Unsupervised Font Clustering Using Stochastic Versio of the EM Algorithm and Global Texture Analysis

Avilés‐Cruz, Carlos; Villegas, Juan; Arechiga-Martínez, René; Escarela‐Perez, R.

doi:10.1007/978-3-540-30463-0_34

Cited by 5 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many classical font recognition models use this approach and detect typographical features such as typeface, weight, slope, and size [13,5,30]. In addition, clustering has been used to recognize groups of fonts [24,3].…”

Section: Font Identification and Recognitionmentioning

confidence: 99%

Character-independent font identification

Haraguchi¹,

Harada²,

Iwana³

et al. 2020

Preprint

View full text Add to dashboard Cite

There are a countless number of fonts with various shapes and styles. In addition, there are many fonts that only have subtle differences in features. Due to this, font identification is a difficult task. In this paper, we propose a method of determining if any two characters are from the same font or not. This is difficult due to the difference between fonts typically being smaller than the difference between alphabet classes. Additionally, the proposed method can be used with fonts regardless of whether they exist in the training or not. In order to accomplish this, we use a Convolutional Neural Network (CNN) trained with various font image pairs. In the experiment, the network is trained on image pairs of various fonts. We then evaluate the model on a different set of fonts that are unseen by the network. The evaluation is performed with an accuracy of 92.27%. Moreover, we analyzed the relationship between character classes and font identification accuracy.

show abstract

Section: Font Identification and Recognitionmentioning

confidence: 99%

Character-independent font identification

Haraguchi¹,

Harada²,

Iwana³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…A method by Avilées-Cruz et al 8 preprocesses the words of a document image to make sure they are monospaced. Next, their technique performs feature extraction on various sized texture windows.…”

Section: Introductionmentioning

confidence: 99%

Font group identification using reconstructed fonts

2011

View full text Add to dashboard Cite

Ideally, digital versions of scanned documents should be represented in a format that is searchable, compressed, highly readable, and faithful to the original. These goals can theoretically be achieved through OCR and font recognition, re-typesetting the document text with original fonts. However, OCR and font recognition remain hard problems, and many historical documents use fonts that are not available in digital forms. It is desirable to be able to reconstruct fonts with vector glyphs that approximate the shapes of the letters that form a font. In this work, we address the grouping of tokens in a token-compressed document into candidate fonts. This permits us to incorporate font information into token-compressed images even when the original fonts are unknown or unavailable in digital format. This paper extends previous work in font reconstruction by proposing and evaluating an algorithm to assign a font to every character within a document. This is a necessary step to represent a scanned document image with a reconstructed font. Through our evaluation method, we have measured a 98.4% accuracy for the assignment of letters to candidate fonts in multi-font documents.

show abstract