CN111311624B - Book detection method and device of point reading equipment - Google Patents
Book detection method and device of point reading equipment Download PDFInfo
- Publication number
- CN111311624B CN111311624B CN202010203077.4A CN202010203077A CN111311624B CN 111311624 B CN111311624 B CN 111311624B CN 202010203077 A CN202010203077 A CN 202010203077A CN 111311624 B CN111311624 B CN 111311624B
- Authority
- CN
- China
- Prior art keywords
- book
- book page
- detection
- page area
- page
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/174—Segmentation; Edge detection involving the use of two or more images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Facsimile Scanning Arrangements (AREA)
- Image Analysis (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the application discloses a book detection method and device of a point-reading device, an electronic device and a storage medium. According to the technical scheme provided by the embodiment of the application, a plurality of target images are continuously acquired within the shooting range of the camera, book page area detection is performed based on the target images, the corresponding book page areas are marked, and when the indication mark is detected to enter or exit from the shielding book page areas, the book page areas are read to serve as book page detection images. By adopting the technical means, the interference existing when the book page detection image is determined can be avoided, and the book page detection image with better quality is provided, so that the original page inquiry and the click-to-read content determination can be conveniently carried out, and the use experience of a user is optimized.
Description
Technical Field
The embodiment of the application relates to the technical field of intelligent learning equipment, in particular to a book detection method and device of point-reading equipment.
Background
Currently, in order to effectively assist students in learning and reduce cost, many electronic devices for learning, such as tablet computers, mobile phones, learning machines and the like, are available on the market, and these devices can solve the problem encountered in the learning process of students to a certain extent. In the process of using the equipment, a common mode is that a user places a book in a shooting range of a camera of the equipment, and through indicating the relevant position on the book, the functions of reading the learning content of the corresponding position, solving questions and the like of the equipment are realized, so that the learning of students is effectively assisted, and the learning effect is optimized.
In the process of using such electronic devices to perform click-to-read learning, it is generally required to extract a corresponding original page according to a book page detection image query database clicked by a user, and determine content indicated by the user according to the original page to perform content click-to-read or solution. However, when determining a book page detection image which is read by a user, a situation that the range of the book page is inaccurately determined and the original page is interfered due to the fact that a book page is blocked by a blocking object such as a finger and a pen, the current reading operation is failed, and the use experience of the user is affected.
Disclosure of Invention
The embodiment of the application provides a book detection method and device of a point-reading device, electronic equipment and a storage medium, and aims to solve the technical problems of page shielding and interference existing in book page detection.
In a first aspect, an embodiment of the present application provides a book detection method of a point-to-read device, including:
continuously acquiring a plurality of target images in the shooting range of the camera, wherein the target images comprise image data of book pages;
detecting a book page area based on the target image, and marking the corresponding book page area;
when the indication mark is detected to enter or exit from the book page area, the book page area is read to serve as a book page detection image, and the indication mark is used for indicating a book page to be read.
Further, after detecting the page area of the book based on the target image and marking the corresponding page area of the book, the method further comprises:
and when the movement of the book page is detected, the detection and marking of the page area of the book are carried out again.
Further, the detecting the book page movement includes:
extracting two continuous target images;
determining two corresponding book page areas according to the book page area detection;
and comparing and judging that the coordinate information of the two book page areas has change, and determining the movement of the book pages.
Further, the detecting the page area of the book based on the target image, marking the corresponding page area of the book, includes:
and detecting the target image based on an edge detection algorithm, identifying a book page area, and marking the book page area.
Further, the detecting the page area of the book based on the target image, marking the corresponding page area of the book, and further includes:
and determining a book page area sample corresponding to each target image according to the book page area detection, and screening out the book page area with the least interference information from the book page area sample based on the interference information detection for marking.
Further, the detecting the indication mark entering or exiting the book page area includes:
and extracting image data corresponding to the page area of the book, and detecting and tracking the indication mark based on a pre-trained indication mark detection and tracking algorithm.
Further, after the reading of the book page area as the book page detection image, the method further includes:
and inquiring a preset original page database based on the book page detection image, and determining corresponding original page data, wherein the original page data is used for determining the content pointed and read by the user indication mark.
In a second aspect, an embodiment of the present application provides a book detecting apparatus of a point-and-read device, including:
the acquisition module is used for continuously acquiring a plurality of target images in the shooting range of the camera, wherein the target images comprise image data of book pages;
the marking module is used for detecting the page areas of the books based on the target image and marking the corresponding page areas of the books;
and the reading module is used for reading the book page area to serve as a book page detection image when the indication mark is detected to enter or exit from the book page area, and the indication mark is used for indicating the book page to be read.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory and one or more processors;
the memory is used for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the book detection method of the point-and-read device as described in the first aspect.
In a fourth aspect, an embodiment of the present application provides a storage medium containing computer executable instructions for performing the book detection method of the point-and-read device according to the first aspect when executed by a computer processor.
According to the embodiment of the application, a plurality of target images are continuously acquired within the shooting range of the camera, book page area detection is carried out based on the target images, the corresponding book page areas are marked, and when the indication mark is detected to enter or exit from the shielding book page areas, the book page areas are read to serve as book page detection images. By adopting the technical means, the interference existing during the determination of the book page detection image can be avoided, and the book page detection image with better quality is provided, so that the inquiry of the original page data and the determination of the click-to-read content can be conveniently carried out, and the use experience of a user can be optimized.
Drawings
Fig. 1 is a flowchart of a book detection method of a point-and-read device according to an embodiment of the present application;
FIG. 2 is a schematic view of a learning plate according to a first embodiment of the present application;
FIG. 3 is a schematic diagram of a finger-touch book page according to a first embodiment of the application;
FIG. 4 is a schematic view of a book page area shielding in accordance with a first embodiment of the application;
FIG. 5 is a schematic diagram of a book page movement detection process according to a first embodiment of the application;
fig. 6 is a schematic structural diagram of a book detecting device of a point-reading device according to a second embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the following detailed description of specific embodiments of the present application is given with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the matters related to the present application are shown in the accompanying drawings. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently, or at the same time. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The book detection method of the point-reading device aims at marking the book page area in advance before the user starts to point-read by using the point-reading device, so that the user can conveniently use the book page area as a book page detection image when the user points-reads, so as to inquire an original page database to determine corresponding original page data and determine the point-read content by combining the coordinate of the point-reading of the user. Because the book page area marked in advance before the point reading generally has no interference information, and when the user points the book page area, indication marks such as fingers or pens can shield the book page area, when the user directly points the book page area, the shot target image determines that the book page area has interference and errors, the determination of point reading content is affected, the point reading failure is further caused, and the use experience of the user is affected. Based on the above, the book detection method of the point-reading device provided by the embodiment of the application is used for solving the technical problems of errors and interference of the book page detection image determined by the prior point-reading device during point-reading.
Embodiment one:
fig. 1 is a flowchart of a book detection method of a point-reading device according to a first embodiment of the present application, where the book detection method of the point-reading device provided in the present embodiment may be executed by the book detection device of the point-reading device, and the book detection device of the point-reading device may be implemented by software and/or hardware, and the book detection device of the point-reading device may be configured by two or more physical entities or may be configured by one physical entity. In general, the book detection device of the point-reading device may be a tablet computer, a point-reading device, a learning device, a mobile phone, and other intelligent devices.
The book detecting apparatus of the point reading apparatus will be described below as an example of a main body of a book detecting method of executing the point reading apparatus. Referring to fig. 1, the book detection method of the point-and-read device specifically includes:
s110, continuously acquiring a plurality of target images in the shooting range of the camera, wherein the target images comprise image data of book pages.
When a user uses the book detection device to conduct reading learning, a reading learning application program on the book detection device is opened, and a camera of the device is called by the reading learning application program to conduct book page shooting in real time. Referring to fig. 2, taking a learning tablet as an example, when a user performs a click-to-read learning, a book is placed in a shooting range of a front camera or an external camera module of the learning tablet. The learning flat board is vertically placed, the camera arranged at the top of one surface of the screen of the corresponding learning flat board faces to the book placement position, and the target image containing the pages of the book is photographed in real time through the camera and identified. When the user is identified to point the book page by using the indication mark such as a finger or a pen, the learning tablet inquires the corresponding feedback content according to the point-reading content by determining the content of the book page currently indicated by the user as the point-reading content, and performs point-reading analysis operations such as pronunciation playing, problem solving and the like.
In general, the learning tablet will correspondingly set an original page database, where the original page database stores original page data corresponding to each page of the book, the original page data corresponding to each page of the book may include a plurality of corresponding problem data, and feedback contents such as corresponding problem solutions, pronunciation audios and the like exist corresponding to each problem data. When the click-to-read content (namely problem data) indicated by the user is determined, the problem data currently asked by the user can be determined, and the feedback content is correspondingly determined to be fed back to the user, so that the click-to-read learning operation of the learning tablet is realized. Further, in order to determine the click-to-read content of the user, it is necessary to determine the book page currently indicated by the user, and define it as a book page detection image. And further according to the coordinates on the book page indicated by the user, the corresponding problem data can be inquired and obtained. Because the condition that fingers shield the page area of the book exists in the target image shot by the user during the click-reading, interference caused by shielding easily influences the inquiry of the original page data, the embodiment of the application can mark the page area of the book in advance before the user performs the click-reading so as to be used for inquiring the original page data later.
Specifically, before the user starts to perform the click-to-read learning, that is, when the user has not used the indication identifier (such as a finger, a pen, etc.) to instruct the book page to perform the click-to-read, the learning tablet invokes the camera to continuously acquire a plurality of target images in the shooting range of the camera, where the target images need to include image data of the book page. The detection marking and screening of the book page areas are further carried out corresponding to the target images.
S120, detecting the page area of the book based on the target image, and marking the corresponding page area of the book.
Specifically, in the embodiment of the application, the detection of the page area of the book is performed by acquiring a plurality of target images in advance, and the detection is mainly used for taking the plurality of target images as sample images so as to determine the page area of the book with the least interference information from the plurality of sample images.
When the book page area detection is carried out on each target image, a book page area sample corresponding to each target image is determined according to the book page area detection, and the book page area with the least interference information is screened from the book page area sample based on the interference information detection to mark. It can be understood that if only a target image is photographed to perform detection marking on the page area of the book, interference in the detected page area of the book is easily caused by the interference object (such as an object such as a document box or the like shielding the page of the book), which affects the determination of the subsequent click-to-read content. Therefore, in order to pre-extract the high-quality book page area, the embodiment of the application continuously shoots a plurality of target head images, detects the book page area one by one for each target image, takes the detection result of each target image as a book page area sample, and screens the book page area sample to obtain the high-quality book page area. When the book page area sample screening is carried out, the book page area sample with the interferents can be detected through the interferent detection model based on the neural network, and finally the book page area with the least interference information is screened out. It should be noted that, the detection and recognition model of the interferents such as writing cases may be obtained by obtaining a large number of writing case images as training samples and training using a neural network-based detection model to finally obtain a writing case detection model. It will be appreciated that if a sample of book page area detects a case or other related interfering object, the sample of book page area is screened out for the presence of interfering information.
In one embodiment, an image quality detection model may be further set, so as to detect the image quality of the captured multiple target images. The method generally detects parameter information such as brightness and definition of target images, compares and judges the image quality of each target image based on a preset standard threshold (representing high image quality), and finally selects target images with higher image quality for book page area detection and marking.
When the detection of the page area of the book is performed, the embodiment of the application detects the target image based on an edge detection algorithm, identifies the page area of the book, and marks the page area of the book. The edge detection algorithm can greatly reduce the data volume, and can reject information which is considered to be irrelevant, so that important structural attributes of the image are reserved. It will be appreciated that the target image captured by the camera typically includes not only the image data of the page of the book, but also image data outside the area of the page of the book. In the user's click-to-read scene, there may be interferences such as writing case, pen, user's limbs, etc. outside the book page area, these interferences will be recorded in the target image too, but in order to reject this part of image data, save the image data of the book page area, the embodiment of the application adopts the edge detection algorithm to detect the book page area, so as to detect the edge of the book actually used, intercept the book, remove the interferences of other objects.
In one embodiment, the book page can be placed at a fixed position, and after the learning tablet captures the target image, the coordinate position at the fixed position can be directly corresponded to the clipping of the book page area. There are many ways to detect the page area of the book, and they are not repeated here.
And then, intercepting the detected book page area and correspondingly marking the coordinates of the book page area. After that, in the case that the book page is not moved, the user's click-to-read content is determined by the intercepted area of the book page. And the situation that the book page moves correspondingly indicates that the situation that the page turning of the book page is likely to occur, and the book page area in the target image at the current moment needs to be determined again. The coordinates of the marked book page areas can be used for judging the basis of the movement of the book pages, and whether the book pages move or not can be determined by judging the coordinate information of the corresponding two book page areas.
And S130, reading the book page area as a book page detection image when the indication mark is detected to enter or exit from the book page area, wherein the indication mark is used for indicating the book page to be read.
Further, after the detection mark of the book page area, the current book page area is taken as a book page detection image, and the detection mark of the book page area is not updated again until the movement of the book page is detected. During this time, referring to fig. 3, when the user indicates the content of a certain partial area of the page of the book using a finger (indication mark), the camera captures this target image in real time. The target image is detected and identified, and book page area image data with the finger indicating the book page is determined, wherein the book page area image data is shown in fig. 4. Since the book page area image data determined at this time has the shielding information of "finger", it affects the determination of the original page data, and thus, the book page area image data is not used for directly inquiring the original page data. But the original page data is searched by the page area of the book which is detected and marked before and has no interference information (shielding object such as fingers).
Specifically, by extracting image data corresponding to the page area of the book, the indication mark is detected and tracked based on a pre-trained indication mark detection and tracking algorithm, so that whether the indication mark enters or exits to block the page area of the book is judged. And (3) carrying out real-time detection, identification and tracking on the fingers of the user by establishing a target detection and tracking model. Further, corresponding to a target image shot in real time, preprocessing by an edge detection algorithm to obtain book page area image data, and further inputting the book page area image data into the target detection tracking model, so that the entering and exiting of a finger (namely an indication mark) of a user into and from a shielding book page area can be tracked and identified. Furthermore, in the time period, as the book page does not move, the learning flat plate uses the book page area which is intercepted and marked before as a book page detection image to carry out the basis of the user to read the content query in the current time period.
Further, when the user clicks the content in the current time period, a preset original page database is queried based on the book page detection image, and corresponding original page data is determined, wherein the original page data is used for determining the content clicked by the user indication mark. It can be understood that, because the condition that the marked book page area is not interfered by fingers is intercepted before, the marked book page area is used as the basis for inquiring the original page database, the book page detection image with better quality is provided, the inquiring efficiency and the accuracy of the original page data can be improved, the click-to-read content is determined, and the use experience of a user is optimized. When inquiring, the original page data of the original page database and the book page area are compared one by one, and the original page data with the highest similarity is determined, so that the original page data is considered to be the original page data corresponding to the book page indicated by the user currently. And further according to the original page data, the click-reading content indicated by the user finger can be determined by combining the corresponding coordinate information on the page of the book clicked by the user. The learning assistance of the learning tablet to the user is realized by determining the corresponding click-through content of the original page data and extracting the feedback content bound with the click-through content and showing the feedback content to the user in the forms of pronunciation playing, problem solving and the like.
On the other hand, when the book page movement is detected, the detection and marking of the book page area is performed again. It will be appreciated that movement of the book pages will cause movement of the book page areas, which may be caused by a user turning pages or moving the original book pages. But either way of moving, either because of the book page changes or the book page area coordinates changes, the originally marked book page area fails. The interception and marking of the book page area needs to be updated for the subsequent determination of the click-to-read content when the user indicates the book page.
Specifically, referring to fig. 5, a book page movement detection flowchart of the present application is provided, where the book page movement process includes:
s141, extracting two continuous target images;
s142, determining two corresponding book page areas according to the book page area detection;
s143, comparing and judging that the coordinate information of the two book page areas has change, and determining the movement of the book pages.
When judging whether the book page moves or not, the embodiment of the application judges whether the change exists or not by detecting and marking the book page areas of the two target images and comparing the coordinates of the two book page areas. And intercepting and marking by an edge detection algorithm to obtain a book page area, recording coordinates of the book page area corresponding to the front target image and the rear target image as A1 and A2, and further comparing the difference of the coordinates of A1 and A2 to judge whether the book page moves or not.
In one embodiment, the method further comprises the steps of capturing a target image in real time, detecting and intercepting a book page area from the target image, and comparing coordinates of the book page area with the book page area of the previous intercepting mark so as to judge whether the book page moves. There are many ways to detect the movement of the pages of the book, and they are not described in detail here.
Further, when it is detected that the book page moves, that is, the previously intercepted and marked book page area fails, the captured target image is intercepted and marked again with reference to the steps S110 to S120. And the newly marked book page area is used as a book page detection image in the subsequent stage (before the book page is not moved). And when the user performs a click-to-read operation, the original page database is queried according to the book page detection image and coordinates on the book page area indicated by the user finger, the content clicked by the user is determined, and the corresponding feedback content is further acquired, so that the assistance of the user learning is realized. And by analogy, if the book page moves again after that, further re-intercepting and marking the area of the book page by using the moved target image.
In practical application, a target image is continuously acquired through a camera, and the target image is used for detecting whether a user performs a click-to-read operation or not on one hand and is used for intercepting a page area of a marked book on the other hand. It can be understood that the book page area is kept unchanged corresponding to the stage before one book page movement, and all the point-reading operations on the book page can be performed to determine the point-reading content of the user based on the stage of intercepting the marked book page area. After that, each time the book page is moved, the book page area is firstly re-intercepted and marked based on the target image, and the point-read content of the user is determined by using the re-intercepted and marked book page area for the point-read operation of the subsequent user. And each time the interception mark of the page area of the book is obtained continuously, a plurality of target images are obtained, and the interception mark is carried out by screening the image data of the page area of the book with the least interference information from the target images, so that the image data is used as a page detection image of the book at the stage.
And when the indication mark is detected to enter or exit from the shielding book page area, reading the book page area as a book page detection image. By adopting the technical means, the interference existing when the book page detection image is determined can be avoided, and the book page detection image with better quality is provided, so that the original page inquiry and the click-to-read content determination can be conveniently carried out, and the use experience of a user is optimized.
Embodiment two:
on the basis of the above embodiment, fig. 6 is a schematic structural diagram of a book detecting device of a point-reading device according to a second embodiment of the present application. Referring to fig. 6, the book detection device of the point-to-read device provided in this embodiment specifically includes: an acquisition module 21, a marking module 22 and a reading module 23.
The acquiring module 21 is configured to continuously acquire a plurality of target images within a shooting range of the camera, where the target images include image data of a book page;
the marking module 22 is configured to detect a book page area based on the target image, and mark a corresponding book page area;
the reading module 23 is configured to read the book page area as a book page detection image when detecting that the indication mark enters or exits from the book page area, where the indication mark is used to indicate the book page to be read.
And when the indication mark is detected to enter or exit from the shielding book page area, reading the book page area as a book page detection image. By adopting the technical means, the interference existing when the book page detection image is determined can be avoided, and the book page detection image with better quality is provided, so that the original page inquiry and the click-to-read content determination can be conveniently carried out, and the use experience of a user is optimized.
Specifically, the method further comprises the following steps:
and the detection updating module is used for carrying out detection and marking on the page area of the book again when the movement of the page of the book is detected.
Specifically, the marking module 22 includes:
the detection unit is used for detecting the target image based on an edge detection algorithm, identifying a book page area and marking the book page area.
And the screening unit is used for determining book page area samples corresponding to each target image according to the book page area detection, and screening out the book page area with the least interference information from the book page area samples based on the interference information detection for marking.
Specifically, the reading module 23 includes:
and the tracking unit is used for extracting image data corresponding to the page area of the book, and detecting and tracking the indication mark based on a pre-trained indication mark detection and tracking algorithm.
The book detection device of the point-reading device provided by the second embodiment of the application can be used for executing the book detection method of the point-reading device provided by the first embodiment, and has corresponding functions and beneficial effects.
Embodiment III:
an electronic device according to a third embodiment of the present application, referring to fig. 7, includes: processor 31, memory 32, communication module 33, input device 34 and output device 35. The number of processors in the electronic device may be one or more and the number of memories in the electronic device may be one or more. The processor, memory, communication module, input device, and output device of the electronic device may be connected by a bus or other means.
The memory 32 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and a module corresponding to a book detection method of a point-and-read device according to any embodiment of the present application (for example, an acquisition module, a marking module, and a reading module in a book detection device of the point-and-read device). The memory may mainly include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, the memory may further include memory remotely located with respect to the processor, the remote memory being connectable to the device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The communication module 33 is used for data transmission.
The processor executes various functional applications of the device and data processing, namely, the book detection method of the point-and-read device described above, by running the software programs, instructions and modules stored in the memory 31.
The input means 34 may be used to receive entered numeric or character information and to generate key signal inputs related to user settings and function control of the device. The output means 35 may comprise a display device such as a display screen.
The electronic device provided by the above-mentioned embodiment can be used for executing the book detection method of the point-and-read device provided by the above-mentioned embodiment, and has corresponding functions and beneficial effects.
Embodiment four:
the embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a book detection method of a point-to-read device, the book detection method of the point-to-read device comprising: continuously acquiring a plurality of target images in the shooting range of the camera, wherein the target images comprise image data of book pages; detecting a book page area based on the target image, and marking the corresponding book page area; when the indication mark is detected to enter or exit from the book page area, the book page area is read to serve as a book page detection image, and the indication mark is used for indicating a book page to be read.
Storage media-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbas (Rambus) RAM, etc.; nonvolatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a second, different computer system connected to the first computer system through a network such as the internet. The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (e.g., in different computer systems connected by a network). The storage medium may store program instructions (e.g., embodied as a computer program) executable by one or more processors.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present application is not limited to the book detection method of the point-reading device described above, and may also perform the related operations in the book detection method of the point-reading device provided in any embodiment of the present application.
The book detection device, the storage medium and the electronic device of the point-to-read device provided in the foregoing embodiments may perform the book detection method of the point-to-read device provided in any embodiment of the present application, and technical details not described in detail in the foregoing embodiments may be referred to the book detection method of the point-to-read device provided in any embodiment of the present application.
The foregoing description is only of the preferred embodiments of the application and the technical principles employed. The present application is not limited to the specific embodiments described herein, but is capable of numerous modifications, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, while the application has been described in connection with the above embodiments, the application is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit of the application, the scope of which is set forth in the following claims.
Claims (9)
1. A book detection method of a point-and-read device, comprising:
continuously acquiring a plurality of target images in the shooting range of the camera, wherein the target images comprise image data of book pages;
detecting a book page area based on the target image, and marking the corresponding book page area; wherein, include: according to the book page area detection, determining a book page area sample corresponding to each target image, and screening out a book page area with the least interference information from the book page area sample based on the interference information detection for marking;
when the indication mark is detected to enter or exit from the book page area, the book page area is read to serve as a book page detection image, and the indication mark is used for indicating a book page to be read.
2. The book detection method of the point-and-read apparatus according to claim 1, characterized by further comprising, after performing book page area detection based on the target image and marking the corresponding book page area:
and when the movement of the book page is detected, the detection and marking of the page area of the book are carried out again.
3. The book detection method of a point-and-read device according to claim 2, wherein the detecting of the book page movement includes:
extracting two continuous target images;
determining two corresponding book page areas according to the book page area detection;
and comparing and judging that the coordinate information of the two book page areas has change, and determining the movement of the book pages.
4. The book detection method of the point-and-read device according to claim 1, wherein the detecting of the book page area based on the target image, marking the corresponding book page area, includes:
and detecting the target image based on an edge detection algorithm, identifying a book page area, and marking the book page area.
5. The book detection method of the point-and-read device according to claim 1, wherein the detecting the indication mark entering or exiting the area of the book page includes:
and extracting image data corresponding to the page area of the book, and detecting and tracking the indication mark based on a pre-trained indication mark detection and tracking algorithm.
6. The book detection method of the point-and-read apparatus according to claim 1, characterized by further comprising, after said reading said book page area as a book page detection image:
and inquiring a preset original page database based on the book page detection image, and determining corresponding original page data, wherein the original page data is used for determining the content pointed and read by the user indication mark.
7. A book detecting apparatus of a point-reading device, comprising:
the acquisition module is used for continuously acquiring a plurality of target images in the shooting range of the camera, wherein the target images comprise image data of book pages;
the marking module is used for detecting the page areas of the books based on the target image and marking the corresponding page areas of the books; wherein, the marking module includes: the screening unit is used for determining book page area samples corresponding to all target images according to the book page area detection, and screening out book page areas with the least interference information from the book page area samples based on the interference information detection for marking;
and the reading module is used for reading the book page area to serve as a book page detection image when the indication mark is detected to enter or exit from the book page area, and the indication mark is used for indicating the book page to be read.
8. An electronic device, comprising:
a memory and one or more processors;
the memory is used for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the book detection method of the point-and-read device of any one of claims 1-6.
9. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the book detection method of the point-and-read device of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010203077.4A CN111311624B (en) | 2020-03-20 | 2020-03-20 | Book detection method and device of point reading equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010203077.4A CN111311624B (en) | 2020-03-20 | 2020-03-20 | Book detection method and device of point reading equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111311624A CN111311624A (en) | 2020-06-19 |
| CN111311624B true CN111311624B (en) | 2023-08-18 |
Family
ID=71157285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010203077.4A Active CN111311624B (en) | 2020-03-20 | 2020-03-20 | Book detection method and device of point reading equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111311624B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007005934A (en) * | 2005-06-21 | 2007-01-11 | Ricoh Co Ltd | Image processing apparatus, image processing method, and image processing program |
| CN107835366A (en) * | 2017-11-07 | 2018-03-23 | 广东欧珀移动通信有限公司 | Multi-medium play method, device, storage medium and electronic equipment |
| CN109656465A (en) * | 2019-02-26 | 2019-04-19 | 广东小天才科技有限公司 | A kind of content acquisition method and private tutor's equipment applied to private tutor's equipment |
| CN109725732A (en) * | 2019-01-23 | 2019-05-07 | 广东小天才科技有限公司 | A kind of querying method and private tutor's equipment of knowledge point |
| CN110060524A (en) * | 2019-04-30 | 2019-07-26 | 广东小天才科技有限公司 | The method and reading machine people that a kind of robot assisted is read |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001093591A1 (en) * | 2000-05-29 | 2001-12-06 | Sony Corporation | Image processing apparatus and method, communication apparatus, communication system and method, and recorded medium |
-
2020
- 2020-03-20 CN CN202010203077.4A patent/CN111311624B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007005934A (en) * | 2005-06-21 | 2007-01-11 | Ricoh Co Ltd | Image processing apparatus, image processing method, and image processing program |
| CN107835366A (en) * | 2017-11-07 | 2018-03-23 | 广东欧珀移动通信有限公司 | Multi-medium play method, device, storage medium and electronic equipment |
| CN109725732A (en) * | 2019-01-23 | 2019-05-07 | 广东小天才科技有限公司 | A kind of querying method and private tutor's equipment of knowledge point |
| CN109656465A (en) * | 2019-02-26 | 2019-04-19 | 广东小天才科技有限公司 | A kind of content acquisition method and private tutor's equipment applied to private tutor's equipment |
| CN110060524A (en) * | 2019-04-30 | 2019-07-26 | 广东小天才科技有限公司 | The method and reading machine people that a kind of robot assisted is read |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111311624A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huh et al. | Fighting fake news: Image splice detection via learned self-consistency | |
| CN111696128B (en) | High-speed multi-target detection tracking and target image optimization method and storage medium | |
| CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| US10600190B2 (en) | Object detection and tracking method and system for a video | |
| US8417026B2 (en) | Gesture recognition methods and systems | |
| CN109947273B (en) | Point reading positioning method and device | |
| CN110348392B (en) | Vehicle matching method and device | |
| JP7204786B2 (en) | Visual search method, device, computer equipment and storage medium | |
| CN111881740A (en) | Face recognition method, face recognition device, electronic equipment and medium | |
| CN111311624B (en) | Book detection method and device of point reading equipment | |
| CN112965602A (en) | Gesture-based human-computer interaction method and device | |
| CN105389812A (en) | Computer vision-based vehicle-mounted information terminal function automatic test method | |
| CN113743434A (en) | Training method of target detection network, image augmentation method and device | |
| US20220122341A1 (en) | Target detection method and apparatus, electronic device, and computer storage medium | |
| CN110765994B (en) | Book content positioning method and device, electronic equipment and storage medium | |
| CN113449652A (en) | Positioning method and device based on biological feature recognition | |
| CN112529883A (en) | Patch detection method and device based on image edge recognition | |
| KR20210079180A (en) | Method and apparatus for recognizinf vehicle license plate | |
| CN112686129A (en) | Face recognition system and method | |
| CN112464828B (en) | Method, device, equipment and storage medium for marking data of document image edge | |
| CN112364867B (en) | Intelligent correcting method and system for handwriting operation, electronic equipment and storage medium | |
| CN111324697B (en) | Analysis management method and device for home education machine data | |
| CN112508927A (en) | Patch image identification method and device based on error feature identification | |
| US20220343538A1 (en) | Model Creation Device and Model Creation Method | |
| CN118034515A (en) | Touch information identification method and device, touch device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |