CN111598943B - Book in-place detection method, device and equipment based on book auxiliary reading equipment - Google Patents
Book in-place detection method, device and equipment based on book auxiliary reading equipment Download PDFInfo
- Publication number
- CN111598943B CN111598943B CN202010295742.7A CN202010295742A CN111598943B CN 111598943 B CN111598943 B CN 111598943B CN 202010295742 A CN202010295742 A CN 202010295742A CN 111598943 B CN111598943 B CN 111598943B
- Authority
- CN
- China
- Prior art keywords
- book
- image
- place
- detection
- frame
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
The invention discloses a book in-place detection method, a device and equipment based on book auxiliary reading equipment. The invention is characterized in that the invention abandons directly searching book images, but firstly detects the whole abnormal input in the imaging range of the camera, and on the basis, compares and analyzes the image information of the local area of the captured current image and the image when not in place, thereby judging the in-place state of the book. According to the invention, a plurality of situations in practical application of a user are considered, other abnormal situations such as non-book positioning are filtered, and the number of times of identifying books per se by triggering is greatly reduced through the comparison thought of local targets, so that the operand is effectively reduced, the problem of time consumption in detection is solved, and the problem of network delay when a request server side performs book retrieval is avoided.
Description
Technical Field
The invention relates to the field of book auxiliary reading equipment, in particular to a book in-place detection method, device and equipment based on the book auxiliary reading equipment.
Background
For specific user groups, such as young children, low-grade students and the like, auxiliary reading equipment which uses electronic components such as cameras and the like to assist in detecting entity book contents, such as a book reading robot and the like, is proposed in the market, and when in use, a user needs to place an entity book in an identifiable area of the auxiliary reading equipment, and the equipment processes and outputs the book contents through an intelligent recognition technology. Therefore, the in-place status of the book has a certain influence on the normal use of such products, that is, how to let the book auxiliary reading device "know" that the identifiable region exists a book to be processed, which plays a fundamental key role in the subsequent processes of identifying, retrieving, outputting the content, etc.
According to analysis, the problems of overhigh comprehensive cost, complex interaction operation, repeated and time-consuming process and the like exist in the detection of the in-place state of the book at present, and particularly, the in-place detection process lacks reasonable design and is considered for a plurality of abnormal conditions, so that frequent refusal of recognition is caused and the user experience is poor.
Disclosure of Invention
In view of the above, the present invention aims to provide a method, an apparatus and a device for detecting the position of a book based on a book auxiliary reading device, and correspondingly provides a computer readable storage medium and a computer program product, which solve a plurality of defects of the existing book position detection technology by designing a detection mode of combining anomaly filtering with image comparison, and provide a reliable basis for further processing such as automatic identification, retrieval and output of book contents.
The technical scheme adopted by the invention is as follows:
in a first aspect, the present invention provides a book in-place detection method based on a book auxiliary reading device, including:
presetting a standard image of a target area in an imaging range based on a specific marker in a book unsetting state;
detecting abnormal input of each input whole image;
after filtering abnormal input, obtaining a current image of the target area in each frame of image;
and comparing the current image with the standard image to determine the current in-place state of the book.
In one possible implementation manner, the detecting abnormal input of the whole image of each frame of input includes:
edge detection is carried out frame by frame;
based on the whole image of each frame after edge detection, the following condition judgment is sequentially carried out: a. whether the number of straight lines in the whole image is four or not; b. whether the four straight lines form a rectangle or not; c. whether the rectangular area is smaller than a preset threshold value or not; d. whether the rotation angle of the rectangle is smaller than a preset threshold value or not;
and when the judging result of any one of the conditions is negative, judging the frame image as abnormal input and filtering the frame image.
In one possible implementation manner, the comparing the current image with the standard image includes:
Comparing the similarity of the pixel characteristics of the specific identifier in the current image and the standard image based on a difference hash algorithm;
determining that the book is in an unseated state for the current image meeting a first similarity standard;
extracting edge characteristics of the current image which does not accord with a first similarity standard by using an OTSU algorithm;
comparing the similarity of the edge characteristics of the specific marker in the current image and the standard image based on edge morphology;
the current in-place status of the book is determined based on the second similarity criteria.
In one possible implementation manner, the method further includes:
before comparing the current image with the standard image, detecting brightness of the current image of each frame;
and carrying out brightness adjustment on the current image with abnormal brightness, and then comparing the current image with the current image.
In one possible implementation manner, the method further includes:
dynamically updating the standard image according to the unset state detected in the process of the seated detection;
and detecting the book in-place state based on the updated standard image.
In a second aspect, the present invention provides a book in-place detection device based on a book auxiliary reading device, including:
The standard image presetting module is used for presetting a standard image of a target area in an imaging range based on a specific marker in a book unsetting state;
the abnormal detection module is used for carrying out abnormal input detection on each input whole image;
the current image acquisition module is used for acquiring a current image of the target area in each frame of image after filtering abnormal input;
and the in-place state detection module is used for comparing the current image with the standard image to determine the current in-place state of the book.
In one possible implementation manner, the abnormality detection module includes:
the first edge detection unit is used for carrying out edge detection frame by frame;
an abnormal condition judgment unit for sequentially performing the following condition judgment based on the whole image of each frame after edge detection: a. whether the number of straight lines in the whole image is four or not; b. whether the four straight lines form a rectangle or not; c. whether the rectangular area is smaller than a preset threshold value or not; d. whether the rotation angle of the rectangle is smaller than a preset threshold value or not;
and the abnormality filtering unit is used for judging the frame image as abnormal input and filtering the frame image when the judging result of any one of the conditions is negative.
In one possible implementation manner, the in-place status detection module includes:
the pixel characteristic comparison unit is used for comparing the similarity of the pixel characteristics of the specific identifier in the current image and the standard image based on a difference hash algorithm;
the in-place state first judging unit is used for determining that the book is in an out-of-place state for the current image meeting a first similarity standard;
the second edge detection unit is used for extracting edge characteristics of the current image which does not accord with the first similarity standard by using an OTSU algorithm;
the edge feature comparison unit is used for comparing the similarity of the edge features of the specific identifier in the current image and the standard image based on edge morphology;
and the second in-place state judging unit is used for determining the current in-place state of the book according to the second similarity standard.
In one possible implementation manner, the apparatus further includes: a brightness detection module;
the brightness detection module specifically comprises:
the brightness detection unit is used for detecting the brightness of each frame of the current image before comparing the current image with the standard image;
And the brightness adjusting unit is used for adjusting the brightness of the current image with abnormal brightness.
In one possible implementation manner, the apparatus further includes:
the standard image updating module is used for dynamically updating the standard image according to the unsetting state detected in the seated detection process;
the in-place state detection module is also used for detecting the in-place state of the book based on the updated standard image.
In a third aspect, the present invention provides a book reading assisting apparatus comprising:
one or more processors, a memory, and one or more computer programs, the memory may employ a non-volatile storage medium, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions which, when executed by the device, cause the device to perform the method as in the first aspect or any of the possible implementations of the first aspect.
In one possible implementation manner, the book auxiliary reading device is a drawing book reader, and a specific identifier for detecting the book in-place state is arranged on the drawing book reader.
In a fourth aspect, the present invention provides a computer readable storage medium having stored therein a computer program which when run on a computer causes the computer to perform the method as in the first aspect or any of the possible implementations of the first aspect.
In a fifth aspect, the invention also provides a computer program product for performing the method of the first aspect or any of the possible implementations of the first aspect, when the computer program product is executed by a computer.
In a possible design of the fifth aspect, the relevant program related to the product may be stored in whole or in part on a memory packaged with the processor, or may be stored in part or in whole on a storage medium not packaged with the processor.
The invention is characterized in that the invention abandons directly searching book images, but firstly detects the whole abnormal input in the imaging range of the camera, and on the basis, compares and analyzes the image information of the local area of the captured current image and the image when not in place, thereby judging the in-place state of the book. According to the invention, a plurality of situations in practical application of a user are considered, other abnormal situations such as non-book positioning are filtered, and the times of identifying and refusing book contents per se are greatly reduced through the comparison thought of local targets, so that the operation amount is effectively reduced, the problem of time consumption in detection is solved, and the problem of network delay when a request server side performs book retrieval is avoided.
Furthermore, the invention combines a difference hash algorithm and an OTSU algorithm-based edge detection algorithm to carry out staged matching analysis on the current image information and the standard image information, and the progressive judging process ensures the reliability of the in-place detection result.
Furthermore, the invention provides dynamic updating of the comparison standard so as to be more close to different use environments of different users, and further, book in-place detection can be adaptively carried out in an actual application scene, so that the accuracy of in-place detection results is improved.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of an embodiment of a book in-place detection method based on a book-assisted reading device provided by the invention;
FIG. 2 is a schematic diagram showing a comparison of the status of a book in-place reading device according to the present invention;
FIG. 3 is a flowchart of an embodiment of an anomaly input filtering method provided by the present invention;
FIG. 4 is a flowchart of an embodiment of an image feature comparison method provided by the present invention;
FIG. 5 is a schematic diagram of an embodiment of a differential hash matrix provided by the present invention;
FIG. 6 is a flowchart of an embodiment of an edge detection method according to the present invention;
FIG. 7 is a block diagram of an embodiment of a book in-place detection device based on a book auxiliary reading apparatus provided by the invention;
fig. 8 is a block diagram of another embodiment of a book in-place detecting device based on a book auxiliary reading apparatus provided by the invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
Before the technical scheme of the invention is described, the prior book in-place state detection scheme is described, and at present, in the field of book auxiliary reading equipment, book in-place detection is generally carried out in three modes: firstly, user intervention, namely triggering book auxiliary reading equipment to start identification processing through interactive operations such as key pressing, selection and the like; secondly, performing physical sensing of the in-place state through a hardware mechanism; thirdly, directly searching the books according to the images captured by the cameras, namely firstly identifying the captured images aiming at the book contents, and triggering refusal if the contents are not identified.
Accordingly, the above manner also causes respective defects: firstly, the user has frequent intervention and poor usability, so that the user experience is poor; secondly, the difficulty of hardware design and production is increased, and particularly once the hardware is damaged, the maintenance is more inconvenient, so that the comprehensive cost is increased; thirdly, whether books are needed to be searched for each frame of image captured by the camera or not is needed continuously, so that frequent requests and repeated operation are needed, background processing pressure and risk are increased, and meanwhile, the calculation process is complex and time-consuming.
In view of this, the present invention proposes a technical concept of comparing information in an input image with information in a standard image based on the setting of a specific identifier, so that a user does not need to participate in a book state confirmation link, and a mechanical detection mechanism is not required to be configured, in particular, many drawbacks of directly identifying a book are avoided, and in a specific embodiment, two key links are designed to ensure accuracy and reliability of in-place detection, firstly, abnormality filtering is performed on a global image, and secondly, local image analysis is performed after abnormality filtering.
In connection with the specific embodiment, the present invention provides an embodiment of a book in-place detection method based on a book auxiliary reading device, as shown in fig. 1, which may include the following steps:
And S0, presetting a standard image of a target area in an imaging range based on the specific marker in a book unsetting state.
It will be appreciated that the area for placing a book in the imaging field is relatively unchanged when the book is not in place, so that an image of a book when it is not in place can be taken by a camera of the book-assisted reading device in a normal daylight environment during a development test period or in a factory setting, as a reference basis for subsequent frame-by-frame comparison. In practical operation, a plurality of specific markers, such as but not limited to LOGO characters, device image patterns and the like, can be arranged in an imaging range in combination with the use characteristics of the book auxiliary reading device, and a target area, namely a local imaging area which is necessarily covered when the book is normally placed, is defined in advance based on the specific markers, and particularly the local area should contain the specific markers, so that the book is necessarily covered on the specific markers when the book is normally placed, and a comparison basis is provided for comparison of subsequent image information. Continuing from the foregoing, in a preset stage, the region image in the global image (which may be denoted as image_std) may be taken as a standard image (which may be denoted as roistd) of the target region a, and then relevant image information of the roistd is obtained, for example, but not limited to, performing Canny operator edge detection on the roistd to obtain an edge binary image (which may be denoted as canny_std), and or performing hash computation after scaling the roistd to obtain a hash sequence (which may be denoted as hash_std), so that in some embodiments, the image information triples (roistd, canny_std, hash_std) may be used. The technical content will be specifically developed, but it may be described herein that the mode of setting the reference standard image related to the link is not only shown in the prefabricated link but also described in the related description in other embodiments of the present invention, which is not described herein.
And S1, detecting abnormal input of the whole input image of each frame.
In the process of analyzing the book in place, the invention finds that in-place state detection under the actual use scene actually encounters various conditions, especially the illegal input condition of various anomalies in the captured image, if the anomalies cannot be filtered before in-place detection, the effect of subsequent in-place detection processing can be interfered, and even the rejection of the book content is frequently triggered.
To facilitate an understanding of the design context and related example scenarios of the present invention, FIG. 2 is a schematic illustration of various book placement scenarios for comparison: fig. 2 (a) shows the situation without book placement, and can also be understood as the aforementioned standard image, wherein the target area a is a local area to be aligned and detected later, and since the schematic diagram is based on the model of some auxiliary reading device (the device comprises a hand board component for placing books), this area a can also be called a hand board characteristic area, and further fig. 2 (a) uses the word "hand board" as the specific identifier in the area a, and the area C shows the whole image range that can be captured by the camera, namely an imaging area; FIG. 2 (B) shows the book in a completely and correctly positioned state, wherein the pixels in the area A are all book parts, i.e. the dark physical book covered area B covers the area A and the "palm" completely; FIG. 2 (c) is a situation where the book is not fully in place and is not able to cover the "palm" two words; FIG. 2 (d) is a case where the book is not fully in place and only partially covers the "palm" two words; fig. 2 (e) is a case where the book is not placed in a correct manner, for example, the book is rotated by a certain angle; fig. 2 (f) is a "pseudo-in-place" situation when other objects than books are placed on the reader's hand plate.
As is clear from this six comparison, there is a clear difference between the absence of the book (a) and the imaging of the area a when the book is placed in various forms (b, c, d, e) and when the non-book object is in place (f). Wherein, (e, f) belongs to the abnormal input condition, if the imaging difference of the area A is only analyzed, the (e, f) is difficult to distinguish from the (b, c, d), and accordingly, the invention proposes that the complete book in-place detection at least comprises two key parts, firstly, the whole image is analyzed to realize the filtering of the abnormal condition, and the local area A is in-place detected after the abnormal filtering is completed, so that the book in-place state can be reliably determined. When the auxiliary reading device is started, each frame of global image captured continuously is recorded as img_test, edge detection is carried out on the current frame img_test, multi-stage abnormality detection is carried out according to a certain condition judgment sequence based on the whole image of each frame after the edge detection, if abnormal input is judged, the subsequent local feature detection is not carried out, in other words, the local feature detection is carried out only when normal input is judged, and once abnormal condition is not met, the current frame image is judged to be abnormal input and filtered.
In particular, reference may be made to the anomaly input filtering flow in some preferred embodiments shown in FIG. 3. As shown in FIG. 3, when judging whether the abnormal input is the abnormal input, firstly, the edge detection is needed to be carried out on the current frame image, and the edge detection algorithm can adopt an improved methodThe Canny operator edge detection is described in detail below. And obtaining an edge binary image by edge detection, wherein the pixel value of an edge point is 1, the pixel value of a non-edge point is 0, and then carrying out cumulative probability Hough transformation on the edge binary image. It should be noted that, the present embodiment adopts the cumulative probability hough transform, which is considered to have higher execution efficiency than the standard hough transform and the multi-scale hough transform; then, detecting straight lines existing in the edge binary image by accumulated probability Hough transform and returning the detected straight line number, wherein the invention is based on book characteristics, and in some embodiments, a first term abnormality judgment condition is defined as whether the number of the straight lines is more than or equal to four, and less than four are illegally input; or determining whether four, i.e. less or more than four, are considered illegal inputs (of course, it may be added that if it is determined that a straight line exists in the whole image after edge detection, coordinates of two end points of the straight line may be returned, i.e. information of each straight line is represented by a four-element tuple (x 1 ，y 1 ，x 2 ，y 2 ))。
When the number of the straight lines is determined to be four, a straight line equation can be determined through two points of the straight lines, and the four straight lines L are obtained 1 、L 2 、L 3 、L 4 Therefore, whether the rectangle is formed by four straight lines can be further judged, and in actual operation, the investigation of the condition can be disassembled into a two-step condition, wherein one straight line can find out only one straight line parallel to the other three straight lines in the four straight lines; and the second is that the included angle between two straight lines of the non-parallel straight line pair is 90 degrees plus or minus delta theta, wherein delta theta represents the deviation of the allowable included angle, so that whether the rectangular frame of the class book is formed can be judged.
Next, the side length of the four sides of the rectangular frame can be recorded as l 1 、l 2 、l 3 、l 4 (ideal state, l 1 ＝l 3 ，l 2 ＝l 4 ) Judging whether the shortest line length is smaller than the set length threshold value l, namely min (l 1 ，l 2 ，l 3 ，l 4 ) < l. By controlling the magnitude of the threshold value l, those which are full can be filtered outFour straight lines are used and can form a rectangle, but illegal input with too small area of the similar area is performed, namely rectangular objects with the area obviously smaller than that of a book, such as mobile phones, notepaper and the like, are filtered out.
Finally, whether the abnormal condition of the rotating book is the abnormal condition can be determined through four vertexes of a rectangular frame formed by four straight lines. Specifically, the point with the smallest ordinate of the four vertex coordinates can be denoted as P, and the included angle between the two straight lines and the positive direction of the x-axis is respectively calculated as theta 1 、θ 2 ，min(θ 1 ，θ 2 ) And the size of the threshold value delta theta' is controlled to set the situation that how much the book rotates to be placed to meet the requirement, so that the problem that the subsequent in-place detection effect is reduced due to overlarge rotation angle is avoided.
In the judging process of the conditions, once any condition detects that the standard is not met, the abnormal filtering operation can be executed, the next frame of whole image is continuously extracted to continue the implementation process, namely, if all the conditions are met, the whole image is considered to have legal entity books which are similar to the outline of books and are placed in a standard, and therefore a processing link for judging whether the books are in place can be further executed successively. It should be noted that the above determination conditions are merely illustrative, and the determination conditions for the abnormal input condition may be adjusted accordingly based on specific implementation manners of the determination conditions for different usage scenarios.
And S2, obtaining the current image of the target area in each frame of image after filtering abnormal input.
After the anomaly filtering, the current image of the target area is intercepted from the whole image of each frame, namely, the global image is cut according to the standard which is consistent with the standard image standard position, so that the current imaging (which can be recorded as a roi_test) of the area A is obtained, and the positioning state of the book can be judged by comparing the roi_std with the roi_test.
Before describing a specific comparison method, it may further be described that, in other embodiments of the present invention, before comparing the current image with the standard image, brightness detection may be performed on each frame of current image, and brightness adjustment may be performed on the current image with abnormal brightness before comparison. Specifically, the brightness detection is performed on the roi_test first, for example, in some embodiments, the image brightness detection may be performed based on the average deviation, by calculating the average deviation and the average deviation of the image, selecting a relative gray scale reference (for example, 128 is selected), and calculating the average deviation Da of the image:
in the formula (1), i is an index of image pixels, and N is the number of image pixels. Obtaining gray scale intervals [0, 255 ] by using gray scale histogram statistical method]The number Hist [ val ] of pixel points corresponding to each gray value]The average deviation M of the deviation reference is obtained by weighting calculation by taking the number of pixels corresponding to the gray level val as the weight a As shown in formula (2):
in formula (2), val ε [0, 255]For image grey level by comparing D a And M is as follows a The absolute value of the ratio is the luminance parameter K,
when K is less than 1, the brightness of the image is normal; k is more than or equal to 1 and D a At > 0, the image is too bright; k is more than or equal to 1 and D a At < 0, the image is too dark.
Then, if the detection result is abnormal brightness (too bright or too dark), histogram equalization processing can be performed on the image with abnormal brightness, so that the influence of abnormal brightness of the image on subsequent in-place detection can be avoided.
It should be emphasized here that, in the preferred embodiment, the above-mentioned brightness detection and adjustment strategy is designed to be relevant and specific to the concept of the present invention, and because the present invention does not need to use a hardware mechanism to determine the in-place status, but relies on the difference of images in different stages of regions (specifically, may refer to the difference of the identifier in the target region in different images) to perform the in-place detection, the process of brightness detection and adjustment may play a more critical role in the concept of the present invention, so that the comparison effect between two images is more reliable and the result is more accurate.
And S3, comparing the current image with the standard image to determine the current in-place state of the book.
Aiming at the step, the invention designs an implementation mode of in-place detection from the angle of image feature similarity, and can adopt a staged comparison thought, the features based on all pixel points and the edge features are selected from the image features to be compared successively, and the method is also characterized in that two elements in the three elements of the standard image are obtained in the prefabrication step, and the final book in-place state detection result is more accurate through the concept of step-by-step screening, filtering and eliminating. Before specific expansion, it should be further noted that if the standard image is an image subjected to scaling, the current image may be scaled to the same size as 9×8 before feature comparison, and those skilled in the art will understand that scaling to a smaller size may eliminate the differential interference caused by different image sizes and scales.
In connection with step S3, the present invention, in some preferred embodiments, employs a staged comparison process as shown in fig. 4, and may include the following steps:
s31, comparing the similarity of pixel characteristics of the specific identifier in the current image and the standard image based on a difference hash algorithm;
step S32, determining that the book is in an unseated state for the current image which accords with a first similarity standard;
step S33, extracting edge characteristics of the current image which does not accord with a first similarity standard by using an OTSU algorithm;
step S34, comparing the similarity of the edge characteristics of the specific marker in the current image and the standard image based on the edge morphology;
and step S35, determining the current in-place state of the book according to the second similarity standard.
Specifically, this embodiment obtains a hash sequence (which may be referred to as hash_test) through a difference hash calculation, so as to represent the pixel characteristics of the image. Of course, there are many kinds of hash algorithms available in the image processing field, such as mean-average hash (aHash) and perceptual hash (pHash). However, in the design of the invention, the aHash is considered to be greatly affected by the average value of the image, and if the image is corrected or the histogram is balanced, the average value of the image is affected, so that the hash value of the aHash is affected; and pHash obtains a scattered cosine transformation coefficient matrix through discrete cosine transformation, and the left upper corner part of the coefficient matrix is subjected to aHash, so that the operation speed is slower although the coefficient matrix is more robust than aHash. Therefore, in some embodiments, the invention proposes to use a difference hash (dHash) with higher precision and fast operation speed to perform the preliminary comparison of the pixel feature similarity, and the algorithm steps can be referred as follows:
Taking the current image after scaling processing as an example, the difference between adjacent pixels in each row of the current image is calculated, if the pixel value on the left is greater than that on the right, the pixel value is marked as 1, otherwise, the pixel value is marked as 0, and an 8×8 difference matrix can be obtained, as shown in fig. 5. The difference hash matrix in fig. 5 may also be regarded as a sequence with a length of d 0-d 63 of 64, so if the standard image and the current image are subjected to difference hash, two sequences with identical lengths may be obtained, and then the similarity of the two images may be measured by comparing the similarity of the two sequences, for example, the difference between the two images may be selectively compared by hamming distance, specifically, the hamming distance (may be denoted as dist) between hash_test and hash_std may be calculated, then it is determined whether dist is greater than the set first similarity threshold T0, if T0 is less than or equal to T0, the two images are considered to be similar, that is, if it is determined that the book in the current image is not in place, then the subsequent determination of the current frame may be ended, and the next frame may be extracted to repeat the above comparison process. If the current frame is greater than T0, the next comparison stage may be entered, for example, the current image is then subjected to Canny operator edge detection to obtain an edge detected image (which may be denoted as canny_test), where the present invention provides the following improved edge detection concept in combination with the existing edge detection flow:
Firstly, smoothing noise through Gaussian filtering, and eliminating the possibility that a noise point generates a pseudo edge point in edge detection; secondly, calculating image gradient and amplitude by adopting a Sobel operator and carrying out non-maximum suppression; finally, the image edge points are detected and edges are connected by using a double-threshold algorithm. The improved thought of edge detection provided by the invention is developed around the last double-threshold algorithm, and particularly, in some preferred embodiments, the improved thought of edge detection of a Canny operator is realized by changing the traditional mode of manually setting high and low double thresholds into an OTSU iterative method to select the double thresholds.
The OTSU iterative double-threshold method (oxford method) is generally used in the art to directly segment an image, and the method provided by the invention is applied to edge detection to improve the rationality of the edge detection, so that the detected edge characteristics have better robustness and adaptability.
The purpose of the Canny operator double threshold mechanism is to obtain more edges with high thresholds and filter more noise false edges with low thresholds. Therefore, the invention adopts OTSU to determine the high threshold Th high Determining a low threshold Th using an iterative threshold low . Reference may be made specifically to the flow shown in fig. 6:
First, an initial threshold is selected
Wherein G is max For maximum image gray level, G min Is the minimum value of the image gray scale. By T 0 Dividing the image to obtain region I 1 And region I 2 ，I 1 For the high gray value region, I 2 For the low gray value region, at I 1 Further using OTSU algorithm to obtain maximum inter-class variance to determine Th high Let t be the threshold value I 1 Dividing into foreground and background areas, and dividing the foreground into pixelsNumber N 1 ，I 1 The total pixel point number is M, the front Jing Zhan I 1 The ratio of the total pixel points is alpha 0 ，
Likewise, the background occupies I 1 The ratio of the total pixel points is alpha 1 ，
The total average gray level of I1 is:
μ＝μ 0 ×α 0 +μ 1 ×α 1 formula (6)
The formula is as follows:
η(t) 2 ＝α 0 (μ 0 -μ) 2 +α 1 (μ 1 -μ) 2 ＝α 0 α 1 (μ 0 -μ 1 ) 2 formula (7)
In the formula, T is E (T) 0 ，255]Traversing the interval of t, and calculating to obtain the t value with the largest eta as the optimal high threshold Th high 。
Pair I 2 Further processing to determine optimal low threshold value, taking I 2 Is the minimum gray value Y of (2) 1 And a maximum gray value Y 2 Let T 1 ＝(Y 1 +Y 2 ) 2, T 1 Partition I 2 Calculating the gray average value U of the two divided parts 1 And U 2 A new threshold T is obtained 2 ＝(U 1 +U 2 )/2。|T 2 -T 1 I < T is the iteration termination condition, T is a set parameter, and is generally measured as small as possible, i.e. T 2 -T 1 When the values are very close, the optimal low threshold Th is considered to be taken low Otherwise using T 2 The value of (2) replaces T 1 The iteration is continued.
After the processing, a canny_test can be obtained, then similarity comparison of edge characteristics is carried out between the canny_std and the canny_std in the standard image information, if the similarity of the edge characteristics accords with a preset second similarity threshold value, the book is considered not to be in place, and the next frame is extracted to continue the processing; if the edge feature detection results are not similar, the book is finally considered to be in place.
For the manner of edge feature comparison, reference may be made to, but is not limited to, the manner in which the following embodiments relate: and obtaining an edge binary image canny_test of the area A after edge detection, and comparing the similarity of edge features of the two images by adopting a feature matching algorithm based on edge morphology. Specifically, morphological operations are performed on the channel_test, and an image obtained by filling the connected region of the edge may be denoted as edge_test. In the prefabrication step, edge filling can be performed on the canny_std to obtain edge_std, n feature points are selected from the edge_std, each feature point is composed of pixel coordinates and pixel values, and the feature points are marked as (x) i ，y i Value), and the same is preferable for edge_test to be detected (x i ，y i ) The value of the pixel in the eight neighborhood position is equal to the value of the pixel in the eight neighborhood, and if the value of the pixel in the eight neighborhood is equal to the value, the characteristics of the position in the two images are considered to be the same. It should be noted that taking pixels in eight neighborhoods instead of exactly the same coordinate position takes into account possible deviations of the camera. Then, the number of feature points which are inconsistent after the n feature points are compared is counted as M, and if M > M (M is a set threshold), the edge of the edge_std is considered to be different from the edge_test, that is, the area A of the current frame (the current image) is different from the area A when the book is not in place (the standard image), that is, the book is judged to be in place. The method can control how much of the total specific identifier of the area A is covered by the specific identifier after the book is in place, so that the book can be considered to be in place, for example, if only the characteristic identifier of the lower half of the area A is selected, the specific identifier is required to be covered completely by the book to judge that the book is in place, and if only half of the specific identifier is covered, the book is considered to be not in place, so that the user can be informed and guided to correctly make book placing actions in a guiding mode, the invention is not limited, but the invention needs to be emphasized again that the method can be used for placing the book by arranging Different similarity comparison criteria are used to adapt to different use needs, and then whether the book can be defined as in-place or out-of-place is determined.
Finally, according to the invention, the real use environment is not invariable, and the probability is very different from the environment in factory test, such as illumination brightness, a desktop carrier, shadows of other surrounding objects and the like, so that in some preferred embodiments, the standard image can be dynamically updated in the in-place detection process, rather than in-place detection according to the fixed comparison standard provided in the prefabricated link, and therefore, the compatibility and the high adaptability of the detection algorithm can be improved. For example, the standard image can be dynamically updated according to the unset state detected in the process of the set detection, and the subsequent book set state detection is performed based on the updated standard image. For example, when the user uses the book auxiliary reading device for the first time, the user performs positioning detection according to a standard image preset by factory, and as a result, when the images are compared due to shadow generated by a pen container on the desktop, the user is judged that the books are not positioned, then in the embodiment, the previously set standard image information can be updated based on the image information obtained by the detection, a new comparison standard is formed, then when the user repeatedly performs book placement, the user can perform detection by means of the updated standard image, so that the positioned books can be smoothly detected, and the subsequent identification, search, output and the like of the book contents can be started. Regarding the timing of dynamic update, the current in-place state of the book can be determined based on the change of the previous and subsequent frames, and the detection standard can be updated accordingly. The present invention provides an exemplary reference embodiment, for example, a global variable lastState may be set in the in-place detection process, and laststate=0 may be initialized to represent the detection result of the previous frame. If the result after detection is that the last frame is in place, the lastState is set to be 1, if the result of the next frame is detected to be out of place, whether the lastState is 1 is checked, if laststate=1, the current frame is an image of a book changed from a in-place state to an out-of-place state, at the moment, the lastState is modified to be 0 again, and the image information of the current frame is taken as standard image information, so that the dynamic update is realized, and the information of the standard image is ensured to be close to the current real use environment in real time.
Through the processes of anomaly filtering, brightness detection, difference hashing, hash sequence comparison, edge feature extraction, edge feature similarity comparison and the like described in the foregoing specific embodiments, the book in-place state is continuously detected in multiple stages after the device is opened, so that the book in-place situation in the using process of the device can be effectively judged, further, the opening time of subsequent processes such as book content identification and the like can be decided, and the number of subsequent identification requests and refusal times can be reduced to a certain extent.
In summary, the invention discards directly searching book content, but detects the whole abnormal input in the imaging range of the camera, and compares and analyzes the image information of the local area of the captured current image and the image when not in place on the basis, thereby judging the in-place state of the book. According to the invention, a plurality of situations in practical application of a user are considered, other abnormal situations such as non-book positioning are filtered, and the times of identifying and refusing book contents per se are greatly reduced through the comparison thought of local targets, so that the operation amount is effectively reduced, the problem of time consumption in detection is solved, and the problem of network delay when a request server side performs book retrieval is avoided.
Furthermore, the invention combines a difference hash algorithm and an OTSU algorithm-based edge detection algorithm to carry out staged matching analysis on the current image information and the standard image information, and the progressive judging process ensures the reliability of the in-place detection result.
Furthermore, the invention provides dynamic updating of the comparison standard so as to be more close to different use environments of different users, and further, book in-place detection can be adaptively carried out in an actual application scene, so that the accuracy of in-place detection results is improved.
Corresponding to the above embodiments and preferred solutions, the present invention further provides an embodiment of a book positioning detection device based on a book auxiliary reading device, as shown in fig. 7, which may specifically include the following components:
the standard image presetting module 0 is used for presetting a standard image of a target area in an imaging range based on a specific identifier in a book unsetting state;
the abnormality detection module 1 is used for detecting abnormal input of each input whole image;
the current image acquisition module 2 is used for acquiring a current image of the target area in each frame of image after filtering abnormal input;
and the in-place state detection module 3 is used for comparing the current image with the standard image to determine the current in-place state of the book.
In one possible implementation manner, the abnormality detection module includes:
the first edge detection unit is used for carrying out edge detection frame by frame;
an abnormal condition judgment unit for sequentially performing the following condition judgment based on the whole image of each frame after edge detection: a|, whether the number of straight lines in the whole image is four; b. whether the four straight lines form a rectangle or not; c. whether the rectangular area is smaller than a preset threshold value or not; d. whether the rotation angle of the rectangle is smaller than a preset threshold value or not;
and the abnormality filtering unit is used for judging the frame image as abnormal input and filtering the frame image when the judging result of any one of the conditions is negative.
In one possible implementation manner, the in-place status detection module includes:
the pixel characteristic comparison unit is used for comparing the similarity of the pixel characteristics of the specific identifier in the current image and the standard image based on a difference hash algorithm;
the in-place state first judging unit is used for determining that the book is in an out-of-place state for the current image meeting a first similarity standard;
the second edge detection unit is used for extracting edge characteristics of the current image which does not accord with the first similarity standard by using an OTSU algorithm;
The edge feature comparison unit is used for comparing the similarity of the edge features of the specific identifier in the current image and the standard image based on edge morphology;
and the second in-place state judging unit is used for determining the current in-place state of the book according to the second similarity standard.
In one possible implementation manner, as shown in fig. 8, the apparatus further includes: a brightness detection module 21;
the brightness detection module specifically comprises:
the brightness detection unit is used for detecting the brightness of each frame of the current image before comparing the current image with the standard image;
and the brightness adjusting unit is used for adjusting the brightness of the current image with abnormal brightness.
In one possible implementation manner, as shown in connection with fig. 8, the apparatus further includes:
a standard image updating module 4, configured to dynamically update the standard image according to an unset state detected in a process of unset detection;
the in-place state detection module is also used for detecting the in-place state of the book based on the updated standard image.
It should be understood that the book in-place detection device based on the book auxiliary reading device shown in fig. 7 and 8 can be used as a subsystem of an on-line system or can be used as a question-answering system alone. Moreover, the division of each component is only a division of a logic function, and may be fully or partially integrated into one physical entity or may be physically separated when actually implemented. And these components may all be implemented in software in the form of a call through a processing element; or can be realized in hardware; it is also possible that part of the components are implemented in the form of software called by the processing element and part of the components are implemented in the form of hardware. For example, some of the above modules may be individually set up processing elements, or may be integrated in a chip of the electronic device. The implementation of the other components is similar. In addition, all or part of the components can be integrated together or can be independently realized. In implementation, each step of the above method or each component above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
For example, the above components may be one or more integrated circuits configured to implement the above methods, such as: one or more specific integrated circuits (Application Specific Integrated Circuit; hereinafter ASIC), or one or more microprocessors (Digital Singnal Processor; hereinafter DSP), or one or more field programmable gate arrays (Field Programmable Gate Array; hereinafter FPGA), etc. For another example, these components may be integrated together and implemented in the form of a System-On-a-Chip (SOC).
In view of the foregoing examples and their preferred embodiments, those skilled in the art will appreciate that in practice the present invention is applicable to a variety of embodiments, and the present invention is schematically illustrated by the following carriers:
(1) A book-reading assisting device may include:
one or more processors, memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions, which when executed by the device, cause the device to perform the steps/functions of the foregoing embodiments or equivalent implementations.
In one possible implementation manner, the book auxiliary reading device is a drawing book reader, and a specific identifier for detecting the book in-place state is arranged on the drawing book reader.
(2) A readable storage medium having stored thereon a computer program or the above-mentioned means, which when executed, causes a computer to perform the steps/functions of the foregoing embodiments or equivalent implementations.
In several embodiments provided by the present invention, any of the functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, certain aspects of the present invention may be embodied in the form of a software product as described below, in essence, or as a part of, contributing to the prior art.
(3) A computer program product (which may comprise the apparatus described above) which, when run on a book-assisted reading device, causes the device to perform the book-in-place detection method based on the book-assisted reading device of the previous embodiment or equivalent.
From the above description of embodiments, it will be apparent to those skilled in the art that all or part of the steps of the above described methods may be implemented in software plus necessary general purpose hardware platforms.
Furthermore, in embodiments of the present invention, "at least one" means one or more, and "a plurality" means two or more. "and/or", describes an association relationship of the association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate that a alone exists, a and B together, and B alone exists. Wherein A, B may be singular or plural. The character "/" generally indicates that the context associated object is an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.
Those of skill in the art will appreciate that the various modules, units, and method steps described in the embodiments disclosed herein can be implemented in electronic hardware, computer software, and combinations of electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
And, each embodiment in the specification is described in a progressive manner, and the same and similar parts of each embodiment are mutually referred to. In particular, for embodiments of the apparatus, device, etc., as they are substantially similar to method embodiments, the relevance may be found in part in the description of method embodiments. The above-described embodiments of apparatus, devices, etc. are merely illustrative, in which modules, units, etc. illustrated as separate components may or may not be physically separate, i.e., may be located in one place, or may be distributed across multiple places, e.g., nodes of a system network. In particular, some or all modules and units in the system can be selected according to actual needs to achieve the purpose of the embodiment scheme. Those skilled in the art will understand and practice the invention without undue burden.
The construction, features and effects of the present invention are described in detail according to the embodiments shown in the drawings, but the above is only a preferred embodiment of the present invention, and it should be understood that the technical features of the above embodiment and the preferred mode thereof can be reasonably combined and matched into various equivalent schemes by those skilled in the art without departing from or changing the design concept and technical effects of the present invention; therefore, the invention is not limited to the embodiments shown in the drawings, but is intended to be within the scope of the invention as long as changes made in the concept of the invention or modifications to the equivalent embodiments do not depart from the spirit of the invention as covered by the specification and drawings.
Claims (10)
1. A book in-place detection method based on a book auxiliary reading device, comprising the steps of:
presetting a standard image of a target area in an imaging range based on a specific marker in a book unsetting state;
the method for detecting the abnormal input of the whole image of each input frame comprises the following steps: based on the whole image of each frame after edge detection, carrying out multi-stage abnormality detection according to a preset condition judgment sequence, and filtering if abnormal input is judged;
after filtering abnormal input, obtaining a current image of the target area in each frame of image;
comparing the current image with the standard image to determine the current in-place state of the book, wherein the current in-place state comprises in-place detection from the view of image feature similarity and stage comparison: and selecting the characteristics based on all the pixel points from the image characteristics and comparing the characteristics with the edge characteristics successively.
2. The book in-place detection method of claim 1, characterized in that said abnormal input detection of the entire image of each frame input includes:
edge detection is carried out frame by frame;
based on the whole image of each frame after edge detection, the following condition judgment is sequentially carried out: a. whether the number of straight lines in the whole image is four or not; b. whether the four straight lines form a rectangle or not; c. whether the rectangular area is smaller than a preset threshold value or not; d. whether the rotation angle of the rectangle is smaller than a preset threshold value or not;
And when the judging result of any one of the conditions is negative, judging the frame image as abnormal input and filtering the frame image.
3. The book in place detection method of claim 1, characterized in that said comparing said current image with said standard image comprises:
comparing the similarity of the pixel characteristics of the specific identifier in the current image and the standard image based on a difference hash algorithm;
determining that the book is in an unseated state for the current image meeting a first similarity standard;
extracting edge characteristics of the current image which does not accord with a first similarity standard by using an OTSU algorithm;
comparing the similarity of the edge characteristics of the specific marker in the current image and the standard image based on edge morphology;
the current in-place status of the book is determined based on the second similarity criteria.
4. A book in-place detection method according to any one of claims 1 to 3, further comprising:
before comparing the current image with the standard image, detecting brightness of the current image of each frame;
and carrying out brightness adjustment on the current image with abnormal brightness, and then comparing the current image with the current image.
5. A book in-place detection method according to any one of claims 1 to 3, further comprising:
dynamically updating the standard image according to the unset state detected in the process of the seated detection;
and detecting the book in-place state based on the updated standard image.
6. Book in-place detection device based on books auxiliary reading equipment, characterized by comprising:
the standard image presetting module is used for presetting a standard image of a target area in an imaging range based on a specific marker in a book unsetting state;
the anomaly detection module is used for carrying out anomaly input detection on the whole input image of each frame, and comprises the following steps: based on the whole image of each frame after edge detection, carrying out multi-stage abnormality detection according to a preset condition judgment sequence, and filtering if abnormal input is judged;
the current image acquisition module is used for acquiring a current image of the target area in each frame of image after filtering abnormal input;
the in-place state detection module is used for comparing the current image with the standard image to determine the current in-place state of the book, and comprises the steps of in-place detection from the view of image feature similarity and stage comparison: and selecting the characteristics based on all the pixel points from the image characteristics and comparing the characteristics with the edge characteristics successively.
7. The book in-place detection device of claim 6, characterized in that the device further comprises: a brightness detection module;
the brightness detection module specifically comprises:
the brightness detection unit is used for detecting the brightness of each frame of the current image before comparing the current image with the standard image;
and the brightness adjusting unit is used for adjusting the brightness of the current image with abnormal brightness.
8. The book in-place detection device of claim 6, characterized in that the device further comprises:
the standard image updating module is used for dynamically updating the standard image according to the unsetting state detected in the seated detection process;
the in-place state detection module is also used for detecting the in-place state of the book based on the updated standard image.
9. A book reading assisting apparatus, comprising:
one or more processors, memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions that, when executed by the device, cause the device to perform the book-in-place detection method based on the book-assisted reading device of any one of claims 1-5.
10. The book-assisted reading apparatus of claim 9, wherein the book-assisted reading apparatus is a book-drawing reader, and wherein a specific identifier for detecting a state of a book in place is provided on the book-drawing reader.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010295742.7A CN111598943B (en) | 2020-04-15 | 2020-04-15 | Book in-place detection method, device and equipment based on book auxiliary reading equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010295742.7A CN111598943B (en) | 2020-04-15 | 2020-04-15 | Book in-place detection method, device and equipment based on book auxiliary reading equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598943A CN111598943A (en) | 2020-08-28 |
| CN111598943B true CN111598943B (en) | 2023-07-11 |
Family
ID=72181418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010295742.7A Active CN111598943B (en) | 2020-04-15 | 2020-04-15 | Book in-place detection method, device and equipment based on book auxiliary reading equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598943B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419687B (en) * | 2020-11-16 | 2022-02-22 | 珠海格力电器股份有限公司 | Method capable of correcting placing angle of book on desk and reading equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2642446A2 (en) * | 2012-03-22 | 2013-09-25 | Sony Computer Entertainment Europe Limited | System and method of estimating page position |
| CN108509136A (en) * | 2018-04-12 | 2018-09-07 | 山东音为爱智能科技有限公司 | A kind of children based on artificial intelligence paint this aid reading method |
| CN110058705A (en) * | 2019-04-28 | 2019-07-26 | 视辰信息科技(上海)有限公司 | It draws this aid reading method, calculate equipment, point reading side apparatus and electronic equipment |
-
2020
- 2020-04-15 CN CN202010295742.7A patent/CN111598943B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2642446A2 (en) * | 2012-03-22 | 2013-09-25 | Sony Computer Entertainment Europe Limited | System and method of estimating page position |
| CN108509136A (en) * | 2018-04-12 | 2018-09-07 | 山东音为爱智能科技有限公司 | A kind of children based on artificial intelligence paint this aid reading method |
| CN110058705A (en) * | 2019-04-28 | 2019-07-26 | 视辰信息科技(上海)有限公司 | It draws this aid reading method, calculate equipment, point reading side apparatus and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 柳青 ; 熊邦书 ; 欧巧凤 ; .基于视频图像的点读机书本识别算法.制造业自动化.2012,(08),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598943A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| CN110414507B (en) | License plate recognition method and device, computer equipment and storage medium | |
| US7639878B2 (en) | Shadow detection in images | |
| CN108564579B (en) | Concrete crack detection method and detection device based on time-space correlation | |
| CN111680690B (en) | Character recognition method and device | |
| CN108875504B (en) | Image detection method and image detection device based on neural network | |
| CN111445459A (en) | Image defect detection method and system based on depth twin network | |
| CN111626295B (en) | Training method and device for license plate detection model | |
| CN110147708B (en) | Image data processing method and related device | |
| WO2021139197A1 (en) | Image processing method and apparatus | |
| CN112417955B (en) | Method and device for processing tour inspection video stream | |
| CN111783524A (en) | Scene change detection method and device, storage medium and terminal equipment | |
| WO2018133101A1 (en) | Image foreground detection apparatus and method, and electronic device | |
| CN108229583B (en) | Method and device for fast template matching based on main direction difference characteristics | |
| CN112651953A (en) | Image similarity calculation method and device, computer equipment and storage medium | |
| CN113661497A (en) | Matching method, matching device, electronic equipment and computer-readable storage medium | |
| CN113780484B (en) | Industrial product defect detection method and device | |
| CN114155285B (en) | Image registration method based on gray histogram | |
| CN111598943B (en) | Book in-place detection method, device and equipment based on book auxiliary reading equipment | |
| CN110765875B (en) | Method, equipment and device for detecting boundary of traffic target | |
| CN111402185B (en) | Image detection method and device | |
| CN109871779B (en) | Palm print identification method and electronic equipment | |
| CN111178200A (en) | Identification method of instrument panel indicator lamp and computing equipment | |
| CN114627113B (en) | Method, system, device and medium for detecting defects of printed circuit board | |
| CN112308061B (en) | License plate character recognition method and device |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 230001 6th and 23rd floors of scientific research building, building 2, zone a, China sound Valley, 3333 Xiyou Road, high tech Zone, Hefei, Anhui Province Applicant after: Anhui taoyun Technology Co.,Ltd. Address before: 230031 9th floor, building 1, tianyuandike science and Technology Park, 66 Qianshui East Road, high tech Zone, Hefei City, Anhui Province Applicant before: ANHUI TAOYUN TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |