This method addresses the domain mismatch problem between training- and prediction-time data. These feature maps are then used as an initial state for parts of a CNN trained in a supervised fashion using synthetic data only. They generate a relatively large sized dataset, which is exploited along with unlabeled real data in an unsupervised way to learn feature maps using Stacked Convolutional Autoencoders (SCAE). They show how to synthesis data to resemble real world text images. train a convolutional neural network (CNN) on KAFD by densely croping each image into patches and then averaging the individual predicitons made on these patches to determine the final decision, which appears to improve performance.ĭeepFont focuses on both data and model. The only reasonbly sized dataset is the King Fahd Univeristy Arabic Font Database (KAFD), which is available online, however, at the time of writing the download page renders error messages when requesting to download the dataset, which hindered using it in this project. Very few work has been done on Arabic VFR, mostly attributed to the lack of data. Some are based on novel feature extraction techniques, other are deep learning based solutions. Related Workĭifferent approaches have been applied to address the VFR problem. Results demonstrate the effectiveness of the synthesization process, which alleviates the domain mismatch problem by a factor of 29% allowing the model to reach 97% accuracy. Finally in 5, a model is trained on the mentioned dataset and its performance is analyzed as more synthesization steps were introduced. ![]() Additionally, a synthesization process is presented to overcome domain mismatch, a common challenge introduced by synthesized data, in which the training data distribution differs from the testing one, leading to a serious drop in performance. As shown in 4, a dataset was synthesized to solve the data scarcity problem. An Arabic font here refers to a form of writing that uses Arabic letters regardless of the language it’s been written in. The task is to classify images of text written using Arabic letters into two classes of Arabic fonts: Ruqaa and Nastaliq (Farsi). This project aims to tackle a simplified version of the font recognition problem. It can be used by font creators to detect and find copyright infringements. also introduced a tool called WhatTheFont as an on-the-fly font recognition tool. For example, DeepFont was developed as part of Adobe Photoshop to detect and suggest similar fonts from images. ![]() Companies like Google, Snapchat, and Adobe have been interested in this technology in order to increase the productivity of their products’ users. It can be used as a complementary part of a product. Identifying the used font in a document then using an OCR model specialized to work with that particular font will improve the accuracy and time complexity of the system, rather than using one model to deal with all the different fonts. Improving other tasks, such as optical character recognition (OCR). ![]() Style/similarity-based font search, to power font engines such as Google Fonts. In addition to standalone usage of VFR systems to simply identify fonts, they can be utilized as subsystems within other more complex ones, for example: Since manual font identification can be tedious and requires expertise, especially when working with fonts of foreign languages, automatically identifing these fonts can be of a great benefit to designers and creative workers. The task of font classification/recognition/visual font recognition (VFR), is to automatically identify the font family of an image of text.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |