Image analysis method, device and system for projector
Through projectors and image analysis methods, the similarity between the original and copied images is automatically evaluated, which solves the problem of low manual judgment efficiency and achieves more accurate and efficient painting skills improvement.
Patent Information
- Application Number
- CN202510315547.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-17
- Publication Date
- 2025-07-01
AI Technical Summary
In the prior art, the manual observation and evaluation methods in painting teaching are inefficient and rely on the professional ability of judges, resulting in inaccurate improvement of painting skills.
The projector combined with image analysis method is used to automatically evaluate the similarity between the original image and the copied image through edge detection and feature extraction, and use the server to perform image feature matching and European distance calculation to provide objective evaluation.
It improves the accuracy and efficiency of judging the difference in paintings, reduces the dependence on the professional ability of judges, and helps copyists improve their painting skills.
Smart Images
Figure CN120236090A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, for example, to an image analysis method, device, and system for a projector. Background Art
[0002] Currently, in the process of traditional painting teaching and training, improving the painting level of painters by copying excellent works and comparing the detailed differences between the original works and the copied works to further improve the copied works is an important method. Based on this, how to determine the detailed differences between the original works and the copied works has become a technical problem that urgently needs to be solved.
[0003] In order to determine the detailed differences between the original works and the copied works, in related technologies, painters compare and copy by printing paper-based excellent works or using small-screen devices such as mobile phones and tablets. After the painters finish copying, the method of manual observation and evaluation is used to determine the difference degree between the original works and the copied works.
[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in related technologies:
[0005] The method of manual observation and evaluation is inefficient and depends on the professional ability of the evaluators, which results in inaccurate evaluation results and is not conducive to painters improving their painting skills.
[0006] It should be noted that the information disclosed in the above background art section is only used to strengthen the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention
[0007] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. The summary is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments, but rather serves as a preamble to the subsequent detailed description.
[0008] The embodiments of the present disclosure provide an image analysis method, device, and system for a projector to improve the accuracy of evaluating the difference degree between the original works and the copied works, provide a more objective evaluation for painters, and improve the painting skills of painters.
[0009] In some embodiments, the method includes: obtaining an original image and a copied image; respectively performing edge detection on the original image and the copied image to obtain an intermediate original image and an intermediate copied image; respectively performing feature extraction on the intermediate original image and the intermediate copied image to obtain an original image feature and a copied image feature; and determining the similarity between the original image and the copied image according to the original image feature and the copied image feature.
[0010] In some embodiments, obtaining the original image and the traced image includes: receiving the original image stored locally in the cloud, and sending the original image to a projector to project the original image onto a projection interface; receiving the traced image obtained by the projector through a camera, where the traced image is projected onto the projection interface by the projector after determining that the tracer has finished tracing, and the projection position of the original interface is different from that of the traced image.
[0011] In some embodiments, feature extraction is respectively performed on the intermediate original image and the intermediate traced image to obtain the original image features and the traced image features, including: respectively performing target region segmentation on the intermediate original image and the intermediate traced image based on the optimal threshold method to determine the target original image and the target traced image; respectively extracting the shapes of the target original image and the target traced image and then performing normalization processing to obtain the normalized original image and the normalized traced image; respectively performing feature extraction on the normalized original image and the normalized traced image to obtain the original image feature vector and the traced image feature vector.
[0012] In some embodiments, based on the optimal threshold method, target region segmentation is performed on the intermediate image to determine the target image, including: determining the gray value range and probability density P(x) of the intermediate image, where P(x) represents the probability density of the gray level x, the gray value range is [0, L - 1], and L represents the number of gray levels; according to determining the foreground mean value of the intermediate image, and according to determining the background mean value of the intermediate image, where determining the threshold that satisfies the maximum between-class variance as the optimal threshold, where the between-class variance is determined by the foreground mean value and the background mean value; selecting the intermediate image that conforms to the optimal threshold as the target image.
[0013] In some embodiments, edge detection is respectively performed on the original image and the traced image to obtain the intermediate original image and the intermediate traced image, including: performing Gaussian filtering on the edge image of the image to be processed for denoising to obtain the denoised edge image; calculating the gradient of the denoised edge image to obtain the edge gradient of the denoised edge image; suppressing the edge gradient based on the non-maximum suppression algorithm to determine the target edge gradient of the denoised edge image; determining the target edge based on the double-threshold algorithm and the target edge gradient.
[0014] In some embodiments, based on the double-threshold algorithm and the target edge gradient, determining the target edge includes: determining the edge type according to the magnitude relationship between the edge gradient and the upper and lower threshold values of the edge gradient; performing edge connection according to the connection conditions of different edge types to determine the target edge.
[0015] In some embodiments, the edge types include strong edges, virtual edges, and weak edges. Edge connection is performed according to the connection conditions of different edge types to determine the target edges, including: determining the virtual edges connected to the strong edges as suspected edges; determining the virtual edges not connected to the strong edges as the second weak edges; suppressing all weak edges, and determining all strong edges and suspected edges as the target edges.
[0016] In some embodiments, determining the similarity between the original image and the traced image according to the original image features and the traced image features includes: calculating the Euclidean distance between the original image features and the traced image features; determining the Euclidean distance as the similarity between the original image and the traced image.
[0017] In some embodiments, the image analysis device includes a processor and a memory storing program instructions. The processor is configured to execute the image analysis method for the projector as described above when running the program instructions.
[0018] In some embodiments, the image analysis system includes: a projector; a server including the image analysis device for the projector as described above, and the server is communicatively connected to the projector.
[0019] The image analysis method, device, and system for the projector provided by the embodiments of the present disclosure can achieve the following technical effects:
[0020] In the embodiments of the present disclosure, the original image features and the traced image features are obtained by performing edge detection and feature extraction on the original image and the traced image in sequence, and the similarity between the original image and the traced image is evaluated based on the original image features and the traced image features. Compared with the method of manual observation and judgment, the above image comparison method has high evaluation efficiency and reduces the dependence on the professional ability of the judgment personnel, can significantly improve the accuracy of the difference judgment between the original work and the traced work, thereby providing a relatively objective evaluation to the tracer, which is beneficial to improving the painting skills of the tracer.
[0021] The above general description and the following description are only exemplary and explanatory, and are not used to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] One or more embodiments are exemplarily illustrated by the corresponding drawings. These exemplary illustrations and the drawings do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and among them:
[0023] Figure 1 is a schematic diagram of an image analysis system for a projector provided by an embodiment of the present disclosure;
[0024] Figure 2It is a schematic diagram of an image analysis method for a projector provided by an embodiment of the present disclosure;
[0025] Figure 3 It is a schematic diagram of another image analysis method for a projector provided by an embodiment of the present disclosure;
[0026] Figure 4 It is a schematic diagram of another image analysis method for a projector provided by an embodiment of the present disclosure;
[0027] Figure 5 It is a schematic diagram of another image analysis method for a projector provided by an embodiment of the present disclosure;
[0028] Figure 6 It is a schematic diagram of an application example of an embodiment of the present disclosure;
[0029] Figure 7 It is a schematic diagram of an image analysis device for a projector provided by an embodiment of the present disclosure. Detailed implementation manners
[0030] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are only for reference and illustration purposes and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, numerous details are provided to give a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be shown in a simplified manner to simplify the drawings.
[0031] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data may be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.
[0032] Unless otherwise specified, the term "plurality" means two or more.
[0033] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.
[0034] The term "and / or" is a description of the associated relationship of objects and indicates that three relationships may exist. For example, A and / or B means: A or B, or, the three relationships of A and B.
[0035] The term "corresponding" may refer to an association relationship or a binding relationship. That A corresponds to B means there is an association relationship or a binding relationship between A and B.
[0036] As shown in the combination Figure 1 The embodiments of the present disclosure provide an image analysis system for a projector, including a projector 100 and a server 200. The projector 100 is communicatively connected to the server 200. In the disclosed embodiments, the communicative connection may be through an Internet connection or through Bluetooth or Wi-Fi to communicate with the server. The specific communicative connection manner in the embodiments of the present disclosure may not be specifically limited.
[0037] Based on the above-mentioned image analysis system for a projector, in combination Figure 2 As shown, the embodiments of the present disclosure provide an image analysis method for a projector, including:
[0038] S01, the server obtains the original image and the traced image.
[0039] S02, the server respectively performs edge detection on the original image and the traced image to obtain an intermediate original image and an intermediate traced image.
[0040] S03, the server respectively performs feature extraction on the intermediate original image and the intermediate traced image to obtain the original image features and the traced image features.
[0041] S04, the server determines the similarity between the original image and the traced image according to the original image features and the traced image features.
[0042] By using the image analysis method for a projector provided by the embodiments of the present disclosure, in the embodiments of the present disclosure, after the server obtains the original image and the traced image, it respectively performs edge detection on the original image and the traced image to obtain an intermediate original image and an intermediate traced image. Then it respectively performs feature extraction on the intermediate original image and the intermediate traced image to obtain the original image features and the traced image features. Finally, the server determines the similarity between the original image and the traced image according to the original image features and the traced image features. The embodiments of the present disclosure obtain the original image features and the traced image features by sequentially performing edge detection and feature extraction on the original image and the traced image, and evaluate the similarity between the original image and the traced image based on the original image features and the traced image features. Compared with the method of manual observation and judgment, the above image comparison method has high evaluation efficiency and reduces the dependence on the professional ability of the judgment personnel, can significantly improve the accuracy of judging the difference between the original work and the traced work, thus providing a relatively objective evaluation for the tracer and being beneficial to improving the painting skills of the tracer.
[0043] It should be noted that in the embodiments of the present disclosure, edge detection is respectively performed on the original image and the traced image to obtain an intermediate original image and an intermediate traced image, and feature extraction is respectively performed on the intermediate original image and the intermediate traced image to obtain an original image feature and a traced image feature. Moreover, according to the original image feature and the traced image feature, determining the similarity between the original image and the traced image can be configured in the server in the form of an artificial intelligence computing model. In addition, in specific applications, the artificial intelligence computing model can be developed using the Java language or other languages.
[0044] Combined with Figure 3 As shown, the embodiments of the present disclosure also provide an image analysis method for a projector, including:
[0045] S11, the server receives the original image stored locally in the cloud, and sends the original image to the projector so that the projector projects the original image onto the projection interface. It should be noted that the projector can also obtain the original image locally from the projector.
[0046] S12, the server receives the traced image captured by the projector through the camera. Among them, the traced image is projected onto the projection interface by the projector after determining that the tracer has completed tracing, and the projection position of the original interface is different from the projection position of the traced image.
[0047] In this step, after the projector determines that the tracer has completed tracing, the traced image is projected onto the first side of the projection interface, and the projector projects the original image onto the second side of the projection interface. Among them, one of the first side and the second side is the left side, and the other is the right side. Here, the tracer can clearly know the details of the original image according to the projection interface, which is more helpful for image tracing. At the same time, during the tracing process, the traced image is also projected onto the projection interface, enabling the tracer to accurately know the differences between the traced image and the original image and the progress of the traced image, which is beneficial to improving the tracer's painting skills.
[0048] S13, the server respectively performs edge detection on the original image and the traced image to obtain an intermediate original image and an intermediate traced image.
[0049] S14, the server respectively performs feature extraction on the intermediate original image and the intermediate traced image to obtain an original image feature and a traced image feature.
[0050] S15, the server determines the similarity between the original image and the traced image according to the original image feature and the traced image feature.
[0051] The image analysis method for a projector provided by the embodiment of the present disclosure is adopted. In the embodiment of the present disclosure, the server receives the original image stored locally in the cloud, and sends the original image to the projector so that it projects the original image to the projection interface. By obtaining the original image through the cloud and transmitting it to the projector, the projector can obtain rich network resources. At the same time, the projection interface of the projector is relatively large. By projecting the original image through the projector, the copier can observe the details of the original work more clearly, and provide intelligent and convenient services to the copier. After the server receives the copy image obtained by the projector through the camera shooting, the original image and the copy image are successively detected and feature extracted to obtain the original image features and the copy image features, and the original image and the copy image are evaluated for similarity based on the original image features and the copy image features. The above-mentioned image comparison method has the characteristics of accuracy, speed and objectivity, and is highly consistent with the field of painting teaching. It can significantly improve the accuracy of the difference judgment between the original work and the copy work, thereby providing a more objective evaluation to the copier, which is conducive to improving the painting skills of the copier.
[0052] Optionally, combined Figure 4 As shown, the server extracts features from the intermediate original image and the intermediate copied image respectively to obtain features of the original image and features of the copied image, including:
[0053] S21, the server performs target region segmentation on the intermediate original image and the intermediate copied image respectively based on the optimal threshold method to determine the target original image and the target copied image.
[0054] S22, the server extracts the shapes of the target original image and the target copied image respectively and performs normalization processing thereon to obtain a normalized original image and a normalized copied image.
[0055] S23, the server performs feature extraction on the normalized original image and the normalized copied image respectively to obtain a feature vector of the original image and a feature vector of the copied image.
[0056] In this way, in the embodiments of the present disclosure, the server first performs target region segmentation on the intermediate original image and the intermediate copied image respectively based on the optimal threshold method, and determines the target original image with the maximum variance between the background and the foreground after image segmentation and the target copied image with the maximum variance between the background and the foreground after image segmentation. Then, the shapes of the target original image and the target copied image are extracted respectively and normalized to standardize the images. Finally, the server extracts features from the normalized original image and the normalized copied image respectively to obtain an original image feature vector that accurately reflects the features of the original image and a copied image feature vector that accurately reflects the features of the copied image. The above image analysis method can significantly improve the reliability and accuracy of feature extraction of the original work and the copied work, which is beneficial to further improving the accuracy of judging the difference between the original work and the copied work, and is more beneficial to improving the painting skills of the copier.
[0057] Optionally, performing target region segmentation on the intermediate image based on the optimal threshold method to determine the target image includes:
[0058] The server determines the gray value range and probability density P(x) of the intermediate image, where P(x) represents the probability density of the gray level x, and the gray value range is [0, L - 1], and L represents the number of gray levels.
[0059] The server determines the foreground mean of the intermediate image according to and determines the background mean of the intermediate image according to where
[0060] The server determines the threshold that satisfies the maximum between-class variance as the optimal threshold, where the between-class variance is determined by the foreground mean and the background mean.
[0061] Select the intermediate image that meets the optimal threshold as the target image.
[0062] In this way, after the embodiments of the present disclosure determine the gray value range and probability density of the intermediate image, they then determine the foreground mean of the intermediate image according to and determine the background mean of the intermediate image according to Finally, the threshold that satisfies the maximum between-class variance is determined as the optimal threshold. The embodiments of the present disclosure can obtain a clear target image through maximizing the background and foreground of the image after region segmentation, providing data support for the subsequent similarity evaluation of the original work and the copied work.
[0063] In a specific embodiment, the maximum between-class variance is where
[0064] As an example, when the intermediate image is the intermediate original image, the server determines the grayscale value range and the first probability density P(x) of the intermediate original image; the server determines the foreground mean of the intermediate original image according to and determines the background mean of the intermediate original image according to ; the server determines the threshold that satisfies the maximum between-class variance as the first optimal threshold, the between-class variance is determined by the foreground mean and the background mean of the intermediate original image, and the intermediate original image that meets the optimal threshold is selected as the target image.
[0065] As another example, when the intermediate image is the intermediate traced image, the server determines the grayscale value range and the second probability density P(x) of the intermediate traced image; the server determines the foreground mean of the intermediate traced image according to and determines the background mean of the intermediate traced image according to ; the server determines the threshold that satisfies the maximum between-class variance as the second optimal threshold, the between-class variance is determined by the foreground mean and the background mean of the intermediate traced image, and the intermediate traced image that meets the optimal threshold is selected as the target image.
[0066] Optionally, as shown in Figure 5 , the server performs edge detection on the original image and the traced image respectively to obtain the intermediate original image and the intermediate traced image, including:
[0067] S31, the server performs Gaussian filtering on the edge image of the image to be processed for denoising to obtain a denoised edge image.
[0068] S32, the server calculates the gradient of the denoised edge image to obtain the edge gradient of the denoised edge image.
[0069] S33, the server suppresses the edge gradient based on the non-maximum suppression algorithm to determine the target edge gradient of the denoised edge image.
[0070] In this step, the server suppresses the edge gradient based on the non-maximum suppression algorithm to determine the target edge gradient of the denoised edge image, including: the server determines each edge pixel point of the denoised edge image, and compares the edge gradient value of each edge pixel point with the edge gradient values of the pixel points adjacent to this edge pixel point along the gradient direction; if the edge gradient value of this edge pixel point is not a local maximum, the server sets the edge gradient value of this edge pixel point to the gradient critical value; where the gradient critical value can be zero.
[0071] S34, the server determines the target edge based on the double-threshold algorithm and the target edge gradient.
[0072] In this way, in the embodiments of the present disclosure, the server first performs Gaussian filtering on the edge image of the image to be processed to remove noise. For the denoised edge image, the positions of the image with large gradient intensity may be the edges of the image. Therefore, after obtaining the denoised edge image, the server calculates its gradient and obtains the edge gradient of the denoised edge image. To accurately locate the image edges, the server suppresses the edge gradient based on the non-maximum suppression algorithm and determines the target edge gradient of the denoised edge image to retain only the edge pixels with the largest edge gradient. Finally, the server determines the target edges based on the double-threshold algorithm and the target edge gradient, ensuring accurate and reliable target edges, further improving the accuracy of judging the difference between the original work and the copied work, and being more conducive to improving the painting skills of the copier.
[0073] Optionally, the server determines the target edges based on the double-threshold algorithm and the target edge gradient, including:
[0074] The server determines the edge type according to the magnitude relationship between the edge gradient and the upper and lower threshold values of the edge gradient.
[0075] The server performs edge connection according to the connection conditions of different edge types to determine the target edges.
[0076] In this way, accurate and reliable target edges are ensured, further improving the accuracy of judging the difference between the original work and the copied work, and being more conducive to improving the painting skills of the copier.
[0077] In a specific example, the server determines the edge type according to the magnitude relationship between the edge gradient and the upper and lower threshold values of the edge gradient, including:
[0078] The server determines that the edge points with edge gradient greater than the upper threshold value of the edge gradient are strong edges.
[0079] The server determines that the edge points with edge gradient greater than or equal to the lower threshold value of the edge gradient and less than or equal to the upper threshold value of the edge gradient are virtual edges.
[0080] The server determines that the edge points with edge gradient less than the lower threshold value of the edge gradient are the first weak edges.
[0081] In this way, in the embodiments of the present disclosure, it is determined that the edge points with edge gradient greater than the upper threshold value of the edge map are strong edges, and it is determined that the edge points with edge gradient greater than or equal to the lower threshold value of the edge gradient and less than or equal to the upper threshold value of the edge gradient are virtual edges. At the same time, it is determined that the edge points with edge gradient less than the lower threshold value of the edge gradient are the first weak edges. Through the comparison of the edge gradient with the gradient threshold values in the embodiments of the present disclosure, the image edges can be accurately classified, ensuring accurate and reliable target edges.
[0082] Optionally, the edge types include strong edges, virtual edges, and weak edges. The server performs edge connection based on the connection conditions of different edge types to determine the target edge, including:
[0083] The server determines that the virtual edge connected to the strong edge is a suspected edge.
[0084] The server determines that the virtual edge not connected to the strong edge is the second weak edge.
[0085] The server suppresses all weak edges and determines that all strong edges and suspected edges are target edges. Among them, the weak edges include the first weak edge and the second weak edge.
[0086] In this way, the embodiments of the present disclosure can further determine the target edge according to the connection conditions of different edge types. At the same time, all weak edges are suppressed. It is beneficial to obtain accurate and reliable target edges, further improve the accuracy of judging the difference between the original work and the copied work, and is more conducive to improving the painting skills of the copier.
[0087] Optionally, the server determines the similarity between the original image and the copied image according to the original image features and the copied image features, including:
[0088] The server calculates the Euclidean distance between the original image features and the copied image features.
[0089] The server determines that the Euclidean distance is the similarity between the original image and the copied image.
[0090] In this way, the Euclidean distance is used to measure the absolute distance between two points in a multi-dimensional space. When applying the Euclidean distance to image analysis, the Euclidean distance can be used to compare the similarity between the original image and the copied image. In similarity calculation, the smaller the Euclidean distance, the more similar the original image and the copied image are. The larger the Euclidean distance, the greater the difference between the original image and the copied image. The embodiments of the present disclosure calculate the Euclidean distance between the original image features and the copied image features and perform similarity calculation, which can know the similarity degree between the original image and the copied image, so as to obtain a relatively objective evaluation, and is beneficial to improving the painting skills of the copier.
[0091] As an example, the server calculates the Euclidean distance between the original image features and the copied image features, including:
[0092] The Euclidean distance is
[0093] where F1(i) and F2(i) respectively represent the original image feature vector and the copied image feature vector, and n represents the dimension of the original image feature vector and the copied image feature vector.
[0094] Understandably, after the server determines the similarity between the original image and the copied image based on the original image features and the copied image features, it further includes: the server outputs the similarity.
[0095] In practical applications, as shown in Figure 6 The image analysis method for a projector specifically includes the following steps:
[0096] S41, the server receives the original image stored locally in the cloud or locally in the projector, and sends the original image to the projector so that the projector projects the original image onto the projection interface.
[0097] S42, the server receives the copied image captured by the camera of the projector. Among them, the copied image is projected onto the left side of the projection interface by the projector after determining that the copier has finished copying, and the projection position of the original interface is on the right side of the projection interface.
[0098] S43, the server performs edge detection on the original image and the copied image respectively to obtain the intermediate original image and the intermediate copied image.
[0099] S44, the server performs target region segmentation on the intermediate original image and the intermediate copied image respectively based on the optimal threshold method to determine the target original image and the target copied image.
[0100] S45, the server extracts the shapes of the target original image and the target copied image respectively and then performs normalization processing to obtain the normalized original image and the normalized copied image.
[0101] S46, the server performs feature extraction on the normalized original image and the normalized copied image respectively to obtain the original image feature vector and the copied image feature vector.
[0102] S47, the server calculates the Euclidean distance between the original image feature vector and the copied image feature vector, and determines it as the similarity between the original image and the copied image.
[0103] As shown in Figure 7 The present disclosure provides an image analysis device 70 for a projector, including a processor 700 and a memory 701. Optionally, the device 70 may further include a communication interface 702 and a bus 703. Among them, the processor 700, the communication interface 702, and the memory 701 can complete mutual communication through the bus 703. The communication interface 702 can be used for information transmission. The processor 700 can call the logical instructions in the memory 701 to execute the image analysis method for a projector in the above embodiment.
[0104] In addition, when the logical instructions in the above-mentioned memory 701 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
[0105] As a computer-readable storage medium, the memory 701 can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 700 executes functional applications and data processing by running the program instructions / modules stored in the memory 701, that is, implements the image analysis method for the projector in the above embodiments.
[0106] The memory 701 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory 701 may include high-speed random access memory and may also include non-volatile memory.
[0107] The embodiments of the present disclosure provide an image analysis system, including: a projector; a server, including the image analysis device for the projector as described above, and the server is communicatively connected to the projector.
[0108] It should be noted that the image analysis device for the projector can be configured in the server in the form of an artificial intelligence computing model. In a specific application, after the server obtains the original image and the copied image, it can determine the similarity between the original image and the copied image based on the artificial intelligence computing model.
[0109] The embodiments of the present disclosure provide a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are set to execute the above-mentioned image analysis method for the projector.
[0110] The technical solution of the embodiments of the present disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The foregoing storage medium may be a non-transitory storage medium, such as: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which are various media that can store program codes.
[0111] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments only represent possible variations. Unless explicitly required, the individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups of these. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. Herein, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the various embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.
[0112] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.
[0113] In the embodiments disclosed in this article, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.
[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the block can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in a different order than that disclosed in the description. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
Claims
1. An image analysis method for a projector, characterized in that: include: Obtaining original images and copied images; Perform edge detection on the original image and the copied image respectively to obtain an intermediate original image and an intermediate copied image; Extract features from the intermediate original image and the intermediate copied image respectively to obtain features of the original image and features of the copied image; According to the features of the original image and the features of the copied image, the similarity between the original image and the copied image is determined.
2. The method according to claim 1, characterized in that Get the original image and the copied image, including: Receiving the original image stored locally in the cloud, and sending the original image to the projector so that the projector projects the original image onto the projection interface; A copying image obtained by the projector through the camera is received, wherein the copying image is projected onto the projection interface by the projector after it is determined that the copier has finished copying, and the projection position of the original interface is different from the projection position of the copying image.
3. The method according to claim 1, characterized in that: Feature extraction is performed on the intermediate original image and the intermediate copy image respectively to obtain the original image features and the copy image features, including: Based on the optimal threshold method, target regions are segmented on the intermediate original image and the intermediate copied image respectively to determine the target original image and the target copied image; The shapes of the target original image and the target copied image are respectively extracted and then normalized to obtain a normalized original image and a normalized copied image; Feature extraction is performed on the normalized original image and the normalized copied image respectively to obtain the feature vector of the original image and the feature vector of the copied image.
4. The method according to claim 3, characterized in that The target area of the intermediate image is segmented based on the optimal threshold method to determine the target image, including: Determine the grayscale value range and probability density P(x) of the intermediate image, where P(x) represents the probability density of grayscale level x, the grayscale value range is [0, L-1], and L represents the number of grayscale levels; according to Determine the foreground mean of the intermediate image and use Determine the background mean of the intermediate image, where Determine the threshold that satisfies the maximum inter-class variance as the optimal threshold, where the inter-class variance is determined by the foreground mean and the background mean; The intermediate image that meets the optimal threshold is selected as the target image.
5. The method according to claim 1, characterized in that Perform edge detection on the original image and the copied image respectively to obtain an intermediate original image and an intermediate copied image, including: Performing Gaussian filtering on the edge image of the image to be processed to perform denoising processing, thereby obtaining a denoised edge image; Performing gradient calculation on the denoised edge image to obtain the edge gradient of the denoised edge image; The edge gradient is suppressed based on the non-maximum suppression algorithm to determine the target edge gradient of the denoised edge image; The target edge is determined based on the double threshold algorithm and the target edge gradient.
6. The method according to claim 5, characterized in that Based on the dual threshold algorithm and the target edge gradient, the target edge is determined, including: Determine the edge type based on the relationship between the edge gradient and the upper and lower thresholds of the edge gradient; Edge connections are performed based on the connection conditions of different edge types to determine the target edge.
7. The method according to claim 6, characterized in that Edge types include strong edges, virtual edges, and weak edges. Edge connections are performed based on the connection conditions of different edge types to determine the target edge, including: Determine the virtual edge connected to the strong edge as a suspected edge; Determine the virtual edge that is not connected to the strong edge as the second weak edge; All weak edges are suppressed, and all strong edges and suspected edges are determined to be target edges.
8. The method according to any one of claims 1 to 7, characterized in that: According to the features of the original image and the copied image, the similarity between the original image and the copied image is determined, including: Calculate the Euclidean distance between the original image features and the copied image features; The Euclidean distance is determined as the similarity between the original image and the copied image.
9. An image analysis device for a projector, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the image analysis method for a projector according to any one of claims 1 to 8 when running the program instructions.
10. An image analysis system for a projector, characterized in that: include: Projector; The server comprises the image analysis device for a projector as claimed in claim 9, and the server is communicatively connected with the projector.