CN211264329U - Text recognition apparatus - Google Patents

Abstract

The utility model provides a text recognition equipment, include: an apparatus body; the camera module is arranged on the equipment body and used for shooting target content; the optical polaroid is arranged in front of the camera module and used for reducing the transmission intensity of glare in incident light; and the display module is arranged on the equipment body and used for outputting and displaying the identification result and/or the image information of the target content. The utility model discloses a text recognition equipment is provided with the optics vibration-damping sheet in the place ahead of camera module, can reduce the intensity of glare in the light that gets into the camera module, consequently can improve text recognition equipment's recognition effect, and then improves the recognition result of output and/or image information's definition, moreover the utility model discloses newly-increased display module can be more directly perceived, clearly to the more abundant information of user transmission form, from this, the utility model discloses can improve text recognition equipment's mutual experience by a wide margin.

Description

Text recognition apparatus

Technical Field

The utility model relates to a text recognition technology field especially relates to a text recognition equipment.

Background

At present, with the interaction and rapid expansion of internet information such as media, news and the like, people can rapidly know the current news information through the internet. However, because people rely on paper culture for a long time, media such as traditional newspapers and magazines are still an essential important way for acquiring external information in life.

When people read traditional paper newspapers and magazines, only pictures and uneditable character information are obtained by reading through a paper channel due to the defects of paper. With the rapid development of text processing technology, it is possible to convert non-editable character information into editable character information by converting the information into image information and then further processing the information, and further possible to view, edit, store, and broadcast by voice, for example, but not limited to OCR technology.

Based on the prior art, a special text recognition device product is provided, but when a camera is adopted to shoot target content, natural light can be directly reflected to the camera or reflected to the camera through a medium, so that the acquired character information on the medium is inaccurate, and the recognition result is influenced; moreover, the existing equipment has single function, does not have the output and display functions of contents such as images and the like, and has poor user experience.

SUMMERY OF THE UTILITY MODEL

The utility model aims at providing a text recognition equipment has solved the defect as above current special text recognition product.

The utility model adopts the technical scheme as follows:

a text recognition apparatus comprising:

an apparatus body;

the camera module is arranged on the equipment body and used for shooting target content;

the optical polaroid is arranged in front of the camera module and used for reducing the transmission intensity of glare in incident light;

and the display module is arranged on the equipment body and used for outputting and displaying the identification result and/or the image information of the target content.

Optionally, the camera module comprises a photosensitive camera.

Optionally, the optical polarizer comprises a polarizing film embedded in a double-sided optical glass structure or a polarizing film attached to the surface of the camera module.

Optionally, the text recognition device further comprises a reflective coating and/or an anti-glare film disposed on the surface of the optical polarizer.

Optionally, the text recognition device further includes brackets located on both sides of the optical polarizer and having adjustable opening and closing angles, and the brackets are connected to the optical polarizer and used for adjusting the glare intensity transmitted through the optical polarizer and supporting the device body.

Optionally, the text recognition device further comprises a motor linkage device arranged in the device body and used for adjusting the opening and closing angle of the support.

Optionally, the text recognition device further comprises a bracket adjusting knob located on a side wall of the device body, and the bracket adjusting knob is used for triggering the motor linkage device and changing the movement speed of the bracket.

Optionally, the support is in contact with the optical polarizer, or a preset gap is provided between the support and the optical polarizer.

Optionally, the display module comprises an OLED display screen.

Optionally, the text recognition device further comprises a processor and a communication module,

the processor is arranged in the equipment body and connected with the camera module, the display module and the communication module;

and the communication module establishes wireless communication with a remote server and is used for transmitting the identification result and/or the image information of the target content.

The utility model provides a text recognition equipment is provided with the optics vibration-damping sheet in the place ahead of camera module, can reduce the intensity of glare in the light that gets into the camera module, consequently can improve text recognition equipment's recognition effect, and then improves the definition of the display content of output, moreover the utility model discloses newly-increased display module can be more directly perceived, the more abundant information of form is passed out to the user visually, for example image information, from this, the utility model discloses can improve text recognition equipment's mutual experience by a wide margin.

Drawings

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described with reference to the accompanying drawings, in which:

fig. 1 is a front view of an embodiment of a text recognition apparatus provided by the present invention;

fig. 2 is a rear view of an embodiment of a text recognition apparatus provided by the present invention;

fig. 3 is a schematic diagram of an embodiment of a relative position relationship between an optical polarizer and an apparatus body of the text recognition apparatus provided by the present invention;

fig. 4 is an electrical connection block diagram of an embodiment of the text recognition apparatus provided by the present invention.

Description of reference numerals:

01 device body 02 processor 03 charging interface

04 remote server 05 communication module 06 display module

07 shell 08 polarization support adjusting knob 09 sound outlet hole

10 volume key 11 switch key 12 confirmation key

13 support 14 optical polaroid 15 camera module

16 battery backplate 17 earphone interface

Detailed Description

Reference will now be made in detail to the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present invention, and should not be construed as limiting the present invention.

The current special text recognition equipment adopts a camera to shoot target content, natural light directly enters the camera, and the incident natural light has reflection and glare, so that the recognition effect of the text recognition equipment on the target content is directly influenced, the text recognition capability is poor, and only text information can be recognized, so that the text recognition equipment does not have an output function such as image information, and the user experience is poor.

The utility model discloses to prior art's not enough, fig. 1 and fig. 2 show respectively the utility model provides a main view and the back view of text recognition equipment's embodiment mainly include: the device comprises an equipment body 01, a camera module 15, an optical polaroid 14 and a display module 06, wherein the camera module 15 is arranged on the equipment body 01 and is used for shooting target contents; the optical polarizer 14 is arranged in front of the camera module 15 and is used for reducing the transmission intensity of glare in incident light; the display module 06 is disposed on the device body 01, and is configured to output and display the identification result of the target content and/or the image information.

The target content shot by the camera module 15 includes, but is not limited to, news information corresponding to news publications and magazines. The optical polaroid 14 is arranged in front of the camera module 15, so that the situation of reflection and glare exists on oily paper, when the camera module 15 shoots target content, natural light from the target content enters the camera module 15 before the natural light enters the camera module 15, the optical polaroid 14 filters glare components in the natural light, the intensity of the glare in the light entering the camera module 15 can be reduced, the effects of eliminating the optical reflection and the glare can be achieved, the image information captured by the camera module 15 can be kept pure, clean image information is provided for text recognition, the accuracy of text recognition is improved, and the recognition effect of text recognition equipment on the target content can be improved. The size of the optical polarizer 14 is the same as that of the camera module 15, or slightly smaller than that of the camera module 15.

The utility model discloses in, camera module 15 adopts rearmounted camera, specifically, camera module 15 can be for the sensitization camera, can realize automatic sensitization to the target content of different materials, for example can be to the automatic sensitization of the periodical of different papers, can automatically regulated adaptation image colour, consequently can realize auto focus and auto-exposure to light level adjustment exposure time according to surrounding environment, carry out text identification's accuracy in order to improve image information. Preferably, the infrared common dual-purpose camera of the camera can adopt different modes according to different light sources, adopt an infrared shooting mode at night or in a dark environment, and adopt a common shooting mode in a normal environment.

Further, the text recognition device further comprises a rotating mechanism connected with the camera module 15, and the rotating mechanism is used for rotating the shooting angle of the camera module 15, so that the automatic correction of the shooting angle of the target content can be realized. Specifically, the rotation mechanism may employ, but is not limited to, an existing movable lens technology such as a micro motor. Camera module 15 is used for shooing the target content, preferably, camera module 15 adopts the sensitization camera, can realize automatic sensitization to the target content of different materials, for example can be to the automatic sensitization of the periodical of different papers, and when treater 02 converts image information into literal information, can discern the light intensity with the sensitization module that the sensitization camera is supporting automatically to the parameter that can further automatic adjustment gathered the image makes and provides clear pending picture for follow-up discernment processing. The reference is made to the prior art for a photo-sensor and its corresponding photo-sensor module and processing procedure.

The optical polarizer 14 may be a polarizing film embedded in a double-sided optical glass structure or a polarizing film attached to the surface of the camera module 15. Preferably, the text recognition device further comprises a reflective coating and/or an anti-glare film disposed on the surface of the optical polarizer 14, so as to further improve the recognition effect of the text recognition device on the target content.

Further, the device body 01 includes a housing 07 and a battery back plate 16, and the text recognition device further includes brackets 13 which are obliquely located on both sides of the optical polarizer 14 and have adjustable opening and closing angles, and are used for adjusting the intensity of glare transmitted through the optical polarizer 14 and supporting the device body 01. Specifically, the bracket 13 and the optical polarizer 14 are in direct contact or indirect contact, or certainly not in contact (for example, a gap with a preset distance is configured between the bracket 13 and the optical polarizer 14), when the bracket 13 is operated, the bracket 13 can contact the optical polarizer 14 by means of the opening and closing angle and the opening and closing force of the bracket 13 and generate a pressing effect of squeezing or relaxing the optical polarizer 14, so that the optical polarizer 14 is deformed or changed in angle, the focal length of the optical polarizer 14 is adjusted, and the polarization direction of the polarized light is rotated by a specific angle, so that reflected light and glare can be filtered out to different degrees. The bracket 13 has a narrow width on the side close to the optical polarizer 14 and a wide width on the side far from the optical polarizer 14 to support the device body 01, so that a user can conveniently view the recognition result and the image information displayed on the display module 06.

The text recognition device further comprises a motor linkage device (not shown in the figure) arranged in the device body 01, the motor linkage device comprises a connecting rod, a gear and a motor, the motor of the motor linkage device is used as a power source, the power output end of the motor linkage device is connected with the support 13, the rotation of the motor drives the gear, the connecting rod and other components to further drive and change the opening and closing angle of the support 13, and therefore the opening and closing angle of the support 13 can be adjusted. As one example and not by way of limitation, the motor in the motor linkage may be a small stepper motor. The text recognition device further comprises a support adjusting knob 08 positioned on the side wall of the device body 01, the motor can be triggered to start through the support adjusting knob 08, the rotating speed of the motor can be adjusted based on the sliding rheostat principle, the moving speed of the support 13 is further changed, and the triggering of the motor starting and the speed regulation control process are all conventional technologies. In addition, in some embodiments, the opening and closing angle of the two brackets is 20 ° to 160 °, and the specific opening and closing angle can be adjusted according to the material of the target content and the user's requirement, which is not limited by the present invention. Of course, in some embodiments, the number of the brackets 13 may not be limited, for example, three or four brackets may be provided, as long as the opening and closing angle between the brackets is adjustable, and the present invention is not limited thereto. To based on different target content, output different angles of opening and shutting and the control command that corresponds, this has a large amount of relevant products and technique to supply to refer to, the utility model discloses a purpose still stands in the design of hardware improvement, provides better recognition effect for current text recognition product, and to how utilizing the corresponding instruction of target content output, then is not in the utility model discloses a restricted range. Fig. 3 shows a schematic view of the relative position of the holder 13 and the apparatus body 01. The support 13 and the apparatus body 01 are both inclined to the horizontal plane, and the inclination can be adjusted by the interlocking device.

It should be noted that the support 13 is described again, and it can be seen from the above description that the support 13 of the present invention can at least serve two technical functions, one of which is to support the device body 01 to make the display module 06 at an angle suitable for the user to watch; the other is to apply a force to the optical polarizing plate 14 to change the shape, angle, etc. thereof, thereby obtaining an appropriate antiglare effect for different lighting environments.

As shown in fig. 1, the display module 06 is located at a central location of the text recognition device. As an example, the display module 06 is an OLED display screen, which has good flexibility, and thus can be folded, and has a small thickness and a large viewing angle, and can protect eyes against blue light, and has low power consumption, and thus is more energy-saving, and has a high resolution, and a high definition, and can greatly improve the interactive experience of the text recognition device, and is convenient for a user to carry. As another example, the display module 06 is an LCD display screen, specifically an embedded LCD display screen, and both the OLED display screen and the LCD display screen can be clicked to select the recognition result and the image information.

To sum up, the key feature of the text recognition equipment that this embodiment provided is, is provided with the optics polaroid in the place ahead of camera module, when shooing target content like this, can reduce the intensity of glare in the light that gets into the camera module to relative current text recognition product, can improve text recognition equipment's recognition effect, and then improve the definition of the display content of output, moreover the utility model discloses newly-increased display module can be more directly perceived, clearly pass out the more abundant information of form to the user, from this, the utility model discloses can improve text recognition equipment's interactive experience by a wide margin.

It should be noted that, the processing procedure to the image that the camera module gathered that wherein relates to all has prior art to supply the reference, the utility model aims at providing the improvement means of hardware level to overcome current product and not handle the defect to reflection of light and glare, and provide the hardware foundation for expanding the interactive function that text recognition equipment is more intelligent.

As shown in fig. 4, further, the text recognition device further includes a processor 02 and a communication module 05, where the processor 02 is embedded in the device body 01 and connected to the camera module 15, the display module 06, and the communication module 05; the communication module 05 establishes wireless communication with the remote server 04 for transmitting the recognition result and/or image information of the target content, such as but not limited to a video related to the recognition result.

Specifically, the camera module 15 transmits image information corresponding to the target content to the processor 02 through the MIPI interface, and the processor 02 captures an image signal in the image information, and performs graying, binarization, denoising, correction, operation recognition and other processing on the image signal to convert the image information into text information (the specific processing method itself has a large number of mature schemes in the field for reference), thereby completing the recognition of the image information. By way of example and not limitation, the processor 02 employs a CPU (e.g., a high-pass 450 platform CPU) or a GPU (e.g., a sailing FPGA accelerator). Further, treater 02 still is connected with aforementioned motor aggregate unit, and specific control principle is not the utility model discloses the focus is merely exemplified, and treater 10 can realize the regulation of support 13 angle of opening and shutting according to different target content control motor aggregate unit. And under the condition of closing the equipment or powering off, the processor 10 can control the motor linkage device to enable the support 13 to automatically retract to the position attached to the equipment body 01, so that the processor is convenient for a user to carry.

Then, the communication module 05 is a WLAN power amplifier chip (for example, RPM6743), after the communication module and the antenna are calibrated and configured with RF, network connection can be performed under WiFi conditions to realize uplink and downlink data transmission, the remote server 04 receives the identification result of the processor 02 through the communication module 05, performs network data retrieval based on keywords in the text information, retrieves a video link to be selected corresponding to the text information, and then transmits the retrieved video link information to be selected to the processor 02 through the communication module 05; the remote server 04 can combine the existing search technology (for example hundred degree search engine, google search engine, 360 search engines etc.) to search, the utility model discloses combine the purpose of this technique, make the utility model provides a text recognition equipment is more intelligent at the aspect of use. As an example and not by way of limitation, the remote server 04 is a cloud server, and can access a cloud online video in real time and output link information of a video to be selected in real time. Preferably, the cloud server can be associated with news publications, magazine agencies and video websites to establish a specific video database, the specific video database is specially used for storing a video link library corresponding to related videos of contents published on paper carriers such as specific news publications and magazines, so that image information identification and video link search can be performed more quickly and conveniently, readers can refer to image information while acquiring text information, the paper publications are rich in science and technology, the paper publications such as news publications and magazines are promoted to have advanced science and technology paper culture, and the interaction experience of users is greatly improved. The video search, push, etc. realized by the server are only the utility model discloses an application extends the example, and the key point of not injecing to above-mentioned process realized by the server also has multiple prior art to supply the reference, and the no longer redundance here is repeated.

Then, the display module 06 is connected to the processor 02 through the MIPI interface, and is configured to display the aforementioned image information, such as but not limited to the information of the video link to be selected, and play the image information corresponding to the video link selected by the user in the video link to be selected for the user to watch, and play the audio information in the image information through an earphone inserted into the earphone interface 17 or a speaker (not shown in the figure) provided in the device body.

Further, as shown in fig. 1 and fig. 2, the text recognition device further includes a housing 07 and a battery backplate 16, and the processor 02 is located in a cavity formed by the housing 07 and the battery backplate 16, so that a large number of related existing products can be used for reference, which is not limited by the present invention.

Further, the text recognition device further comprises a power supply module (not shown) located in the cavity and corresponding to the position of the battery backboard 16. The power supply module includes: a lithium battery, a PMIC (Power management IC), a charging protection unit, and a charging interface 03. The power supply module converts the electric energy stored in the lithium battery into the power supply voltage of each module of the text recognition device through the PMIC through the lithium battery, and the lithium battery can be charged through the charging protection unit through the charging interface 03. Preferably, the charging protection unit is an overvoltage protection circuit.

Optionally, the text recognition device further comprises a key module located on the housing 07. Specifically, the key module includes a volume key 10, a switch key 11, and a confirmation key 12. As shown in fig. 1 and 2, the volume keys 10 and the switch keys 11 are disposed on the right side of the text recognition device from top to bottom, the number of the volume keys 10 is two, namely, a volume up key and a volume down key, when a user watches image information corresponding to a video link, the volume can be adjusted through the volume keys 10, and the switch keys 11 are mainly used for turning on and off the display module 06 when the user watches the video link, and the screen is turned on and off when the user presses the display module for a short time. The confirmation key 12 is located at a central position below the text recognition device, as shown in fig. 1, the confirmation key 12 is located below the display module 06, and is mainly used for selecting a command to be executed, for example, a camera module can be used for taking a picture, and a user can realize a video pause function in the process of watching image information corresponding to a video link.

The structure, features and effects of the present invention have been described in detail in the above embodiments shown in the drawings, but the above embodiments are only preferred embodiments of the present invention, and it should be noted that, the technical features related to the above embodiments and their preferred modes can be reasonably combined and assembled into various equivalent schemes by those skilled in the art without departing from or changing the design idea and technical effects of the present invention; therefore, the present invention is not limited to the embodiments shown in the drawings, and all changes made according to the idea of the present invention or equivalent embodiments modified to equivalent changes are within the scope of the present invention without departing from the spirit of the present invention.

Claims (10)

1. A text recognition apparatus, comprising:

an apparatus body;

the camera module is arranged on the equipment body and used for shooting target content;

the optical polaroid is arranged in front of the camera module and used for reducing the transmission intensity of glare in incident light;

and the display module is arranged on the equipment body and used for outputting and displaying the identification result and/or the image information of the target content.

2. The text recognition device of claim 1, wherein the camera module comprises a photographic camera.

3. The text recognition device of claim 1, wherein the optical polarizer comprises a polarizing film embedded in a double-sided optical glass structure or a polarizing film attached to a surface of the camera module.

4. The document recognition apparatus according to claim 1, further comprising a light reflecting coating and/or an anti-glare film provided on a surface of the optical polarizing plate.

5. The text recognition device of claim 1, further comprising brackets positioned on both sides of the optical polarizer and having adjustable opening and closing angles, for adjusting the intensity of glare transmitted through the optical polarizer and supporting the device body.

6. The text recognition device of claim 5, further comprising a motor linkage built into the device body for adjusting the opening and closing angle of the support.

7. The text recognition device of claim 6, further comprising a stand adjustment knob located on a side wall of the device body for activating the motor linkage and changing a speed of movement of the stand.

8. The text recognition device of claim 5, wherein the bracket is in contact with the optical polarizer or a preset gap is provided between the bracket and the optical polarizer.

9. The text recognition device of claim 1, wherein the display module comprises an OLED display screen.

10. The text recognition device of any one of claims 1-9, further comprising a processor and a communication module,

the processor is arranged in the equipment body and connected with the camera module, the display module and the communication module;

and the communication module establishes wireless communication with a remote server and is used for transmitting the identification result and/or the image information of the target content.

Images