Font

Abstract: In this work, we focus on the challenge of taking partial observations of highly-stylized text and generalizing the observations to generate unobserved glyphs in the ornamented typeface. To generate a set of multi-content images following a consistent style from very few examples, we propose an end-to-end stacked conditional GAN model considering content along channels and style along network layers. Our proposed network transfers the style of given glyphs to the contents of unseen ones, capturing highly stylized fonts found in the real-world such as those on movie posters or infographics. We seek to transfer both the typographic stylization (ex. serifs and ears) as well as the textual stylization (ex. color gradients and effects.) We base our experiments on our collected data set including 10,000 fonts with different styles and demonstrate effective generalization from a very small number of observed glyphs.

Abstract: Many efforts have been made to discriminate, categorize, and quantitate patterns, and to reduce them into a usable machine language. The results have ordinarily been methods or devices with a high degree of specificity. For example, some devices require a special type font; others can read only one type font; still others require magnetic ink.

Abstract: We describe the current state of a system that recognizes printed text of various fonts and sizes for the Roman alphabet. The system combines several techniques in order to improve the overall recognition rate. Thinning and shape extraction are performed directly on a graph of the run-length encoding of a binary image. The resulting strokes and other shapes are mapped, using a shape-clustering approach, into binary features which are then fed into a statistical Bayesian classifier. Large-scale trials have shown better than 97 percent top choice correct performance on mixtures of six dissimilar fonts, and over 99 percent on most single fonts, over a range of point sizes. Certain remaining confusion classes are disambiguated through contour analysis, and characters suspected of being merged are broken and reclassified. Finally, layout and linguistic context are applied. The results are illustrated by sample pages.

Abstract: A hand held portable reading unit having a screen capable of presenting characters in variable font sizes is provided for readers, such as the visually impaired, allowing them to read characters in a font size most comfortable to them. The reader effects font size changes by depressing a font size select button, in turn activating a counter incremented the number of times the button has been depressed to generate the corresponding size font desired. The incremented counter may be used to address a particular place in memory where bit-mapped characters of different font sizes are stored or may be used as a scalar inputted into a character scaling algorithm to generate a desired character font size. The stored textual data may further be presented in useable form to the blind wherein an audible processor is utilized to convert the stored character code into audible signals inputted into a speaker.