An audio reader device

EP4285343A4Inactive Publication Date: 2024-11-27YILDIZ TEKNOLOJI TRANSFER OFISI ANONIM SIRKETI
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
EP2022746372
Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-01-28
Filing Date
2022-01-27
Publication Date
2024-11-27
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing audio reader devices are difficult for visually impaired individuals to use effectively, as they require precise scanning of written texts, which is challenging due to the need for proper alignment and orientation of the scanning surface.

Method used

An audio reader device equipped with cameras, optical character recognition software, and text-to-speech software that can capture images of text from any angle, process them to generate digital text data, and convert it into audio, along with a control unit to regulate operations, and a system for data transfer between devices, allowing for easy access and sharing of digital text and audio data.

Benefits of technology

Enables visually impaired users to easily capture and convert printed text into audio, improving accessibility and usability by allowing text to be read aloud without the need for precise scanning, and facilitating data sharing among devices.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 000014
    Figure 000014
  • Figure 000015
    Figure 000015
  • Figure 000016
    Figure 000016
Patent Text Reader

Abstract

The present invention provides an audio reader device (10). Said audio reader device (10) comprises one or more cameras (20) for capturing one or more images of a surface in order to obtain one or more digital image data, an optical character recognition software to detect a text in the captured images by processing said image data and to generate a text data based on the text detected, a text-to-speech software for converting text data into an audio data, and a control unit for regulating the operation of the optical character recognition software and the text-to-speech software. The present invention also provides a system (100) comprising one or more central units (50) suitable for establishing data transfer communication with one or more audio reader devices (10). Said one or more central units (50) comprise one or more data transfer mechanisms for exchanging one or more digital image data and / or one or more text data and / or one or more digital audio data with one or more audio reader devices (10). Said one or more central units (50) also comprise a digital library provided with one or more memory members for storing one or more digital image data and / or one or more text data and / or one or more digital audio data.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] AN AUDIO READER DEVICE

[0002] Technical Field of the Invention

[0003] The present invention relates to an audio reader device enabling users to listen to written texts, and a system comprising such a device.

[0004] Background Art

[0005] Thanks to electronic books and audio books, it is possible to read written texts digitally or listen them aloud. In this way, it is easier for users to access information. Audio books are generally created by recording written texts being read aloud by a person. Electronic books are obtained by transferring written texts into digital medium. Moreover, written texts transferred to digital medium can be read aloud by using different software. Thanks to the fact that written texts can be listened to, it is possible for illiterate people and visually impaired people to access information. By means of the scanners in the prior art, written texts can be scanned and transferred to digital medium. However, in order to scan the written texts in the prior art scanners, the surface on which the written text is present must be scanned very properly. Performing such proper scanning is almost impossible especially for visually impaired people.

[0006] An example of the prior art is the patent application no. US 2015 / 242096. Said publication relates to a system and method that allow visually impaired individuals to access information printed on a document.

[0007] Objects of the Invention

[0008] The main object of the present invention is to eliminate the problems encountered in the prior art.

[0009] Another object of the present invention is to provide an audio reader device that makes it easier to scan written texts and transfer them to digital medium.

[0010] Another object of the present invention is to provide an audio reader device in which written texts transferred to digital medium can be read aloud. Still another object of the present invention is to provide a system suitable for transferring digital image data, digital text data or digital audio data with an audio reader device by establishing a data transfer communication with one or more audio reader devices.

[0011] Summary of the Invention

[0012] The audio reader device of the invention comprises one or more cameras for capturing one or more images of a surface in order to obtain one or more digital image data, an optical character recognition software to detect a text in the captured images by processing said image data and to generate a text data based on the text detected, a text- to-speech software for converting text data into an audio data, and a control unit for regulating the operation of the optical character recognition software and the text-to- speech software.

[0013] The device is suitably configured to capture images of a surface from which a user desires to obtain digital text data by means of the camera. If there is text in the captured images, the device is suitably configured to obtain text data about said text by means of the optical character recognition software. The obtained text data is converted into an audio data by the text-to-speech software. In this way, the texts on the page surfaces of a magazine, book or similar printed publication, or on surfaces that may contain text such as a signboard or banner, can be captured by an audio reader device and converted into audio data by the user, and can be listened to.

[0014] The present invention also provides a system suitable for establishing data transfer communication with one or more audio reader devices. The system comprises one or more data transfer mechanisms for exchanging one or more digital image data and / or one or more text data and / or one or more digital audio data with the audio reader device, and a digital library provided with one or more memory members for storing one or more digital image data and / or one or more text data and / or one or more digital audio data. In this way, the system allows users to listen to written text by transferring digital image data, digital text data or digital audio data from a digital library, without the need to scan the written texts every time a printed publication is desired to be read. In addition, with the system of the invention, the users are provided with the opportunity to transfer digital image data, digital text data or digital audio data obtained previously from the written texts to each other through the data transfer mechanism created between the audio reader devices, thereby offering ease of use.

[0015] Brief Description of the Drawings

[0016] The subject of the present invention is illustrated in the accompanying drawings for better understanding thereof. The drawings are only included for better understanding of the present invention and are not intended to limit the scope of the application.

[0017] Figure 1 is a schematic view of an audio reader device according to the present invention. Here, the audio reader device is provided with a single camera.

[0018] Figure 2 is a schematic view of another embodiment of the audio reader device of the present invention. Here, the audio reader device is provided with more than one camera.

[0019] Figure 3 is an exemplary schematic illustration of a system according to the present invention, comprising a central unit in data transfer communication with more than one audio reader device.

[0020] Detailed Description of the Invention

[0021] With reference to the drawings briefly explained above, the present invention is hereinafter described in detail with reference to the accompanying drawings. The list of reference signs in the drawings is as follows;

[0022] 10. audio reader device

[0023] 20. camera

[0024] 30. first command switch

[0025] 31. second command switch

[0026] 50. central unit

[0027] 100. system

[0028] The audio reader device (10) (in short: device (10)) of the present invention comprises one or more cameras (20) for capturing one or more images of a surface to obtain one or more digital image data. The audio reader device (10) also comprises an optical character recognition software to detect a text in the captured images by processing said image data and to generate a text data based on the text detected. The audio reader device (10) also comprises a text-to-speech software for converting the text data into an audio data. The audio reader device (10) comprises a control unit for regulating the operation of the optical character recognition software and the text-to-speech software.

[0029] In an exemplary use of the audio reader device (10) which is the subject of the invention, the audio reader device (10) allows that the camera (20) is pointed at a surface on which text can be available in order to capture one or more images of the surface. The images captured by the camera (20) are processed by means of the optical character recognition software in the audio reader device (10). Therefore, if there is text in the captured images, a text data can be generated by processing said text. As an optical character recognition software, current Python Tesseract OCR, PILLOW or OPEN CV libraries may, for example, be used.

[0030] It is possible to adapt the optical character recognition software in such a way that it can detect the text even if the camera (20) is held upside down or titled at the instance of capturing an image, regardless of the direction of the text that may be present in an image that is in the frame of the camera (20). Accordingly, if the image captured by the camera (20) is reversed or tilted, the optical character recognition software may, for example, determine that the image is not plane, and the captured image may be processed accordingly, thereby generating the corresponding digital text data without error. The optical character software may be adapted to obtain text data from written texts having different font sizes. The text data generated is converted into an audio data by the text-to-speech software. Said image, text and / or audio data may be in a file format suitable for running on a computer. The control unit is suitably configured to control the operation of the camera (20), the optical character recognition software, and the text-to- speech software. Accordingly, the control unit may be provided with a processor and software adapted to operate said processor.

[0031] In an embodiment of the present invention, the audio reader device (10) comprises an infrared sensor, which is suitably configured to determine a distance between a surface whose image is intended to be captured and the camera (20). The camera (20) may be adapted to perform focusing based on the distance value determined by the infrared sensor. In this case, one or more images captured by the camera (20) may be ensured to have an improved level of resolution, which may be processed by the optical character recognition software at an improved level of precision and reality so that the text data is generated with a lower margin of error.

[0032] In an embodiment of the invention, the audio reader device (10) comprises a lens for focusing on the image to be captured. Said lens may be a lens capable of providing image focusing in an image capture process preferably at a short distance, e.g. at a distance in the range of 1 cm to 3 cm. In this context, a macro lens may be used. Such an audio reader device (10) allows the user to capture an image by placing or moving it on a surface to be scanned. Thus, it is easier for visually impaired individuals to scan texts in printed sources such as books or magazines in an easy and clear manner. On a side of an audio reader device (10) according to this description having one or more cameras (20), three or more protrusions (not shown) may be provided extending in a direction perpendicular to a plane passing through that side. Said protrusions may be configured to extend perpendicular to said plane at a distance, for example in the range of 1 cm to 3 cm. Thus, the audio reader device (10) allows the distance between the camera(s) (20) and the surface to be scanned to be easily stabilized.

[0033] In an embodiment of the invention, the audio reader device (10) may include one or more image sensors coupled with one or more cameras (20) to convert a captured image into digital pixels. An audio reader device (10) according to this description may be considered to be adapted for converting the image captured by the camera (20) into a digital image data by means of the image sensor. An image sensor suitable for use to this end may, for example, be a charged coupling device (in short: CCD) or a complimentary metal-oxide semiconductor (in short: CMOS). The precision level of the selected image sensor determines the size, resolution and / or quality of the digital image data to be obtained.

[0034] In an embodiment of the audio reader device (10) of the invention, the audio reader device (10) comprises more than one camera (20) suitable to operate simultaneously and collaboratively in order to capture more than one image of a surface simultaneously. In Figure 2, in accordance with an exemplary embodiment in this context, a schematic view of an audio reader device (10) having 9 cameras (20) arranged in a matrix arrangement with three rows and three columns is illustrated. By using more than one camera (20), it is ensured that the entire text on a surface is scanned in a faster manner. In an exemplary embodiment of the audio reader device (10) of the invention, one or more cameras (20) are suitable for capturing wide angle images. With such configuration, even if the number of cameras (20) in the audio reader device (10) is at minimum, and even if there is only one camera (20) in the audio reader device (10), it is possible to capture an image of a surface with a relatively wide angle of frame. The audio reader device (10) having such configuration is suitable to operate with a high level of accuracy even in a situation where the number of images captured is relatively low, in order to create a holistic text data by capturing multiple images of a surface and combining them.

[0035] A possible embodiment of the audio reader device (10) of the invention is suitably arranged to obtain text data by combining and processing images, of a text that is too large to fit in the frame of a single camera (20), captured by more than one camera (20) suitable to operate together. When images are captured by more than one camera (20) located at different positions on one side of the audio reader device (10), the frames corresponding to the images captured by each camera (20) may be different from each other, but may contain regions partially overlapping with each other. Therefore, common text parts may be available in more than one image captured, depending on the location of the cameras (20). The images captured can be combined by means of the software such that said common text parts overlap. Thus, more than one image captured and more than one image captured from a surface that would not fit in the frame of a single camera (20) are combined in an original manner, obtaining a text data with a high level of accuracy. For example, said configuration can be achieved when the optical character recognition software of the audio reader device (10) is configured to perform such an operation.

[0036] A possible embodiment of the audio reader device (10) of the invention is arranged to obtain text data by combining and processing the images that are obtained from different parts of the text captured by means of a single camera (20). The audio reader device (10) with a single camera (20) is schematically shown in Fig. 1. By moving the camera (20) over the surface on which the written text is present, sequential images of different parts of the text can be captured by the camera (20). The images captured can be combined by means of the software such that said common text parts overlap. Thus, more than one image captured and more than one image captured from a surface that would not fit in the frame of a single camera (20) are combined in an original manner, obtaining a text data with a high level of accuracy. For example, said configuration can be achieved when the optical character recognition software of the audio reader device (10) is configured to perform such an operation.

[0037] A possible embodiment of the audio reader device (10) of the invention comprises a communication interface suitable for wireless communication. In this way, the user's control of the audio reader device (10) can be performed wirelessly. Moreover, in this way, it is possible for more than one audio reader device (10) to communicate wirelessly with each other, or to transfer data between them. Again, with such configuration, communication between the audio reader device (10) and a remote data library, is enabled for data transfer and / or software update purposes. As a wireless communication interface, any or more of the wireless communication protocols such as WiFi, Bluetooth, NFC can be used.

[0038] A possible embodiment of the audio reader device (10) of the invention may include an audio output unit (not shown) for vocalizing audio data. The audio output unit may be provided with one or more sound wave generators that generate sound waves for direct vocalization of the audio data. The sound wave generator may, for example, be one or more loudspeakers and / or headphones. Alternatively, or additionally, the audio reader device (10) of the invention may be provided with a connection interface to provide one or more sound wave generators with a data flow associated with the audio file. The connection interface may, for example, include one or more options selected from jack, Bluetooth, WiFi. A possible embodiment of the audio reader device (10) of the invention may comprise a first command switch (30) for initiating an image capture process. The first command switch (30) is preferably a mechanical switch. More preferably, the first command switch

[0039] (30) forms a protrusion towards the outside of the body of the audio reader device (10). Figure 1 and Figure 2 schematically show a first command switch (30) in accordance with these descriptions. It is thus easier for a visually impaired user to determine the location of the first command switch (30), which is in accordance with any of these descriptions, and to start the imaging process by pressing the first command switch (30).

[0040] A possible embodiment of the audio reader device (10) of the invention comprises a second command switch (31) for initiating a vocalization process. The second command switch (31) is preferably a mechanical switch. For example, by interfering with the second command switch (31), a vocalization process can be initiated and stopped by a user based on the voice data. Figure 1 and Figure 2 schematically show a second command switch

[0041] (31). The second command switch (31) is preferably a mechanical switch, with the reasons for preference for the first command switch (30) being also applicable here. More preferably, the second command switch (31) forms a protrusion towards the outside of the body of the audio reader device (10).

[0042] A possible embodiment of the audio reader device (10) of the invention comprises a screen. Such an embodiment allows the audio reader device (10) to be controlled by the user via the screen. Moreover, such an embodiment allows the images captured by the camera (20) and / or the frame of the camera (20) to be followed on the screen.

[0043] A possible embodiment of the audio reader device (10) of the present invention comprises a memory for storing the captured images and / or storing the text data generated by the optical character software and / or storing one or more audio data generated by the text-to- speech software. In this way, by storing one or more of one or more images, text data and audio data obtained from a surface, for example a printed source, it is possible to access the recorded content or data at a later time and repeatedly. For example, when a user desires to listen to an audio data that is previously stored in the memory, he may again access the relevant audio data from the memory. A possible embodiment of the audio reader device (10) of the invention comprises an infrared sensor for determining a distance between the camera (20) and a surface, i.e., a distance between the surface and the camera (20); a lens for focusing on the image to be captured; an image sensor for converting the captured image into digital pixels; and one or more audio output units for vocalizing said one or more audio data. The text data obtained from the captured images is converted into audio data by the text-to-speech software. The audio data is transferred to the audio output unit, to the control unit to be vocalized. By using the infrared sensor, the lens, the image sensor and the camera (20) together, the resolution of the images captured can be increased, thus, the level of reality of the obtained text data and audio data is improved.

[0044] A possible embodiment of the audio reader device (10) of the invention is a smart mobile device. Such an audio reader device (10) may take the form of a smartphone or tablet.

[0045] In addition, the present invention provides a system (100) comprising one or more audio reader devices (10) according to any or more of the above descriptions, and one or more central units (50). Said system (100) comprises one or more central units (50); one or more data transfer mechanisms for exchanging one or more digital image data and / or one or more text data and / or one or more digital audio data with said one or more audio reader devices (10). In this way, it is possible to transfer data between the audio reader devices (10). In a possible embodiment of the system (100) of the invention, one or more data transfer mechanisms are adapted to carry out said data exchange wirelessly. Such a data transfer mechanism enables wireless data transfer between the system (100) and said one or more audio reader devices (10) by using one or more wireless communication protocols such as WiFi, Bluetooth, NFC. The one or more central units (50) in said system (100) also comprise one or more digital libraries provided with one or more memory members for storing one or more digital image data and / or one or more text data and / or one or more digital audio data. This embodiment allows the digital data in said digital library to be shared among users by means of the data transfer mechanism via the audio reader devices (10).

Claims

CLAIMS1. An audio reader device (10), wherein said audio reader device (10) comprises: one or more cameras (20) for capturing one or more images of a surface to obtain one or more digital image data, an optical character recognition software to detect a text in the captured images by processing said image data and to generate a text data based on the text detected, a text-to-speech software for converting the text data into an audio data, and a control unit for regulating the operation of the optical character recognition software and the text-to-speech software.

2. The audio reader device (10) according to claim 1, comprising an infrared sensor to determine a distance between the surface and the camera (20).

3. The audio reader device (10) according to any one of claim 1 or 2, comprising a lens for focusing on the image to be captured.

4. The audio reader device (10) according to any one of claims 1 to 3, comprising an image sensor for converting the captured image into digital pixels.

5. The audio reader device (10) according to any one of claims 1 to 4, comprising more than one camera (20) suitable to operate simultaneously and collaboratively, in order to capture more than one image of said surface simultaneously.

6. The audio reader device (10) according to claim 5, wherein said audio reader device (10) is arranged to obtain text data by combining and processing the images, of different parts of a text that is too large to fit in the frame of a single camera (20), captured by more than one camera (20) suitable to operate together.

7. The audio reader device (10) according to any one of claims 1 to 4, wherein said audio reader device (10) is arranged to obtain text data by combining and processing the images obtained from different parts of the text captured by means of a single camera (20).

8. The audio reader device (10) according to any one of claims 1 to 7, comprising a communication interface suitable for wireless communication.

9. The audio reader device (10) according to any one of claims 1 to 8, comprising an audio output unit for vocalizing audio data.

10. The audio reader device (10) according to any one of claims 1 to 9, comprising a first command switch (30) for initiating an image capture process.

11. The audio reader device (10) according to any one of claims 1 to 10, comprising a second command switch (31) for initiating a vocalization process.

12. The audio reader device (10) according to any one of claims 1 to 11, comprising a screen.

13. The audio reader device (10) according to any one of claims 1 to 12, comprising a memory for storing captured images and / or storing text data generated by the optical character software and / or storing one or more audio data generated by the text-to-speech software.

14. An audio reader device (10) according to claim 1, comprising an infrared sensor for determining a distance between the surface and the camera (20), a lens for focusing on the image to be captured, an image sensor for converting the captured image into digital pixels, and one or more audio output units for vocalizing said one or more audio data.

15. The audio reader device (10) according to any one of claims 1 to 13, wherein said audio reader device (10) is a smart mobile device.

16. A system (100) comprising one or more audio reader devices (10) according to any one of claims 1 to 15 and one or more central units (50), wherein the one or more central units (50) in said system (100) comprise:- one or more data transfer mechanisms for exchanging one or more digital image data and / or one or more text data and / or one or more digital audio data with said one or more audio reader devices (10), and- one or more digital libraries provided with one or more memory members for storing one or more digital image data and / or one or more text data and / or one or more digital audio data. A system (100) according to claim 16, wherein said one or more data transfer mechanisms are adapted to perform said data exchange wirelessly.

Citation Information

Patent Citations

  • Portable character recognition voice reader and method for reading characters

    CN102509479A

  • Information processing apparatus, information processing method and software product

    US20050052558A1

  • Text capture and presentation device

    US20080260210A1

  • Automated recognition of text utilizing multiple images

    US9292739B1