For Chinese font images, when all their strokes are replaced by pattern elements such as flowers and birds, they become flower–bird character paintings, which are traditional Chinese art treasures. ...The generation of flower–bird painting requires professional painters’ great efforts. How to automatically generate these paintings from font images? There is a huge gap between the font domain and the painting domain. Although many image-to-image translation frameworks have been proposed, they are unable to handle this situation effectively. In this study, a novel method called font-to-painting network (F2PNet) is proposed for font-to-painting translation. Specifically, an encoder equipped with dilated convolutions extracts features of the font image, and then the features are fed into the domain translation module for mapping the font feature space to the painting feature space. The acquired features are further adjusted by the refinement module and utilised by the decoder to obtain the target painting. The authors apply adversarial loss and cycle-consistency loss to F2PNet and further propose a loss term, which is called recognisability loss and makes the generated painting have font-level recognisability. It is proved by experiments that F2PNet is effective and can be used as an unsupervised image-to-image translation framework to solve more image translation tasks.
Handwritten fonts possess unique expressive qualities; however, their clarity often suffers because of inconsistent handwriting. This study introduces FontFusionGAN (FFGAN), a novel method that ...enhances handwritten fonts by mixing them with printed fonts. The proposed approach leverages a generative adversarial network (GAN) to synthesize fonts that combine the desirable features of both handwritten and printed font styles. Training a GAN on a comprehensive dataset of handwritten and printed fonts enables it to produce legible and visually appealing font samples. The methodology was applied to a dataset of handwriting fonts, showing substantial enhancements in the legibility of the original fonts, while retaining their unique aesthetic essence. Unlike the original GAN setting where a single noise vector is used to generate a sample image, we randomly selected two noise vectors, z1 and z2, from a Gaussian distribution to train the generator. Simultaneously, we input a real image into the fusion encoder for exact reconstruction. This technique ensured the learning of style mixing during training. During inference, we provided the encoder with two font images, one handwritten and the other printed font, to obtain their respective latent vectors. Subsequently, the latent vector of the handwritten font image was injected into the first five layers of the generator, whereas the latent vector of the printed font image was injected into the last two layers to obtain a refined handwritten font image. The proposed method has the potential to improve the readability of handwritten fonts, offering benefits across diverse applications, such as document composition, letter writing, and assisting individuals with reading and writing difficulties.
In this paper, we present multi-font printed Arabic text recognition using hidden Markov models (HMMs). We propose a novel approach to the sliding window technique for feature extraction. The size ...and position of the cells of the sliding window adapt to the writing line of Arabic text and ink-pixel distributions. We employ a two-step approach for mixed-font text recognition, in which the input text line image is associated with the closest known font in the first step, using simple and effective features for font identification. The text line is subsequently recognized by the recognizer that was trained for the particular font in the next step. This approach proves to be more effective than text recognition using a recognizer trained on samples from multiple fonts. We also present a framework for the recognition of unseen fonts, which employs font association and HMM adaptation techniques. Experiments were conducted using two separate databases of printed Arabic text to demonstrate the effectiveness of the presented techniques. The presented techniques can be easily adapted to other scripts, such as Roman script.
•A novel approach to the sliding window technique for feature extraction.•A two-step approach to mixed-font and unseen font text recognition.•Simple and effective features for font identification.•A multi-font printed Arabic text database for text recognition research.•Experiments were conducted using two separate databases of printed Arabic text.
Tree source-sink ratio has a predominant and complex impact on tree performance and can affect multiple physiological processes including vegetative and reproductive growth, water and nutrient use, ...photosynthesis, and productivity. In this study, we manipulated the branch level source-sink ratio by reduction of photosynthetic activity (partial branch defoliation) or thinning branch fruit load early in the growing season (after fruit set) in pistachio (
Pistacia vera
) trees. We then characterized the leaf photosynthetic light response curves through leaf aging. In addition, we determined changes in leaf non-structural carbohydrates (NSC) and nitrogen (N) concentrations. In leaves with high source-sink ratios, there was a gradual decrease in maximum net photosynthetic rate (A
Nmax
) over the growing season, while in branches with low source-sink ratios, there was a sharp decline in A
Nmax
in the first two weeks of August. Branches with high-sink showed an up-regulation (increase) in photosynthesis toward the end of July (at 1,500 growing degree days) during the period of rapid kernel growth rate and increased sink strength, with A
Nmax
being about 7 μmol m
-1
s
-1
higher than in branches with low-sink. In August, low source-sink ratios precipitated leaf senescence, resulting in a drastic A
Nmax
decline, from 25 to 8 μmol m
-1
s
-1
(70% drop in two weeks). This reduction was associated with the accumulation of NSC in the leaves from 20 to 30 mg g
-1
. The mechanisms of A
Nmax
reduction differ between the two treatments. Lower photosynthetic rates of 8-10 μmol m
-1
s
-1
late in the season were associated with lower N levels in high-sink branches, suggesting N remobilization to the kernels. Lower photosynthesis late in the season was associated with lower respiration rates in low-source branches, indicating prioritization of assimilates to storage. These results can facilitate the adaptation of management practices to tree crop load changes in alternate bearing species.
•A multi-Tasking learning (MTL) based network to perform document’s attribute classification.•A hybrid CNN architecture which is based on the combination of MTL and multi-instance (MI).•To avoid ...unequal influence of one instance compared to other, we propose weighted MTL+MI framework.•An intelligent voting system for complete document classification, based on the posterior probabilities.
In this work, we adhere to explore a Multi-Tasking learning (MTL) based network to perform document attribute classification such as the font type, font size, font emphasis and scanning resolution classification of a document image. To accomplish these tasks, we operate on either segmented word level or on uniformed size patches randomly cropped out of the document. Furthermore, a hybrid convolution neural network (CNN) architecture ”MTL+MI”, which is based on the combination of MTL and Multi-Instance (MI) of patch and word is used to accomplish joint learning for the classification of the same document attributes. The contribution of this paper are three fold: firstly, based on segmented word images and patches, we present a MTL based network for the classification of a full document image. Secondly, we propose a MTL and MI (using segmented words and patches) based combined CNN architecture (“MTL+MI”) for the classification of same document attributes. Thirdly, based on the multi-tasking classifications of the words and/or patches, we propose an intelligent voting system which is based on the posterior probabilities of each words and/or patches to perform the classification of document’s attributes of complete document image.
With the increase of various media, fonts continue to be newly developed. In Korea, numerous ‘Hangul’ fonts are also being developed, and as a result, the need for research on determining the ...similarity between fonts is emerging. For example, when creating a document, the font to be used must be downloaded from each computing environment. However, this is a very cumbersome process. If there is a font that is not supported in the system, the above problem can be easily solved by recommending the most similar font that can replace it. According to this need, we conducted various prior studies for similar font recommendations. As a result, we developed a ‘stroke element’ that exists in each consonant and vowel in Korean font and developed a font recommendation model using a stroke element. However, there is a limitation in that the existing research was studied only for the structured fonts corresponding to the printed type. Additionally, the font size was not considered in the font recommendation. In this study, two experiments were conducted to expand the font recommendation model by supplementing the limitations of existing studies. First, in order to enable similar font recommendations based on the stroke element even in fonts with various shapes, the font was classified according to the shape, and the stroke elements in each classification were detected. Second, when the font sizes were different, the change in the font recommendations result based on the stroke element was analyzed. In conclusion, we found that it was necessary to find a plan to extract stroke elements for font recommendation of fonts that do not belong to standard fonts. In addition, since the influence of the stroke element varies depending on the size of the font, we propose a stroke element weight model that can be used for recommendation by reflecting it.
•A new approach, DropRegion-IFN, is proposed for Chinese font recognition.•DropRegion is proposed as a new data augmentation and regularization technique.•We design a new deep model named inception ...font network (IFN).•Very high accuracies of 99.78% and 98.98% are achieved for text block and single character font recognition.
Chinese font recognition (CFR) has gained significant attention in recent years. However, due to the sparsity of labeled font samples and the structural complexity of Chinese characters, CFR is still a challenging task. In this paper, a DropRegion method is proposed to generatea large number of stochastic variant font samples whose local regions are selectively disrupted and an inception font network (IFN) with two additional convolutional neural network (CNN) structure elements, i.e., a cascaded cross-channel parametric pooling (CCCP) and global average pooling, is designed. Because the distribution of strokes in a font image is non-stationary, an elastic meshing technique that adaptively constructs a set of local regions with equalized information is developed. Thus, DropRegion is seamlessly embedded in the IFN, which enables end-to-end training; the proposed DropRegion-IFN can be used for high performance CFR. Experimental results have confirmed the effectiveness of our new approach for CFR.
Automatic few-shot font generation aims to solve a well-defined, real-world problem because manual font designs are expensive and sensitive to the expertise of designers. Existing methods learn to ...disentangle style and content elements by developing a universal style representation for each font style. However, this approach limits the model in representing diverse local styles because it is unsuitable for complicated letter systems. For example, Chinese characters consist of a varying number of components (often called "radical") with a highly complex structure. In this paper, we propose a novel font generation method that learns localized styles, namely component-wise style representations, instead of universal styles. The proposed style representations enable synthesizing complex local details in text designs. However, learning component-wise styles solely from a few reference glyphs is infeasible when a target script has a large number of components, for example, over 200 for Chinese. To reduce the number of required reference glyphs, we represent component-wise styles by a product of component and style factors inspired by low-rank matrix factorization. Owing to the combination of strong representation and a compact factorization strategy, our method shows remarkably better few-shot font generation results (with only eight reference glyphs) than other state-of-the-art methods. Moreover, strong locality supervision was not utilized, such as the location of each component, skeleton, or strokes. The source code is available at https://github.com/clovaai/lffont .