluster visually similar noise images [16]. They employed a 3-stage scalable clustering approach which first clusters a subset of the data, then these clusters are further split to create purer subclusters, and at last a classifier is trained on top to recreate the subclusters.…”

Section: Related Workmentioning

confidence: 99%

Learning Document Image Features With SqueezeNet Convolutional Neural Network

Hassanpour

Malek

2020

IJE

View full text Add to dashboard Cite

The classification of various document image classes is considered an important step towards building a modern digital library or office automation system. Convolutional Neural Network (CNN) classifiers trained with backpropagation are considered to be the current state of the art model for this task. However, there are two major drawbacks for these classifiers: the huge computational power demand for training, and their very large number of weights. Previous successful attempts at learning document image features have been based on training very large CNNs. SqueezeNet is a CNN architecture that achieves accuracies comparable to other state of the art CNNs while containing up to 50 times less weights, but never before experimented on document image classification tasks. In this research we have taken a novel approach towards learning these document image features by training on a very small CNN network such as SqueezeNet. We show that an ImageNet pretrained SqueezeNet achieves an accuracy of approximately 75 percent over 10 classes on the Tobacco-3482 dataset, which is comparable to other state of the art CNN. We then visualize saliency maps of the gradient of our trained SqueezeNet's output to input, which shows that the network is able to learn meaningful features that are useful for document classification. Previous works in this field have made no emphasis on visualizing the learned document features. The importance of features such as the existence of handwritten text, document titles, text alignment and tabular structures in the extracted saliency maps, proves that the network does not overfit to redundant representations of the rather small Tobacco-3482 dataset, which contains only 3482 document images over 10 classes.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning Document Image Features With SqueezeNet Convolutional Neural Network

Hassanpour

Malek

2020

IJE

View full text Add to dashboard Cite

show abstract

“…This model has a complex pipeline that depends heavily on traditional hand-crafted features; in contrast, our approach achieves better results using a pipeline that is based entirely on unsupervised feature learning. Moreover, the CONFIRM algorithm [24] uses page elements such as OCR transcriptions and rule lines to obtain collection-dependent features.…”

Section: Related Work a Document Image Classificationmentioning

confidence: 99%

Unsupervised Exemplar-Based Learning for Improved Document Image Classification

2019

View full text Add to dashboard Cite

Many recent state-of-the-art approaches for document image classification are based on supervised feature learning that requires a large amount of labeled training data. In real-world problem of document image classification, the available amount of labeled data is limited and scarce while a large amount of unlabeled data is often available at almost no cost. In this paper, we present an approach for learning visual features for document analysis in an unsupervised way, which improves the document image classification performance without increasing the amount of annotated data. The proposed approach trains a neural network model on an auxiliary task in which every training example is associated with a different label (exemplar) and expanded to multiple images through a data augmentation technique. Thus, the learned model, which is trained in an unsupervised way, is used to boost the document classification performance. In fact, this learned model has proved to be consistently efficient in two different settings: i) as an unsupervised feature extractor to represent document images for an unsupervised classification task (i.e., clustering); and ii) in the parameters initialization of a supervised classification task trained with a small amount of annotated data. We perform experiments on the Tobacco-3482 dataset and demonstrate the capability of our approach to improve i) the unsupervised classification accuracy up to 2.4%; and ii) the supervised classification accuracy by 1.5% without any extra data or by 5% when using 3000 additional not annotated samples. INDEX TERMS Document image classification, document analysis, document image representation.

show abstract