CN112785883A

CN112785883A - Point reading position marking method and system based on image recognition and intelligent learning table

Info

Publication number: CN112785883A
Application number: CN202110110358.XA
Authority: CN
Inventors: 吕瑞
Original assignee: Individual
Current assignee: Individual
Priority date: 2021-01-27
Filing date: 2021-01-27
Publication date: 2021-05-11

Abstract

The invention discloses a point reading position marking method based on image recognition, which comprises the following steps of: projecting a mark image to a reading page through a projection device; and acquiring the image of the reading page and the marked image by an image acquisition device. The invention also provides a point-reading position marking system based on image recognition and an intelligent learning table, which are used for realizing the point-reading position marking method based on image recognition. By adopting the technical scheme, not only can information such as characters, letters, patterns and the like on a reading page be obtained, but also the positions of the marked images are collected, so that the subsequent operations of pronouncing or explaining, searching and the like after the positions guided by the marked images are identified through an image identification technology are facilitated; since the projection of the marker image is performed by the projection device, no trace is formed on the reading page, and any reading page can be read by pointing.

Description

Point reading position marking method and system based on image recognition and intelligent learning table

Technical Field

The invention relates to a point-reading position marking method and system based on image recognition and an intelligent learning table, and belongs to the technical field of auxiliary learning methods and systems.

Background

Although some books are read at present, the student can read the corresponding point area through the point pen, but to ordinary paper books, the student meets unknown word, idiom that does not understand, word that can not read, mathematics subject that can not calculate etc. when studying, can't look up fast, can only seek help mr or head of a family usually. In the prior art, there is also an Optical Character Recognition (Optical Character Recognition) method for performing image Recognition on a regular book by an image Recognition method, and then positioning a text to be recognized by a positioning technique. While the text to be read or explained is usually pointed by a finger or other pointing object, the text is selected by the position of the finger or other pointing object. For example, chinese patent document CN109445588A discloses a click judgment method for a click-to-read pointing device based on an image recognition tracking technology, in which a horizontal tracking and a height tracking are performed on the click-to-read pointing device by the image recognition technology, a coordinate of the click-to-read pointing device on a page coordinate system is tracked, and when one or more points at the front end of the click-to-read pointing device enter a coordinate range of a trigger region, it is judged that the click-to-read pointing device enters the trigger region. However, the error rate of positioning in this way is large, and the text cannot be accurately positioned in use. Chinese patent document CN110633027A also discloses a method, a system, a computer device, and a storage medium for implementing point reading, in which the method first obtains images of books, and then locates the finger by means of infrared recognition, so as to avoid the inaccuracy of finger position recognition through images, but the accuracy of the infrared location is not high due to the influence of temperature.

Disclosure of Invention

Therefore, the invention aims to provide a click-to-read position marking method and system based on image recognition and an intelligent learning table, which can realize more accurate positioning.

In order to achieve the above object, the present invention provides a click-to-read position marking method based on image recognition, which comprises the following steps:

projecting a mark image to a reading page through a projection device;

and acquiring the image of the reading page and the marked image by an image acquisition device.

The projection device can adjust the mark image projected to the reading page.

The projection device comprises a projector, a slide device or a laser projection device.

Further comprising the steps of:

identifying a track defined by the position indicator;

and projecting the identified track by a projection device to form a mark image.

And collecting an operation image of the position indicator and performing image analysis so as to identify the track.

The position indicator includes a spatial location tracking module by which the trajectory formed when operating the position indicator is captured.

The position indicator includes a pressure trigger module.

In the process of marking out the track by the position indicator, the projection device projects an image corresponding to the marked out track onto the reading page in real time.

The reading page is a page displayed in a projection mode.

The invention also provides a point reading position marking system based on image recognition, which is used for realizing the point reading position marking method based on image recognition and comprises a projection device and an image acquisition device.

The invention also provides an intelligent learning table, which comprises the point-reading position marking system based on image recognition.

By adopting the technical scheme, the click-to-read position marking method, the system method and the learning table based on image recognition firstly project the marking image to the reading page through the projection device, the marking image is displayed on the reading page of the reading object, and the position marking can be visually carried out on the area needing click-to-read, so that when the image acquisition device is used for carrying out image acquisition on the reading page, not only can information such as characters, letters and patterns on the reading page be obtained, but also the position of the marking image is acquired, and therefore, other operations such as pronunciation or explanation, searching and the like are conveniently carried out after the position guided by the marking image is recognized through the image recognition technology; because the projection of the marking image is carried out by the projection device, no trace is formed on the reading page, and any reading page can be read by point; and the defect of high identification error rate in the prior art can not occur.

Drawings

Fig. 1 is a flow chart of a click-to-read position marking method based on image recognition according to the present invention.

Fig. 2 is a flowchart of a click-to-read position marking method based on image recognition according to an embodiment of the present invention.

Fig. 3 is a flow chart of a click-to-read position marking method based on image recognition according to another embodiment of the present invention.

Fig. 4 is a schematic diagram of an operating state of a projection apparatus and an image capturing apparatus according to an embodiment of the present invention.

Fig. 5 is another schematic view of the projection apparatus and the image capturing apparatus.

Fig. 6 is a schematic diagram of an image acquired by the image acquisition device.

Fig. 7 is a block diagram of a click-to-read position marking system based on image recognition according to an embodiment of the present invention.

Detailed Description

The invention is described in further detail below with reference to the figures and the detailed description.

The invention relates to a point-reading position marking method based on image recognition, which comprises the following steps as shown in figure 1: firstly, a marking image is projected to a reading page through a projection device, the marking image is displayed on the reading page, and the position of an area needing to be read can be marked visually; and then the image acquisition device acquires the image of the reading page, so that not only can information such as characters, letters, patterns and the like on the reading page be obtained, but also the position of the marked image is acquired, and the position guided by the marked image can be conveniently identified by the image identification technology subsequently. Therefore, it should be emphasized that the "click-to-read" in the present invention does not merely mean to read the letters, letters or numbers of the selected position by pronunciation, but may also perform other operations such as searching and explaining on the recognized letters, numbers or patterns.

The shape of the mark image projected on the reading page can be selected according to actual needs, for example, the shape of a square, circular or oval hollow frame or a filled frame can be framed in the reading page, so that characters, letters, patterns and the like of the reading area can be framed in the reading page, the size of the shape can be further adjusted to adapt to different sizes of the reading area, the selected shape can be set to be a point shape, a straight line shape or a wavy line shape, the color of the mark image can be selected according to actual conditions so as to be obviously different from the color on the reading page, and subsequent identification is more accurate. The projection device can be a slide device and comprises a projection lamp and a projection film, emergent light of the projection lamp penetrates through the projection film and then is projected onto a reading page, and patterns on the projection film are displayed on the reading page of a reading object to form the marking images. The projection film can be replaced to replace mark images of different shapes, sizes, colors. Of course, the projector may be a projector connected to the input device, so that the marker image information to be projected by the projector can be more flexibly and freely input to the projector. In addition, the projection device can also be a laser projection device such as a laser pen, the laser pen can emit a point-shaped, linear or frame-shaped laser pattern, and students can hold the laser pen to irradiate the reading page so as to form a bright spot as a marking image.

In an embodiment of the present invention, as shown in fig. 2, a position indicator is provided, a track is defined by the position indicator, the track may be a track of a point, a line segment or a frame, and after the central processing unit recognizes that the track is defined by the position indicator, information of the track is sent to the projector for projection, so that the projector can project a corresponding track image onto the reading page to form the mark image.

The position indicator comprises a handheld part, an end part and a space positioning and tracking module, wherein the space positioning and tracking module is connected with the central processing unit and is used for acquiring the coordinate of the end part in a real coordinate system in real time and transmitting the acquired coordinate data to the central processing unit. The central processing unit is used for receiving the coordinate data of the end part in the real coordinate system sent by the space positioning and tracking module so as to form track information, and sending the track information to the projector for projection.

As shown in fig. 7, a pressure trigger module is further disposed at an end of the position indicator, and when the end of the position indicator is subjected to a pressure, the pressure trigger module is triggered to serve as a starting point for the central processing unit to collect the end coordinate data, and when the pressure applied to the end disappears, the pressure trigger module serves as an end point for the central processing unit to collect the end coordinate data. Therefore, when the student uses the position indicator, the student can hold the position indicator by hand, the selection frame is drawn out through the area needing to be read on the reading page by the end part, and the pressure trigger module is triggered in the process of drawing the selection frame, so that the central processing unit can accurately acquire the track information of the movement of the end part of the position indicator in the process.

Of course, in another embodiment, as shown in fig. 3, besides the trajectory drawn by the position indicator is collected by the spatial positioning and tracking module, the trajectory may be identified by collecting an operation image of the position indicator and performing image analysis, that is, when the device is used, a student draws a frame, a point or a line segment on a reading page for an area needing to be clicked and read through the end of the position indicator, collects the process of drawing the frame, the point or the line segment in real time through the image collection device, identifies the trajectory of the end through the image identification technology, and projects an image corresponding to the trajectory onto the reading page through the projection device to form a mark image.

The image acquisition device and the projection device can be arranged above the reading page and close to each other, the camera 1 of the image acquisition device and the projection lens 2 of the projection device are aligned with the reading page 3, and as shown in fig. 4-6, an oval frame is drawn on the reading page 3 by using the position indicator to frame a Chinese character on the reading page. The coordinate data of the tip of the position indicator in the real coordinate system does not use its elevation coordinate but only its coordinate in the x, y plane, considering that different readings have different thicknesses (the dotted lines representing the x-axis and the y-axis in fig. 6 do not exist in the acquired image, and only the x, y coordinate system is illustrated). The image acquired by the image acquisition device corresponds to a real coordinate system, and the coordinate data of the end part of the position indicator in the real coordinate system can correspond to the image acquired by the image acquisition device. Therefore, the central processor can obtain the track of the oval frame, project the mark image 4 corresponding to the oval frame through the projection device, and then the image acquisition device can shoot the reading page 3 and the mark image 4 together.

The method for clicking and reading the position mark based on the image recognition is not limited to common paper reading materials, but also is suitable for a display screen based on a photoelectric principle or a reading page formed by projection through a projector. That is, the student can project the reading page on the desktop or the projection screen using the projector, and the reading page formed by the projection can also use the click-to-read position marking method based on the image recognition of the present invention. Then, the projector projects not only the reading page but also the subsequent marker image, and the final projection image is acquired by the image acquisition device.

In the process of drawing the track by the position indicator, the projection device can project the image corresponding to the drawn track onto the reading page in real time, so that students can see the projection of the drawn track in real time in the process of drawing the track, and therefore, even if the position of the projected track has errors, the students can properly adjust the position of the position indicator to finally form the track on the position needing to be drawn.

In another embodiment of the present invention, an image of the reading page may be obtained and displayed, for example, image data of the reading page is collected by an image collecting device, and the image data of the reading page is displayed in real time by a display, a student may observe the image displayed in the display, and mark a track on the image by operating an input device such as a mouse to select the click-to-read area, and a central processing unit may directly identify the click-to-read area.

The invention also provides a point reading position marking system based on image recognition, which is used for realizing the point reading position marking method based on image recognition. As shown in fig. 7, the image recognition-based click-to-read position marking system includes the central processor, a projection device, an image capture device, and a position indicator, which can realize the positioning function of the end portion of the position indicator, such as a VR handle device.

It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.

Claims

1. A point reading position marking method based on image recognition is characterized by comprising the following steps:

projecting a mark image to a reading page through a projection device;

2. The image recognition-based click-to-read position marking method according to claim 1, wherein the projection device comprises a projector, a slide device or a laser projection device.

3. The image recognition-based click-to-read position marking method according to claim 1, further comprising the steps of:

identifying a track defined by the position indicator;

4. The image recognition-based click-to-read position marking method according to claim 3, wherein an operation image of the position indicator is collected and subjected to image analysis so as to recognize the trajectory.

5. The image recognition-based click-to-read position marking method according to claim 3, wherein the position indicator comprises a spatial location tracking module by which the trajectory formed when operating the position indicator is captured.

6. The image recognition-based click-to-read position marking method according to claim 5, wherein the position indicator comprises a pressure trigger module.

7. The image recognition-based click-to-read position marking method according to any one of claims 3 to 6, wherein in the process of drawing the track by the position indicator, the projection device projects an image corresponding to the drawn track onto the reading page in real time.

8. The image-recognition-based click-to-read position marking method according to any one of claims 1 to 6, wherein the read page is a projection display page.

9. A point reading position marking system based on image recognition is characterized by comprising a projection device and an image acquisition device, wherein the point reading position marking system is used for realizing the point reading position marking method based on image recognition according to any one of claims 1 to 8.

10. The utility model provides an intelligence study table which characterized in that: comprising a click-to-read position marking system based on image recognition according to claim 9.