WO2022039516A1

WO2022039516A1 - Methods and electronic device for handling personalized font

Info

Publication number: WO2022039516A1
Application number: PCT/KR2021/011017
Authority: WO
Inventors: Jayesh Rajkumar Vachhani; Rakshith SRINIVAS; Rishabh KHURANA; Bhanodai Guggilla; Barath Raj Kandur Raja; Sumit Kumar
Original assignee: Samsung Electronics Co., Ltd.
Priority date: 2020-08-19
Filing date: 2021-08-19
Publication date: 2022-02-24

Abstract

Embodiments herein provide methods for handling a personalized font by an electronic device (100). Further, the method includes determining at least one N-gram ligature pair and at least one N-gram kerning pair based on a handwriting input and a processed handwriting stroke. Further, the method includes identifying a style vector by encoding the handwriting input, the N-gram ligature pair and the N-gram kerning pair. Further, the method includes generating at least one data item with at least one ligature from the at least one N-gram ligature pair and at least one kerning from the at least one N-gram kerning pair based on the at least one extracted style vector. Further, the method includes generating at least one personalized font based on the at least one generated data item with the at least one ligature and the at least one kerning.

Description

METHODS AND ELECTRONIC DEVICE FOR HANDLING PERSONALIZED FONT

Embodiments disclosed herein relate to handling fonts on an electronic device and more particularly to creating and personalizing fonts on the electronic device.

CROSS REFERENCE TO RELATED APPLICATION

This application is based on and derives the benefit of Indian Provisional Application 202041035769 and Indian Application 202041035769, the contents of which are incorporated herein by reference.

FIG. 1a and FIG. 1b are example scenarios in which font generation is depicted, according to prior art. As shown in the FIG. 1a and FIG. 1b, handwriting input does not support keyboard features like word predictions/suggestions, spell corrections, auto corrections, grammar correction, and so on. The handwriting input does not support touch keyboard features. The user of the electronic device (100) needs to erase and re-write to correct mistakes. There are no solutions that provide on the go correction of handwritten text. Current solutions do not provide on the go handwriting assistance by word predictions, suggestions, spell corrections, auto corrections and grammar corrections in the user's own handwriting by either generating text using personalized font or image of words in the users handwriting.

Thus, it is desired to address the above mentioned disadvantages or other shortcomings or at least provide a useful alternative.

The principal object of the embodiments herein is to disclose methods and electronic device for creating and personalizing fonts on the electronic device, which provide on-go handwriting assistance by enabling all touch keyboard features to handwriting users.

Another object of the embodiments herein is to enable a personalized font to be created using styles based on the handwriting of the user.

Another object of the embodiments herein is to assist a word prediction operation associated with the handwriting input.

Another object of the embodiments herein is to assist a spell check operation associated with the handwriting input.

Another object of the embodiments herein is to assist an auto correction operation associated with the handwriting input

Another object of the embodiments herein is to assist a direct writing on a content.

Another object of the embodiments herein is to assist a writing with the personalized font on the electronic device.

Accordingly, the embodiments herein provide methods for handling a personalized font. The method includes obtaining, by an electronic device, at least one handwriting input from a user of the electronic device. Further, the method includes processing, by the electronic device, at least one handwriting stroke corresponding to the at least one handwriting input. Further, the method includes determining, by the electronic device, at least one N-gram ligature pair and at least one N-gram kerning pair based on the at least one handwriting input and the at least one processed handwriting stroke. Further, the method includes identifying, by the electronic device, at least one style vector by encoding the at least one handwriting input, the at least one N-gram ligature pair and the at least one N-gram kerning pair. Further, the method includes generating, by the electronic device, at least one data item with at least one ligature from the at least one N-gram ligature pair and at least one kerning from the at least one N-gram kerning pair based on the at least one extracted style vector. Further, the method includes generating, by the electronic device, at least one personalized font based on the at least one generated data item with the at least one ligature and the at least one kerning.

In an embodiment, the method includes performing, by the electronic device, at least one action based on the at least one generated personalized font, wherein the at least one action comprises at least one of a word prediction operation associated with the at least one handwriting input, a spell check operation associated with the at least one handwriting input, an auto correction operation associated with the at least one handwriting input, a direct writing on at least one content, and writing with the at least one personalized font on the electronic device.

In an embodiment, writing with the at least one personalized font on the electronic device is performed by activating a personalized font mode on the electronic device, while writing a user input on the electronic device, mapping the writing user input with the at least one personalized font, and producing the at least one personalized font corresponding to the writing user input on a display of the electronic device.

In an embodiment, the direct writing on the at least one content is performed by activating a personalized font mode on the electronic device, while writing a user input on the at least one content displayed on the electronic device, selecting a user input region on the at least one content displayed on the electronic device, writing the user input on the selected user input region on the at least one content, mapping the user input with the at least one personalized font, and producing the at least one personalized font corresponding to the user input on a display of the electronic device.

In an embodiment, the method includes extracting, by the electronic device, at least one font property of the at least one personalized font and a predefined font, wherein the at least one font property comprises at least one of strong, soft, gentle, formal, and calm. Further, the method includes learning, by the electronic device, at least one font property of the at least one personalized font and the predefined font over a period of time using a data driven module. Further, the method includes optimizing, by the electronic device, the at least one personalized font and the predefined font by applying the at least one font property on the at least one personalized font and the predefined font.

In an embodiment, the method includes storing, by the electronic device, the generated personalized font in the electronic device. Further, the method includes sharing, by the electronic device, the generated personalized font to another electronic device.

In an embodiment, generating, by the electronic device, the at least one personalized font based on the at least one generated data item with the at least one ligature and the kerning includes extracting, by the electronic device, at least one font attributes based on the at least one generated data item with the at least one ligature and the kerning, generating, by the electronic device, at least one glyph for the at least one data item, at least one ligature and at least one kerning pairs, and generating, by the electronic device, the personalized font based on the at least one generated glyph.

In an embodiment, the at least one font attributes includes at least one of a baseline of the at least one handwriting input from the at least one generated data item, an ascent of the at least one handwriting input from the at least one generated data item, a descent of the at least one handwriting input from the at least one generated data item, an advance width of the at least one handwriting input from the at least one generated data item, a kerning adjustment of the at least one handwriting input from the at least one generated data item, a left bearing of the at least one handwriting input from the at least one generated data item, and a right bearing of the at least one handwriting input from the at least one generated data item.

In an embodiment, the extracting, by the electronic device, the at least one N-gram ligature pair and the at least one N-gram kerning pair includes processing, by the electronic device, at least one handwriting stroke corresponding to the at least one handwriting input by capturing randomness of at least one handwriting input over a period of time, wherein the randomness of at least one handwriting input corresponds to cursive writing and different ways of writing same data item using a data driven controller, and extracting, by the electronic device, the at least one N-gram ligature pair and at least one N-gram kerning pair.

In an embodiment, the at least one N-gram ligature pair and the at least one N-gram kerning pair are used for recognizing a cursive-ness of the at least one handwriting input, randomness of the at least one handwriting input and a variation of the at least one handwriting input, wherein the at least one data item comprises at least one of a character, a symbol, a numeric value, and an alphabet.

Accordingly, the embodiments herein provide methods for handling a personalized font. The method includes activating, by an electronic device, at least one personalized font mode in the electronic device. Further, the method includes obtaining, by an electronic device, at least one handwriting input, from a user of the electronic device, in the at least one personalized font mode. Further, the method includes determining, by the electronic device, at least one N-gram ligature pair and at least one N-gram kerning pair based on the at least one handwriting input and at least one handwriting stroke associated with the at least one handwriting input. Further, the method includes generating, by the electronic device, at least one personalized font based on the at least one determined N-gram ligature pair and at least one determined N-gram kerning pair.

Accordingly, the embodiments herein provide an electronic device. The electronic device includes a personalized font generation controller coupled with a memory and a processor. The personalized font generation controller is configured to obtain at least one handwriting input from a user of the electronic device and process at least one handwriting stroke corresponding to the at least one handwriting input. Further, the personalized font generation controller is configured to determine at least one N-gram ligature pair and at least one N-gram kerning pair based on the at least one handwriting input and the at least one processed handwriting stroke. Further, the personalized font generation controller is configured to identify at least one style vector by encoding the at least one handwriting input, the at least one N-gram ligature pair and the at least one N-gram kerning pair. Further, the personalized font generation controller is configured to generate at least one data item with at least one ligature from the at least one N-gram ligature pair and at least one kerning from the at least one N-gram kerning pair based on the at least one extracted style vector. Further, the personalized font generation controller is configured to generate at least one personalized font based on the at least one generated data item with the at least one ligature and the at least one kerning.

Accordingly, the embodiments herein provide an electronic device. The electronic device includes a personalized font generation controller coupled with a memory and a processor. The personalized font generation controller is configured to activate at least one personalized font mode in the electronic device. The personalized font generation controller is configured to obtain at least one handwriting input, from a user of the electronic device, in the at least one personalized font mode. The personalized font generation controller is configured to determine at least one N-gram ligature pair and at least one N-gram kerning pair based on the at least one handwriting input and at least one handwriting stroke associated with the at least one handwriting input. The personalized font generation controller is configured to generate at least one personalized font based on the at least one determined N-gram ligature pair and at least one determined N-gram kerning pair.

Accordingly, the embodiments herein provide methods for handling a personalized font. The method includes receiving, by an electronic device, at least a portion of handwritten text as an input on the electronic device. Further, the method includes analysing, by the electronic device, at least one of a kerning pair of the handwritten text and a ligature pair of the handwritten text to determine at least one handwriting characteristic of the text. Further, the method includes creating, by the electronic device, a font following the handwriting characteristics. Further, the method includes configuring, by the electronic device, the created font as a user selectable for future use.

Accordingly, the embodiments herein provide methods for handling a personalized font. The method includes receiving, by an electronic device, a handwritten text on the electronic device. Further, the method includes processing, by the electronic device, the handwritten text through a data driven model to extract a plurality of kerning pairs and a plurality ligature pairs from the handwritten text; and determine handwriting characteristics by analysing the kerning pairs and ligature pairs. Further, the method includes creating, by the electronic device, a font using the determined handwriting characteristics on the electronic device.

Accordingly, the embodiments herein provide an electronic device comprising a personalized font generation controller coupled with a memory and a processor. The personalized font generation controller is configured to receive at least a portion of handwritten text as an input on the electronic device. Further, the personalized font generation controller is configured to analyse at least one of a kerning pair of the handwritten text and a ligature pair of the handwritten text to determine at least one handwriting characteristic of the text. Further, the personalized font generation controller is configured to create a font following the handwriting characteristics and configure the created font as a user selectable for future use.

Accordingly, the embodiments herein provide an electronic device comprising a personalized font generation controller coupled with a memory and a processor. The personalized font generation controller is configured to receive a handwritten text on the electronic device. The personalized font generation controller is configured to processes the handwritten text through a data driven model to extract a plurality of kerning pairs and a plurality ligature pairs from the handwritten text; and determine handwriting characteristics by analysing the kerning pairs and ligature pairs. The personalized font generation controller is configured to create a font using the determined handwriting characteristics on the electronic device.

-

The embodiments disclosed herein are illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:

FIG. 1a and FIG. 1b are example scenarios in which font generation is depicted, according to prior art;

FIG. 2 is an example scenario in which a personalized font generation is depicted on an electronic device, according to embodiments as disclosed herein;

FIG. 3 shows various hardware components of the electronic device, according to embodiments as disclosed herein;

FIG. 4 shows various hardware components of a personalized font generation controller included in the electronic device, according to embodiments as disclosed herein;

FIG. 5 to FIG. 9 are example flow charts illustrating a method for creating the personalized font generation in the electronic device, according to embodiments as disclosed herein;

FIG. 10 is an example scenario in which a hand writing assistance is depicted, according to embodiments as disclosed herein;

FIG. 11a is an example scenario in which a direct writing assistance is depicted, according to prior art;

FIG. 11b is an example scenario in which a direct writing assistance is depicted, according to embodiments as disclosed herein;

FIG. 12a is an example scenario in which a personalized greeting is depicted, according to prior art;

FIG. 12b-FIG. 12c are example scenarios in which a personalized greeting is depicted, according to embodiments as disclosed herein;

FIG. 13a is an example scenario in which a live message scenario is depicted, according to prior art;

FIG. 13b is an example scenario in which a live message scenario is depicted, according to embodiments as disclosed herein;

FIG. 14 is an example scenario in which a personalized font table generation is depicted, according to embodiments as disclosed herein;

FIG. 15 is an example scenario in which a personalized font generation is depicted, while taking photo or taking notes, according to embodiments as disclosed herein;

FIG. 16 is a detailed architecture scenario in which personalized font generation is depicted, according to embodiments as disclosed herein;

FIG. 17 is an example scenario in which kerning and ligature extraction is depicted, according to embodiments as disclosed herein;

FIG. 18 is an example scenario in which style extraction and character generation is depicted, according to embodiments as disclosed herein;

FIG. 19 is an example scenario in which on device font creation is depicted, according to embodiments as disclosed herein; and

FIG. 20 is an example scenario in which the font creation and personalization is depicted using a Unigram, Bigram, N-gram generation and the extra style input.

-

The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

In the proposed method, the method can be used to assist completely offline handwriting recreation with font creation and personalization. The method can be used to capture the handwriting randomness (e.g., cursive, different ways of writing same character) as a font. The method can be used to extract the Kerning pairs, ligature pairs, character endings. The method can be used to extract handwriting style and create generic writer style characters. The method can be used to extract the attributes required for font creation like baseline, ascent, descent. In the proposed method, the model inferencing not required once the font is created, any text can be converted to user handwriting style and the handwriting style can be shared with another electronic device. The method can be used to create the user font on the electronic device in a real time. This results in enhancing the user experience.

The method can be used to support the handwriting style adaptation as font. The method can be used to capture randomness in the handwritten text in the font. The method can be used to support the editing handwriting input with touch keyboard features like word predictions / suggestions, spell correction, auto corrections, grammar correction and provides on the go correction of handwritten text. The method can be used to enhance the fonts with visible attributes like strong, soft, gentle, formal, calm as per the user case requirement.

Referring now to the drawings, and more particularly to FIGS. 2 through 20, where similar reference characters denote corresponding features consistently throughout the figures, there are shown at least one embodiment.

FIG. 2 is an example scenario in which a personalized font generation is depicted on an electronic device (100), according to embodiments as disclosed herein. The electronic device (100) can be, for example, but not limited to a smart phone, a foldable device, a laptop, a virtual assistance device, a tablet, a smart TV, an immersive device, an internet of things (IoT) device or the like.

The electronic device (100) obtains the handwriting input from a user of the electronic device (100) and process the handwriting stroke corresponding to the handwriting input. Based on the handwriting input and the processed handwriting stroke, the electronic device (100) determines a N-gram ligature pair and a N-gram kerning pair.

In an embodiment, the electronic device (100) processes the handwriting stroke corresponding to the handwriting input by capturing randomness of the handwriting input over the period of time. The randomness of the handwriting input corresponds to cursive writing and different ways of writing same data item using a data driven controller (160 (as shown in the FIG. 3)). Further, the electronic device (100) determines the N-gram ligature pair and the N-gram kerning pair. The N-gram ligature pair and the N-gram kerning pair are used for recognizing a cursive-ness of the handwriting input, randomness of the at least one handwriting input and a variation of the at least one handwriting input.

Further, the electronic device (100) identifies the style vector by encoding the handwriting input, the N-gram ligature pair and the N-gram kerning pair. Further, the electronic device (100) generates the data item with the ligature from the N-gram ligature pair and the kerning from the the N-gram kerning pair based on the extracted style vector. The data item can be, for example, but not limited to a character, a symbol, a numeric value, and an alphabet.

Based on the generated data item with the ligature and the kerning, the electronic device (100) generates the personalized font. In an embodiment, the electronic device (100) generates the personalized font by extracting the font attributes based on the generated data item with the ligature and the kerning, generating a glyph for the data item, the ligature and the kerning pair, and generating the personalized font based on the generated glyph.

In an example, the glyph is the shape, design, or representation of a character, specified using vector graphics. Each glyph can be mapped to a Unicode character, and is rendered when that character is encountered. Further, for aesthetics, a combination of characters is represented by a single glyph, called ligature. In an example, In the below representation 1, in the first case, fi and fl are rendered using there individual character glyphs. In the second case, fi and fl are rendered using their ligature, a single glyph representing the combination of fi and fl.

Representation 1

Further, the Kerning is another way to improve visual appeal. It is the process of adjusting the spacing between characters in a proportional font as shown in the below representation 2.

Representation 2

The font attributes can be, for example, but not limited to a baseline of the handwriting input from the generated data item, an ascent of the handwriting input from the generated data item, a descent of the handwriting input from the generated data item, an advance width of the handwriting input from the generated data item, a kerning adjustment of the handwriting input from the generated data item, a left bearing of the handwriting input from the generated data item, and a right bearing of the handwriting input from the generated data item (the example scenario is explained in the FIG. 19).

Further, the electronic device (100) performs an action based on the generated personalized font. The action can be, for example, but not limited to a word prediction operation associated with the handwriting input, a spell check operation associated with the handwriting input, an auto correction operation associated with the handwriting input, a direct writing on the content, and writing with the personalized font on the electronic device (100).

In an embodiment, the writing with the personalized font on the electronic device (100) is performed by activating a personalized font mode on the electronic device (100), while writing as in handwriting a user input on the electronic device (100), mapping the writing user input with the personalized font, and producing the personalized font corresponding to the writing user input on the display (140) (as shown in the FIG. 3) of the electronic device (100).

In an embodiment, the direct writing on the content is performed by activating the personalized font mode on the electronic device (100), while writing the user input on the content displayed on the electronic device (100), selecting a user input region on the content (e.g., image, video or the like) displayed on the electronic device (100), writing the user input on the selected user input region on the content, mapping the user input with the personalized font, and producing the personalized font corresponding to the user input on the display (140) of the electronic device (100).

Further, the electronic device (100) extracts the font property of the personalized font and a predefined font. The font property can be, for example, but not limited to a strong, soft, gentle, formal, and calm. Further, the electronic device (100) learns the font property of the personalized font and the predefined font over a period of time using the data driven controller ((160) as shown in the FIG. 3). Further, the electronic device (100) optimizes the personalized font and the predefined font by applying the font property on the personalized font and the predefined font.

Further, the electronic device (100) stores the generated personalized font in the electronic device (100) and share the generated personalized font to another electronic device.

FIG. 3 shows various hardware components of the electronic device (100), according to embodiments as disclosed herein. In an embodiment, the electronic device (100) includes a processor (110), a communicator (120), a memory (130), the display (140), a personalized font generation controller (150) and a data driven controller (160). The processor (110) is coupled with the communicator (120), the memory (130), the display (140), the personalized font generation controller (150) and the data driven controller (160).

The personalized font generation controller (150) is physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware.

In an embodiment, the personalized font generation controller (150) is configured to obtain the handwriting input from the user of the electronic device (100) and process the handwriting stroke corresponding to the handwriting input. Based on the handwriting input and the processed handwriting stroke, the the personalized font generation controller (150) is configured to determines the N-gram ligature pair and the N-gram kerning pair.

In an embodiment, the personalized font generation controller (150) is configured to process the handwriting stroke corresponding to the one handwriting input by capturing randomness of the handwriting input over the period of time. Further, the personalized font generation controller (150) is configured to determine the N-gram ligature pair and the N-gram kerning pair.

Further, the personalized font generation controller (150) is configured to identify the style vector by encoding the handwriting input, the N-gram ligature pair and the N-gram kerning pair. Further, the personalized font generation controller (150) is configured to generate the data item with the ligature from the N-gram ligature pair and the kerning from the the N-gram kerning pair based on the extracted style vector.

Based on the generated data item with the ligature and the kerning, the the personalized font generation controller (150) is configured to generate the personalized font. In an embodiment, the personalized font generation controller (150) is configured to generate the personalized font by extracting the font attributes based on the generated data item with the ligature and the kerning, generating a glyph for the data item, the ligature and the kerning pair, and generating the personalized font based on the generated glyph.

Further, the personalized font generation controller (150) is configured to perform the action based on the generated personalized font. Further, the personalized font generation controller (150) is configured to extract the font property of the personalized font and the predefined font. Further, the personalized font generation controller (150) is configured to optimize the personalized font and the predefined font by applying the font property on the personalized font and the predefined font.

Further, the processor (110) is configured to execute instructions stored in the memory (130) and to perform various processes. The communicator (120) is configured for communicating internally between internal hardware components and with external devices via one or more networks. The memory (130) also stores instructions to be executed by the processor (110). The memory (130) may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory (130) may, in some examples, be considered a non-transitory storage medium. The term "non-transitory" may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted that the memory (130) is non-movable. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache).

Further, at least one of the plurality of modules/controller may be implemented through the AI model. A function associated with the AI model may be performed through the non-volatile memory, the volatile memory, and the processor (110). The processor (110) may include one or a plurality of processors. At this time, one or a plurality of processors may be a general purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and/or an AI-dedicated processor such as a neural processing unit (NPU).

The one or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or AI model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

Here, being provided through learning means that a predefined operating rule or AI model of a desired characteristic is made by applying a learning algorithm to a plurality of learning data. The learning may be performed in a device itself in which AI according to an embodiment is performed, and/o may be implemented through a separate server/system.

The AI model may comprise of a plurality of neural network layers. Each layer has a plurality of weight values, and performs a layer operation through calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, self-supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

Although the FIG. 3 shows various hardware components of the electronic device (100) but it is to be understood that other embodiments are not limited thereon. In other embodiments, the electronic device (100) may include less or more number of components. Further, the labels or names of the components are used only for illustrative purpose and does not limit the scope of the invention. One or more components can be combined together to perform same or substantially similar function in the electronic device (100).

FIG. 4 shows various hardware components of the personalized font generation controller (150) included in the electronic device (100), according to embodiments as disclosed herein. In an embodiment, the personalized font generation controller (150) includes a ligature and kerning extraction controller (150a), a style analyzer and text generation controller (150b) and a font attributes extraction and creation controller (150c).

In an embodiment, the ligature and kerning extraction controller (150a) is configured to obtain the handwriting input from the user of the electronic device (100) and process the handwriting stroke corresponding to the handwriting input. Based on the handwriting input and the processed handwriting stroke, the ligature and kerning extraction controller (150a) is configured to determines the N-gram ligature pair and the N-gram kerning pair.

In an embodiment, the ligature and kerning extraction controller (150a) is configured to process the handwriting stroke corresponding to the one handwriting input by capturing randomness of the handwriting input over the period of time. Further, the ligature and kerning extraction controller (150a) is configured to determine the N-gram ligature pair and the N-gram kerning pair.

The ligature and kerning extraction controller (150a) is physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware.

Further, the style analyzer and text generation controller (150b) is configured to identify the style vector by encoding the handwriting input, the N-gram ligature pair and the N-gram kerning pair. The style analyzer and text generation controller (150b) is physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware.

Further, the font attributes extraction and creation controller (150c) is configured to generate the data item with the ligature from the N-gram ligature pair and the kerning from the the N-gram kerning pair based on the extracted style vector.

Based on the generated data item with the ligature and the kerning, the font attributes extraction and creation controller (150c) is configured to generate the personalized font. In an embodiment, the font attributes extraction and creation controller (150c) is configured to generate the personalized font by extracting the font attributes based on the generated data item with the ligature and the kerning, generating a glyph for the data item, the ligature and the kerning pair, and generating the personalized font based on the generated glyph.

Further, the font attributes extraction and creation controller (150c) is configured to extract the font property of the personalized font and a predefined font. Further, the font attributes extraction and creation controller (150c) is configured to optimize the personalized font and the predefined font by applying the font property on the personalized font and the predefined font.

The font attributes extraction and creation controller (150c) is physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware.

Although the FIG. 4 shows various hardware components of the personalized font generation controller (150) but it is to be understood that other embodiments are not limited thereon. In other embodiments, the personalized font generation controller (150) may include less or more number of components. Further, the labels or names of the components are used only for illustrative purpose and does not limit the scope of the invention. One or more components can be combined together to perform same or substantially similar function in the personalized font generation controller (150).

FIG. 5 to FIG. 9 are example flow charts (500-900) illustrating a method for creating the personalized font generation in the electronic device (100), according to embodiments as disclosed herein.

As shown in the FIG. 5, the operations (502-512) are handled by the personalized font generation controller (150). At 502, the method includes obtaining the handwriting input from the user of the electronic device (100). At 504, the method includes processing the handwriting stroke corresponding to the handwriting input. At 506, the method includes determining the N-gram ligature pair and the N-gram kerning pair based on the handwriting input and the processed handwriting stroke. At 508, the method includes identifying the style vector by encoding the handwriting input, the N-gram ligature pair and the N-gram kerning pair. At 510, the method includes generating the data item with at least one ligature from the at least one N-gram ligature pair and at least one kerning from the at least one N-gram kerning pair based on the at least one extracted style vector. At 512, the method includes generating the personalized font based on the at least one generated data item with the at least one ligature and the at least one kerning.

As shown in the FIG. 6, the operations (602-608) are handled by the personalized font generation controller (150). At 602, the method includes activating the personalized font mode in the electronic device (100). At 604, the method includes obtaining the one handwriting input, from the user of the electronic device (100), in the personalized font mode. At 606, the method includes determining the N-gram ligature pair and the N-gram kerning pair based on the handwriting input and the handwriting stroke associated with the handwriting input. At 608, the method includes generating the personalized font based on the at least one determined N-gram ligature pair and at least one determined N-gram kerning pair.

As shown in the FIG. 7, the operations (702-708) are handled by the personalized font generation controller (150). At 702, the method includes receiving the portion of handwritten text as an input on the electronic device (100). At 704, the method includes analysing the kerning pair of the handwritten text and the ligature pair of the handwritten text to determine at least one handwriting characteristic of the text. At 706, the method includes creating the font following the handwriting characteristics. At 708, the method includes configuring the created font as a user selectable for future use.

As shown in the FIG. 8, the operations (802-806) are handled by the personalized font generation controller (150). At 802, the method includes receiving the handwritten text on the electronic device (100). At 804, the method includes processing the handwritten text through the data driven controller (160) to extract the plurality of kerning pairs and the plurality ligature pairs from the handwritten text, and determine handwriting characteristics by analysing the kerning pairs and ligature pairs. At 806, the method includes creating the font using the determined handwriting characteristics on the electronic device.

As shown in the FIG. 9, At 902, the electronic device (100) receives the user input. At 904, instances where letters are joined cursively, where letters are joined as ligatures, Instances which should be utilized to generate individual letters are generated based on the user input. At 906, the electronic device generates the lowercase letter, the upper case letter, the identified ligature and generate the out of vocab words. At 908, the electronic device (100) stores the text from generated font.

FIG. 10 is an example scenario in which a hand writing assistance is depicted, according to embodiments as disclosed herein. Based on the proposed method, the electronic device (100) provides the handwriting assistance, auto corrections, grammar, word predictions to the user.

FIG. 11a is an example scenario in which a direct writing assistance is depicted, according to prior art.

FIG. 11b is an example scenario in which a direct writing assistance is depicted, according to embodiments as disclosed herein. In an embodiment, the writing with the personalized font on the electronic device (100) is performed by activating a personalized font mode on the electronic device (100), while writing as in handwriting a user input on the electronic device (100), mapping the writing user input with the personalized font, and producing the personalized font corresponding to the writing user input on the display (140) of the electronic device (100).

FIG. 12a is an example scenario in which a personalized greeting is depicted, according to prior art. In the existing methods, the greeting image copied and shared as it is.

FIG. 12b-FIG. 12c are example scenarios in which a personalized greeting is depicted, according to embodiments as disclosed herein. Based on the proposed method, once the greeting image is copied, auto generate greeting images in user handwriting both in English and his/her preferred handwritten languages maintaining aesthetics. The greetings in own handwriting is depicted in the FIG. 12b and the greetings in own handwriting in the native language (i.e., Hindi) is depicted in the FIG. 12c.

FIG. 13a is an example scenario in which a live message scenario is depicted, according to prior art. In the existing methods, for the live message, if there is spelling mistake in initial words, but the electronic device does not correct the spelling mistake, so that the user of the electronic device (100) has to revert everything and recreate the message.

FIG. 13b is an example scenario in which a live message scenario is depicted, according to embodiments as disclosed herein. Based on the proposed method, in live message, erroneous words can be corrected without recreating message again maintaining orientation of original handwriting input.

FIG. 14 is an example scenario in which a personalized font table generation is depicted, according to embodiments as disclosed herein. Based on the proposed method, providing all the glyphs in user's handwriting in vector drawable format, the electronic device (100) can create a font using reasonable default values for some of the font metrics, and calculating the rest based on provided glyphs.

In an example, the personalized font generation is depicted, while taking photo and the user of the electronic device (100) takes the notes on the electronic device (100) as shown in the FIG. 15. Also, the FIG. 15 depicts the style extraction operations using the CNN model.

FIG. 16 is a detailed architecture scenario (1600) in which personalized font generation is depicted, according to embodiments as disclosed herein. The operations and functions of the personalized font generation is already explained in the FIG. 2 to FIG. 4. Further, the architecture can be used to extract the plurality of ligature and kerning using the AI model. The sequence to sequence AI model does character boundary marking and ligature/kerning start/end marking based on input handwriting input. Further, the style extraction and character generation is provided using AI model. The CNN based AI model does style extraction based on handwriting input and does character/ligature/kerning generalized generation based on handwriting input and extracted ligature/kerning. Further, the architecture can be used to perform the font attributes extraction and glyph generation. FIG. 17 is an example scenario (1700) in which kerning and ligature extraction is depicted, according to embodiments as disclosed herein. The operations and functions of the kerning and ligature extraction is already explained in the FIG. 2 to FIG. 4. The example scenario depicts the extraction of the plurality of ligature and kerning using the AI model. The sequence to Sequence AI model does character boundary marking and ligature/kerning start/end marking based on the input handwriting input.

FIG. 18 is an example scenario (1800) in which style extraction and character generation is depicted, according to embodiments as disclosed herein. The operations and functions of the style extraction and character generation is already explained in the FIG. 2 to FIG. 4. The example scenario depicts the style extraction and character generation using the AI model. The CNN based AI model does style extraction based on handwriting input and does character/ligature/kerning generalized generation based on the handwriting input and extracted ligature/kerning.

FIG. 19 is an example scenario (1900) in which on device font creation is depicted, according to embodiments as disclosed herein. In an embodiment, the electronic device (100) generates the personalized font by extracting the font attributes based on the generated data item with the ligature and the kerning, generating the glyph for the data item, the ligature and the kerning pair, and generating the personalized font based on the generated glyph. The font attributes can be, for example, but not limited to a baseline of the handwriting input from the generated data item, an ascent of the handwriting input from the generated data item, a descent of the handwriting input from the generated data item, an advance width of the handwriting input from the generated data item, a kerning adjustment of the handwriting input from the generated data item, a left bearing of the handwriting input from the generated data item, and a right bearing of the handwriting input from the generated data item.

In an example scenario, the font creation and personalization is depicted using the Unigram, Bigram, N-gram generation and the extra style input as shown in the FIG. 20.

The various actions, acts, blocks, steps, or the like in the flow charts (500-900) may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the invention.

The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements can be at least one of a hardware device, or a combination of hardware device and software module.

The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of at least one embodiment, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

Claims

A method for handling a personalized font, the method comprising:

obtaining, by an electronic device (100), at least one handwriting input from a user of the electronic device (100);

processing, by the electronic device (100), at least one handwriting stroke corresponding to the at least one handwriting input;

determining, by the electronic device (100), at least one N-gram ligature pair and at least one N-gram kerning pair based on the at least one handwriting input and the at least one processed handwriting stroke;

identifying, by the electronic device (100), at least one style vector by encoding the at least one handwriting input, the at least one N-gram ligature pair and the at least one N-gram kerning pair;

generating, by the electronic device (100), at least one data item with at least one ligature from the at least one N-gram ligature pair and at least one kerning from the at least one N-gram kerning pair based on the at least one extracted style vector; and

generating, by the electronic device (100), at least one personalized font based on the at least one generated data item with the at least one ligature and the at least one kerning.
The method as claimed in claim 1, wherein the method comprises:

performing, by the electronic device (100), at least one action based on the at least one generated personalized font, wherein the at least one action comprises at least one of a word prediction operation associated with the at least one handwriting input, a spell check operation associated with the at least one handwriting input, an auto correction operation associated with the at least one handwriting input, a direct writing on at least one content, and writing with the at least one personalized font on the electronic device (100).
The method as claimed in claim 2, wherein writing with the at least one personalized font on the electronic device (100) is performed by:

activating a personalized font mode on the electronic device (100), while writing a user input on the electronic device (100);

mapping the writing user input with the at least one personalized font; and

producing the at least one personalized font corresponding to the writing user input on a display (140) of the electronic device (100).
The method as claimed in claim 2, wherein the direct writing on the at least one content is performed by:

activating a personalized font mode on the electronic device (100), while writing a user input on the at least one content displayed on the electronic device (100);

selecting a user input region on the at least one content displayed on the electronic device (100);

writing the user input on the selected user input region on the at least one content;

mapping the user input with the at least one personalized font; and

producing the at least one personalized font corresponding to the user input on a display (140) of the electronic device (100).
The method as claimed in claim 1, wherein the method comprises:

extracting, by the electronic device (100), at least one font property of the at least one personalized font and a predefined font, wherein the at least one font property comprises at least one of strong, soft, gentle, formal, and calm;

learning, by the electronic device (100), at least one font property of the at least one personalized font and the predefined font over a period of time using a data driven controller (160); and

optimizing, by the electronic device (100), the at least one personalized font and the predefined font by applying the at least one font property on the at least one personalized font and the predefined font.
The method as claimed in claim 1, wherein the method comprises:

storing, by the electronic device (100), the generated personalized font in the electronic device (100); and

sharing, by the electronic device (100), the generated personalized font to another electronic device.
The method as claimed in claim 1, wherein generating, by the electronic device (100), the at least one personalized font based on the at least one generated data item with the at least one ligature and the kerning comprises:

extracting, by the electronic device (100), at least one font attributes based on the at least one generated data item with the at least one ligature and the kerning;

generating, by the electronic device (100), at least one glyph for the at least one data item, at least one ligature and at least one kerning pairs; and

generating, by the electronic device (100), the personalized font based on the at least one generated glyph.
The method as claimed in claim 7, wherein the at least one font attributes comprises at least one of a baseline of the at least one handwriting input from the at least one generated data item, an ascent of the at least one handwriting input from the at least one generated data item, a descent of the at least one handwriting input from the at least one generated data item, an advance width of the at least one handwriting input from the at least one generated data item, a kerning adjustment of the at least one handwriting input from the at least one generated data item, a left bearing of the at least one handwriting input from the at least one generated data item, and a right bearing of the at least one handwriting input from the at least one generated data item.
The method as claimed in claim 1, wherein the extracting, by the electronic device (100), the at least one N-gram ligature pair and the at least one N-gram kerning pair comprises:

processing, by the electronic device (100), at least one handwriting stroke corresponding to the at least one handwriting input by capturing randomness of at least one handwriting input over a period of time, wherein the randomness of at least one handwriting input corresponds to cursive writing and different ways of writing same data item using a data driven controller;

extracting, by the electronic device (100), the at least one N-gram ligature pair and at least one N-gram kerning pair.
The method as claimed in claim 1, wherein the at least one N-gram ligature pair and the at least one N-gram kerning pair are used for recognizing a cursive-ness of the at least one handwriting input, randomness of the at least one handwriting input and a variation of the at least one handwriting input, wherein the at least one data item comprises at least one of a character, a symbol, a numeric value, and an alphabet.
An electronic device (100), comprising:

a memory (130),

a processor (110), and

a personalized font generation controller (150), coupled with the memory (130) and the processor (110), configured to:

obtain at least one handwriting input from a user of the electronic device (100);

process at least one handwriting stroke corresponding to the at least one handwriting input;

determine at least one N-gram ligature pair and at least one N-gram kerning pair based on the at least one handwriting input and the at least one processed handwriting stroke;

identify at least one style vector by encoding the at least one handwriting input, the at least one N-gram ligature pair and the at least one N-gram kerning pair;

generate at least one data item with at least one ligature from the at least one N-gram ligature pair and at least one kerning from the at least one N-gram kerning pair based on the at least one extracted style vector; and

generate at least one personalized font based on the at least one generated data item with the at least one ligature and the at least one kerning.
The electronic device (100) as claimed in claim 11, wherein the personalized font generation controller (150) is configured to perform at least one action based on the at least one generated personalized font, wherein the at least one action comprises at least one of a word prediction operation associated with the at least one handwriting input, a spell check operation associated with the at least one handwriting input, an auto correction operation associated with the at least one handwriting input, a direct writing on at least one content, and writing with the at least one personalized font on the electronic device (100).
The electronic device (100) as claimed in claim 12, wherein writing with the at least one personalized font on the electronic device (100) is performed by:

activating a personalized font mode on the electronic device (100), while writing a user input on the electronic device (100);

mapping the writing user input with the at least one personalized font; and

producing the at least one personalized font corresponding to the writing user input on a display (140) of the electronic device (100).
The electronic device (100) as claimed in claim 12, wherein the direct writing on the at least one content is performed by:

activating a personalized font mode on the electronic device (100), while writing a user input on the at least one content displayed on the electronic device (100);

selecting a user input region on the at least one content displayed on the electronic device (100);

writing the user input on the selected user input region on the at least one content;

mapping the user input with the at least one personalized font; and

producing the at least one personalized font corresponding to the user input on a display (140) of the electronic device (100).
The electronic device (100) as claimed in claim 11, wherein the personalized font generation controller (150) is configured to:

extract at least one font property of the at least one personalized font and a predefined font, wherein the at least one font property comprises at least one of strong, soft, gentle, formal, and calm;

learn at least one font property of the at least one personalized font and the predefined font over a period of time using a data driven controller (150); and

optimize the at least one personalized font and the predefined font by applying the at least one font property on the at least one personalized font and the predefined font.