Tensor representation learning based image patch analysis for text identification and recognition

Zhong, Guoqiang; Cheriet, Mohamed

doi:10.1016/j.patcog.2014.09.025

Cited by 19 publications

(6 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To take relational data into account, Zhong, Shi and Cheriet (2016) introduced the relational Fisher analysis (RFA) model, which can be used to applications with non-iid data. Zhong and Cheriet (2015) proposed a framework for dimensionality reduction from the perspective of tensor representation learning. To the end, many dimensionality reduction algorithms can be formulated in a general way, although the inputs may in the form of vectors, kernel representations and high order tensors.…”

mentioning

confidence: 99%

From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures

Zhong

Ling

Wang

2018

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

Since Pearson developed principal component analysis (PCA) in 1901, feature learning (or called representation learning) has been studied for more than 100 years. During this period, many “shallow” feature learning methods have been proposed based on various learning criteria and techniques, until the popular deep learning research in recent years. In this advanced review, we describe the historical profile of the shallow feature learning research and introduce the important developments of the deep learning models. Particularly, we survey the deep architectures with benefits from the optimization of their width and depth, as these models have achieved new records in many applications, such as image classification and object detection. Finally, several interesting directions of deep learning are presented and briefly discussed. This article is categorized under: Technologies > Classification Technologies > Machine Learning Technologies > Computational Intelligence

show abstract

mentioning

confidence: 99%

From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures

Zhong

Ling

Wang

2018

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

show abstract

“…Methods of this group are often closely related with methods of the previous one, but some of them focus only on separating text from non-text zones [30,26,25,23] (which can be considered as a simplified form of Zone labeling). Other approaches go further to provide not just the segmentation of the zones but also the corresponding zone labels (three different zones are labeled in [27], two in [24] and six in [28]).…”

Section: Zone Labelingmentioning

confidence: 99%

Multi-Task Handwritten Document Layout Analysis

Quirós

2018

Preprint

View full text Add to dashboard Cite

Document Layout Analysis is a fundamental step in Handwritten TextProcessing systems, from the extraction of the text lines to the type of zone it belongs to. We present a system based on artificial neural networks which is able to determine not only the baselines of text lines present in the document, but also performs geometric and logic layout analysis of the document. Experiments in three different datasets demonstrate the potential of the method and show competitive results with respect to state-of-the-art methods.

show abstract

“…Contrary to the case of printed document images, research in script identification on non traditional paper layouts is more scarce, and has been mainly dedicated to handwritten text [29,30,31,32,33], and video overlaidtext [12,34,35,36,13] until very recently. Gllavatta et al [12], in the first work dealing with video text script identification, proposed a method using the wavelet transform to detect edges in overlaid-text images.…”

Section: Related Workmentioning

confidence: 99%

Improving patch-based scene text script identification with ensembles of conjoined networks

Gómez

Nicolaou

Karatzas

2017

Pattern Recognition

View full text Add to dashboard Cite

show abstract

Tensor representation learning based image patch analysis for text identification and recognition

Cited by 19 publications

References 51 publications

From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures

From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures

Multi-Task Handwritten Document Layout Analysis

Improving patch-based scene text script identification with ensembles of conjoined networks

Contact Info

Product

Resources

About