CN108234868B - Intelligent shooting system and method based on case reasoning - Google Patents

Abstract

The invention discloses an intelligent shooting system and method based on case reasoning, including an image acquisition module, a RAM module, an analysis processing module and a case library module; the image acquisition module acquires a target preview image and caches it in the RAM module, and then The analysis and processing module retrieves the target preview image and performs target subject feature encoding and target mapping relationship encoding. Finally, the case library module calculates the similarity between the target subject feature encoding and the source case subject feature encoding, and calculates the target mapping relationship encoding and source code. The similarity of the case mapping relationship is encoded, and the shooting angle with the highest similarity is selected for intelligent shooting composition. The invention uses the algorithm intelligence in the analysis processing module to obtain the relevant feature information of the target image, and based on the case reasoning, uses the algorithm intelligence in the case library module to recommend the best shooting angle for the user, and solves the problem that the mobile phone shooting system in the prior art cannot guide the The defect of the user's adjustment of the shooting angle.

Description

An intelligent shooting system and method based on case reasoning

technical field

The present invention relates to the technical field of mobile phone shooting, and more particularly, to an intelligent shooting system and method based on case reasoning.

Background technique

Mobile phone shooting has functions such as face recognition, focusing, scene selection, and beauty, and the pixel is getting higher and higher. At present, the mobile phone shooting system can also set shooting reference lines to help users shoot. However, in order to take high-quality photos, users need to understand professional photography techniques, and most users do not understand these skills; at present, the mobile phone shooting system automatically recognizes the positional relationship between the characters and the background based on the preview photos. The relative shooting angle of the background is often determined by the user based on his own experience, and the quality of the photos taken by the user is not high due to the lack of experience. Therefore, a system that can guide the user to adjust the shooting angle is needed to facilitate the user to shoot High quality photos.

SUMMARY OF THE INVENTION

In view of this, the present invention provides an intelligent shooting system and method based on case reasoning, which solves the defect in the prior art that the mobile phone shooting system cannot guide the user to adjust the shooting angle.

For achieving the above object, the present invention provides the following technical solutions:

An intelligent shooting system based on case reasoning includes an image acquisition module, a RAM module, an analysis processing module and a case library module; wherein, the image acquisition module is used for acquiring a camera preview image; the RAM module is used for caching The preview image; the analysis and processing module analyzes the background of the preview image, determines the image subject and the background, their mapping relationship, and the relevant attributes of the subject; the analysis and processing module specifically includes a focus acquisition unit, a feature analysis unit, a mapping a relationship unit and a feature encoding unit; the focus acquisition unit, which acquires the focus position and determines the image subject; the feature analysis unit, which acquires the characteristics of the image subject; the mapping relationship unit, which determines the mapping relationship between the image background and the shooting subject; the The feature encoding unit encodes the main features of the image and the mapping relationship.

The case library module is used for storing image subject attribute information and composition information, and also for attribute similarity matching; the case library module specifically includes a coding acquisition unit, a similarity matching unit and a source case storage unit; the coding The acquisition unit is used to obtain the feature code and the mapping relationship code; the similarity matching unit performs similarity matching calculation on the subject feature of the target case and the subject feature of the source case, then performs the similarity matching calculation on the mapping relationship, and finally outputs the shooting angle, To guide the user to adjust the shooting angle; the source case storage unit is used to store the source case, including the source case set by the system and the source case added by the user;

The image acquisition module acquires a preview photo, and stores the preview photo in the RAM module; then the focus acquisition unit retrieves the preview photo stored in the RAM module and determines the main body of the image; then the feature analysis The unit retrieves the image subject information in the focus acquisition unit and determines the image subject feature according to the image subject; then the mapping relationship unit retrieves the image subject feature information of the feature analysis unit to determine the mapping between the image background and the image subject Then the feature encoding unit calls the image subject feature information of the feature analysis unit on the one hand for encoding, and on the other hand calls the mapping relationship information between the image background of the mapping relationship unit and the image subject for encoding; Then the code acquisition unit calls the target feature code and the target mapping relationship code in the feature encoding unit and transmits the feature code and the mapping relationship code to the similarity matching unit; then the similarity matching unit calls The source case subject feature code and the source case mapping relationship code stored in the source case storage unit, the target case subject feature code and the source case subject feature code are subjected to subject feature similarity matching calculation, and the target case mapping relationship code is mapped to the source case. The relationship coding performs mapping relationship similarity matching calculation, and retrieves and outputs the most similar source case subject feature information and mapping relationship information in the source case storage unit according to the subject feature similarity matching calculation result and the mapping relationship similarity matching calculation result, and The main feature information of the source case is replaced and integrated into the mapping relationship information of the source case, so as to obtain the closest shooting angle of the source case, and the newly integrated closest source case is retrieved and output to guide the user to adjust the shooting angle. The source case storage unit retrieves the target feature code and the target mapping relationship code in the code acquisition unit, and saves the target feature code and the target mapping relationship code as the feature code and the mapping relationship code of the newly added source case.

Preferably, the algorithm used by the focus acquisition unit is g(i,j)=sqrt((f(i,j)-f(i+1,j))^2+(f(i+1,j)-f (i,j+1))^2), where f(i-1,j-1), f(i-1,j), f(i-1,j+1), f(i,j -1), f(i,j), f(i,j+1), f(i+1,j-1), f(i+1,j), f(i+1,j+1) All are image pixels to be processed, and g(i, j) is the processed pixel.

其中，X为目标主体，Y为源案例主体，目标主体X和源案例主体Y均包含了N维特征，即X＝(x1,x2,x3,……,xn)，Y＝(y1,y2,y3,……,yn)，算法中的余弦值越小则相似度越高。Preferably, the algorithm of the similarity matching unit is

Among them, X is the target subject, Y is the source case subject, and both the target subject X and the source case subject Y contain N-dimensional features, that is, X=(x1,x2,x3,...,xn), Y=(y1,y2 ,y3,...,yn), the smaller the cosine value in the algorithm, the higher the similarity.

An intelligent shooting method based on case reasoning is characterized in that: it includes the following steps: step 1, obtaining a camera preview image, after a user performs a focusing operation, intercepting and buffering the preview image; step 2, analyzing the background of the preview image, Determine the image subject and background, their mapping relationship, the attributes of the subject, and encode them; Step 3, prompt the user whether the source case is needed: if the user needs the source case, go to step 4; if the user does not need the source case, click in the interface Display the cancel case button, complete the composition by yourself, and go to step 8; step 4, search the case library, match with the target case, and output the best source case subject feature information and the mapping relationship between the best source case subject and the background respectively. information; step 5, replace and integrate the feature information of the best source case subject into the mapping relationship information between the best source case subject and the background to form a new best source case; step 6, display the new best source case on the shooting interface The best source case body contour; Step 7, according to the source case body contour, the user manually adjusts the angle as much as possible to make the target body contour coincide with the source case body contour; Step 8, trigger the shooting button to complete the shooting, save the image and prompt the user whether to save this Subject attribute features and subject and background mapping relationships are used as source cases.

Preferably, this step 2 includes the following execution process: a. Determine the basic position of the target image subject through the focusing operation, and use the edge detection method to determine the outline of the target subject; b. Use the SIFT algorithm to extract the feature attributes of the target image subject; c. Determine The mapping relationship between the target image background and the target shooting subject; d. Encoding the target subject feature and the target mapping relationship for case similarity calculation.

Preferably, the algorithm formula of the edge detection method is g(i,j)=sqrt((f(i,j)-f(i+1,j))^2+(f(i+1,j)- f(i,j+1))^2), where f(i-1,j-1), f(i-1,j), f(i-1,j+1), f(i, j-1), f(i,j), f(i,j+1), f(i+1,j-1), f(i+1,j), f(i+1,j+1 ) are the image pixels to be processed, and g(i, j) are the processed pixels.

Preferably, the steps of the SIFT algorithm include: a. first constructing a scale space, detecting extreme points, and obtaining scale invariance; b. then filtering extreme value feature points and performing precise positioning; c. then assigning extreme value feature points Direction value; d. Finally generate a feature descriptor.

Preferably, this step 4 includes the following execution processes: a. obtaining the feature code and the mapping relationship code; b. calculating the similarity between the target case subject feature code and the source case subject feature code, according to the set threshold, the pre-stored similarity is high c. Calculate the similarity of the mapping relationship for the source cases with high feature similarity, and output the shooting angle corresponding to the highest similarity of the mapping relationship.

It can be seen from the above technical solutions that, on the one hand, the present invention uses the focus acquisition unit to retrieve the preview target image information, then uses the feature analysis unit to analyze and filter out the feature information of the target case subject, and uses the mapping relationship unit to analyze and filter the relationship between the target subject and the background. Then use the feature coding unit to encode the target case subject feature information and mapping relationship information, which is convenient for system record identification, and then use the similarity matching unit in the case library module to call the source case storage unit. information, perform subject feature similarity matching calculation between the target case subject feature coding and the source case subject feature coding, and perform the mapping relationship similarity matching calculation between the target case mapping relationship coding and the source case mapping relationship coding, and calculate based on the subject feature similarity matching calculation. The result and the mapping relationship similarity matching calculation result retrieve and output the most similar source case subject feature information and mapping relationship information in the source case storage unit, and replace and integrate the source case subject feature information into the source case mapping relationship information, thereby Obtain the most similar shooting angle of the source case, and output the shooting angle in the source case to the interface to guide the user to adjust the shooting angle in time, so that the contour of the target subject and the subject contour of the source case basically coincide, so as to intelligently guide the user to adjust the shooting angle On the other hand, the present invention uses the feature analysis unit to analyze and filter out the feature information of the target case subject, and uses the mapping relationship unit to analyze and filter the mapping relationship information between the target subject and the background, so that the feature information in the target image is filtered out of the subject. Based on case reasoning, the main feature similarity matching calculation and the subject and background mapping relationship feature similarity matching calculation are carried out respectively through the case library module, which overcomes the problem caused by the feature similarity matching calculation of the overall image. The matching accuracy is low and the matching error is large, thereby improving the matching accuracy between the target case and the source case.

Description of drawings

FIG. 1 is a system schematic diagram of an intelligent shooting system and method based on case reasoning provided by an embodiment of the present invention.

FIG. 2 is a schematic diagram of a case-based reasoning-based intelligent shooting system and method according to an embodiment of the present invention.

Description of drawings:

10-image acquisition module; 20-RAM module; 30-analysis processing module; 40-case library module; 31-focus acquisition unit; 32-feature analysis unit; 33-mapping relationship unit; 34-feature encoding unit; 41-feature acquisition unit; 42-similarity matching unit; 43-source case storage unit.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only For some embodiments of the present invention, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

Detailed ways

Embodiments of the present invention provide an intelligent shooting system and method based on case reasoning.

As shown in Figures 1-2, an intelligent shooting system based on case reasoning includes an image acquisition module 10, a RAM module 20, an analysis processing module 30 and a case library module 40; wherein, the image acquisition module 10 is used for The camera preview image is obtained; the RAM module 20 is used to cache the preview image; the analysis processing module 30 analyzes the background of the preview image, and determines the image subject and the background, their mapping relationship, and the relevant attributes of the subject; the The analysis processing module 30 specifically includes a focus acquisition unit 31, a feature analysis unit 32, a mapping relationship unit 33 and a feature encoding unit 34; the focus acquisition unit 31 acquires the focus position and determines the image subject; the feature analysis unit 32 acquires Image subject features; the mapping relationship unit 33 determines the mapping relationship between the image background and the shooting subject; the feature encoding unit 34 encodes the image subject features and the mapping relationship. The case library module 40 is used for storing image subject attribute information and composition information, and also for attribute similarity matching; the case library module 40 specifically includes a coding acquisition unit, a similarity matching unit 42 and a source case storage unit 43 The coding acquisition unit is used to obtain the feature coding and the mapping relationship coding; the similarity matching unit 42 performs similarity matching calculation with the target case subject feature and the source case subject feature, and then carries out the mapping relationship similarity matching calculation, Finally, output the shooting angle to guide the user to adjust the shooting angle; the source case storage unit 43 is used to store the source case, including the source case set by the system and the source case added by the user; in the embodiment of the present invention, the image The acquisition module 10 is an existing integrated camera assembly, and its purpose is to acquire the target image. The user can select the image acquisition module 10 with different pixels according to actual needs, which can mainly ensure the smooth acquisition of the target image. Similarly, the RAM module 20 The purpose of the RAM is to cache target image information. Therefore, the RAM module 20 may include a memory stick in the prior art, or may include other storage electronic devices, which can mainly achieve the purpose of caching the target image. In addition, the source case storage unit 43 may include a database or a cloud platform, or may be other removable storage devices, the purpose of which is to save the source case file information.

The overall working principle of the present invention is: first obtain the target image through the image acquisition module 10, and then obtain the target image subject feature encoding of the target image and the mapping relationship encoding between the target image subject and the background through the analysis processing module 30; , through the similarity matching unit 42, on the one hand, the target image subject feature encoding information and the source case image subject feature encoding information in the source case storage unit 43 are retrieved and the similarity matching is performed, and the most similar source case image is found from the source case. On the other hand, the coding information of the mapping relationship between the subject of the target image and the background and the coding information of the mapping relationship between the subject and the background of the source case are retrieved, and the similarity matching is performed to find out from the source case. The mapping relationship between the most similar source case subject and the background encodes the information and displays it, and finally guides the user to adjust the shooting angle to take high-quality photos.

Correspondingly, the algorithm used by the focus acquisition unit 31 is g(i,j)=sqrt((f(i,j)-f(i+1,j))^2+(f(i+1,j)- f(i,j+1))^2), where f(i-1,j-1), f(i-1,j), f(i-1,j+1), f(i, j-1), f(i,j), f(i,j+1), f(i+1,j-1), f(i+1,j), f(i+1,j+1 ) are the image pixels to be processed, and g(i, j) are the processed pixels. In the algorithm of the focus acquisition unit 31, N*N pixel blocks are often used, such as 3*3 or 4*4. The 3*3 pixel blocks are as follows, f(i-1, j-1), f(i- 1,j), f(i-1,j+1), f(i,j-1), f(i,j), f(i,j+1), f(i+1,j-1 )f(i+1,j) and f(i+1,j+1), use the pixel information of each pixel block to take its relative threshold, because there is often a large difference between the contour of the image main body and the image background. value, scan out each pixel point in the image by array scanning, and compare it with the relative threshold value, if the existence of the two is larger, it is judged that this is the contour point, through this cyclic array scanning method, you can quickly get The contour information of the target image is extracted and the contour of the target image is extracted. The purpose here is to extract the main contour feature information of the target image on the one hand, and to extract the background pixel information in the target image on the other hand, so as to achieve the main body of the target image. The feature information of the mapping relationship between the contour and the background.

其中，X为目标主体，Y为源案例主体，目标主体X和源案例主体Y均包含了N维特征，即X＝(x1,x2,x3,……,xn)，Y＝(y1,y2,y3,……,yn)，算法中的余弦值越小则相似度越高。由于在焦点获取单元31中已提取出目标图像的主体轮廓特征信息以及目标图像的主体轮廓与背景之间的映射关系特征信息，通过整合目标图像的主体轮廓特征信息，利用相似度匹配单元42中的算法，对目标图像主体轮廓特征信息与源案例主体轮廓特征信息进行一一相似度匹配，从源案例储存单元43中找出相似度最高的源案例主体轮廓；然后整合目标图像的主体轮廓与背景之间的映射关系特征信息，利用相似度匹配单元42中的算法，对目标图像映射关系息与源案例映射关系特征信息进行一一相似度匹配，从源案例储存单元43中找出相似度最高的源案例映射关系信息，然后相似度匹配单元42再将匹配出来的源案例主体轮廓整合到源案例中映射关系最强的背景源图像中并将整合后的源图像作为指导图像，用于指导用户调整拍摄角度。In this embodiment of the present invention, the algorithm of the similarity matching unit 42 is:

Among them, X is the target subject, Y is the source case subject, and both the target subject X and the source case subject Y contain N-dimensional features, that is, X=(x1,x2,x3,...,xn), Y=(y1,y2 ,y3,...,yn), the smaller the cosine value in the algorithm, the higher the similarity. Since the subject contour feature information of the target image and the mapping relationship feature information between the subject contour and the background of the target image have been extracted in the focus acquisition unit 31, by integrating the subject contour feature information of the target image, using the similarity matching unit 42 Algorithm, the main body contour feature information of the target image and the source case body contour feature information are matched one-to-one, and the source case body contour with the highest similarity is found from the source case storage unit 43; then the main body contour of the target image is integrated with For the feature information of the mapping relationship between the backgrounds, use the algorithm in the similarity matching unit 42 to perform a one-to-one similarity matching between the mapping relationship information of the target image and the feature information of the mapping relationship of the source case, and find the similarity from the source case storage unit 43 The highest source case mapping relationship information, and then the similarity matching unit 42 integrates the matched source case body outline into the background source image with the strongest mapping relationship in the source case and uses the integrated source image as a guide image for use. Instruct the user to adjust the shooting angle.

The working process of the embodiment of the present invention is as follows: the image acquisition module 10 acquires a preview photo, and stores the preview photo in the RAM module 20; and determine the image subject; then the feature analysis unit 32 retrieves the image subject information in the focus acquisition unit 31 and determines the image subject feature according to the image subject; then the mapping relationship unit 33 retrieves the feature analysis The image subject feature information of the unit 32 determines the mapping relationship between the image background and the image subject; then the feature encoding unit 34 retrieves the image subject feature information of the feature analysis unit 32 for encoding on the one hand, and retrieves the data on the other hand. The mapping relationship information between the image background and the image main body of the mapping relationship unit 33 is encoded; then the encoding acquisition unit calls the target feature encoding and the target mapping relationship encoding in the feature encoding unit 34 and encodes the feature with the mapping The relationship code is transmitted to the similarity matching unit 42; then the similarity matching unit 42 retrieves the source case subject feature code and the source case mapping relationship code stored in the source case storage unit 43, and combines the target case subject feature code with the source case subject feature code. The source case subject feature code performs the subject feature similarity matching calculation, and performs the mapping relationship similarity matching calculation between the target case mapping relationship coding and the source case mapping relationship coding, and calculates the similarity matching calculation result according to the subject feature similarity matching calculation result and the mapping relationship similarity matching calculation result. Retrieve and output the most similar source case shooting angle in the source case storage unit 43 to guide the user to adjust the shooting angle; finally, the source case storage unit 43 calls the target feature code and target mapping in the code acquisition unit Relation encoding, and will save the target feature encoding and target mapping relation encoding as the feature encoding and mapping relation encoding of the newly added source case.

An intelligent shooting method based on case reasoning is characterized in that: it includes the following steps: step 1, obtaining a camera preview image, after a user performs a focusing operation, intercepting and buffering the preview image; step 2, analyzing the background of the preview image, Determine the image subject and background, their mapping relationship, the attributes of the subject, and encode them; Step 3, prompt the user whether the source case is needed: if the user needs the source case, go to step 4; if the user does not need the source case, click in the interface Display the cancel case button, complete the composition by yourself, and go to step 8; step 4, search the case library, match with the target case, and output the best source case subject feature information and the mapping relationship between the best source case subject and the background respectively. information; step 5, replace and integrate the feature information of the best source case subject into the mapping relationship information between the best source case subject and the background to form a new best source case; step 6, display the new best source case on the shooting interface The best source case body contour; Step 7, according to the source case body contour, the user manually adjusts the angle as much as possible to make the target body contour coincide with the source case body contour; Step 8, trigger the shooting button to complete the shooting, save the image and prompt the user whether to save this Subject attribute features and subject and background mapping relationships are used as source cases.

Specifically, this step 2 includes the following execution process: a. Determine the basic position of the target image subject through the focusing operation, and use the edge detection method to determine the outline of the target subject; b. Use the SIFT algorithm to extract the feature attributes of the target image subject; c. Determine The mapping relationship between the target image background and the target shooting subject; d. Encode the target subject feature and the target mapping relationship for case similarity calculation; the algorithm formula of the edge detection method is g(i,j)=sqrt((f (i,j)-f(i+1,j))^2+(f(i+1,j)-f(i,j+1))^2), where f(i-1,j -1), f(i-1,j), f(i-1,j+1), f(i,j-1), f(i,j), f(i,j+1), f (i+1,j-1), f(i+1,j), f(i+1,j+1) are all image pixels to be processed, and g(i,j) is the processed pixel; the SIFT The algorithm steps include: a. firstly constructing a scale space, detecting extreme point points, and obtaining scale invariance; b. then filtering extreme value feature points and performing precise positioning; c. then assigning direction values to extreme value feature points; d. Finally, a feature descriptor is generated; this step 4 includes the following execution processes: a. Obtaining the feature code and the mapping relationship code; b. Calculating the similarity between the target case subject feature code and the source case subject feature code, and pre-stored according to the set threshold Multiple source cases with high similarity; c. Perform mapping relationship similarity calculation on source cases with high feature similarity, and output the shooting angle corresponding to the highest mapping relationship similarity.

As can be seen from the above technical solutions, on the one hand, the present invention uses the focus acquisition unit 31 to retrieve the preview target image information, then uses the feature analysis unit 32 to analyze and filter out the feature information of the target case subject, and uses the mapping relationship unit 33 to analyze and filter the target subject and the mapping relationship information between the background, and then use the feature encoding unit 34 to encode the target case subject feature information and the mapping relationship information, so as to facilitate the identification of system records, and then use the similarity matching unit 42 in the case library module 40 to retrieve the source For the storage information in the case storage unit 43, the subject feature similarity matching calculation is performed on the target case subject feature coding and the source case subject feature coding, and the mapping relationship similarity matching calculation is performed on the target case mapping relationship coding and the source case mapping relationship coding, The closest source case shooting angle in the source case storage unit 43 is retrieved and output according to the subject feature similarity matching calculation result and the mapping relationship similarity matching calculation result, and the shooting angle in the source case is output to the interface for guidance The user adjusts the shooting angle in time, so that the contour of the target subject and the subject contour of the source case basically overlap, so as to achieve the purpose of intelligently guiding the user to adjust the shooting angle; The mapping relationship unit 33 analyzes and filters the mapping relationship information between the target subject and the background, so that the feature information in the target image is filtered out the subject feature and the subject and the background mapping relationship feature, and the case library module 40 respectively performs the subject feature similarity matching calculation. The feature similarity matching calculation of the mapping relationship between the subject and the background overcomes the defects of low matching accuracy and large matching error caused by the feature similarity matching calculation of the overall image, thereby improving the matching accuracy between the target case and the source case. Therefore, the advantages of the present invention are: 1. By extracting the subject feature of the preview image, the mapping relationship between the subject feature and the background is analyzed, so that the matching accuracy is higher; 2. Based on the principle of case reasoning, the similarity and mapping relationship of the subject feature are matched 3. Based on the user's shooting position, the system provides the user with the optimal shooting angle, without requiring the user to adjust the shooting angle and position in a large range; 4. The system displays the main outline of the source case on the same screen , the user can complete the adjustment of the shooting angle by making the subject overlap, and at the same time display the degree of coincidence (and similarity), making the adjustment of the shooting angle more convenient and quick; 5. The user can add a source case to make the source case resources more complete, making the subject Adapt to more shooting adjustment angles.

The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the various embodiments can be referred to each other.

The above description of the disclosed embodiments enables those skilled in the art to practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (7)

1. An intelligent shooting system based on case-based reasoning is characterized in that: the system comprises an image acquisition module, an RAM module, an analysis processing module and a case library module; wherein,

the image acquisition module is used for acquiring a camera preview;

the RAM module is used for caching the preview image;

the analysis processing module is used for analyzing the preview image background and determining an image main body, the background, the mapping relation of the image main body and the background and the related attributes of the image main body; the analysis processing module specifically comprises a focus acquisition unit, a feature analysis unit, a mapping relation unit and a feature coding unit; the focus acquisition unit acquires a focus position and determines an image main body; the characteristic analysis unit acquires the main characteristics of the image; the mapping relation unit determines the mapping relation between the image background and the shooting subject; the feature coding unit is used for coding the image main body features and the mapping relation;

the case library module is used for storing the attribute information and composition information of the image main body and is also used for matching attribute similarity; the case library module specifically comprises a code acquisition unit, a similarity matching unit and a source case storage unit; the code acquiring unit is used for acquiring a feature code and a mapping relation code; the similarity matching unit is used for performing similarity matching calculation on the target case subject characteristics and the source case subject characteristics, then performing mapping relation similarity matching calculation, and finally outputting an intelligent shooting angle mode to guide a user to adjust a shooting angle; what is needed isThe algorithm of the similarity matching unit is

Wherein X is a target subject, Y is a source case subject, and both the target subject X and the source case subject Y include N-dimensional features, that is, X is (X1, X2, X3, … …, xn), Y is (Y1, Y2, Y3, … …, yn), and the smaller the cosine value in the algorithm, the higher the similarity; the source case storage unit is used for storing source cases, including source cases set by the system and source cases added by users;

the image acquisition module acquires a preview photo and stores the preview photo in the RAM module; then, the preview picture stored in the RAM module is called through the focus acquisition unit and an image main body is determined; then the characteristic analysis unit calls the image subject information in the focus acquisition unit and determines the image subject characteristics according to the image subject; then the mapping relation unit calls the image main body characteristic information of the characteristic analysis unit to determine the mapping relation between the image background and the image main body; then the feature coding unit calls the image main body feature information of the feature analysis unit for coding on one hand, and calls the mapping relation information between the image background and the image main body of the mapping relation unit for coding on the other hand; then the code acquiring unit calls a target feature code and a target mapping relation code in the feature coding unit and transmits the feature code and the mapping relation code to the similarity matching unit; then the similarity matching unit calls a source case main body feature code and a source case mapping relation code stored in a source case storage unit, carries out main body feature similarity matching calculation on a target case main body feature code and the source case main body feature code, carries out mapping relation similarity matching calculation on the target case mapping relation code and the source case mapping relation code, calls and outputs the most similar source case main body feature information and mapping relation information in the source case storage unit according to a main body feature similarity matching calculation result and a mapping relation similarity matching calculation result, replaces and integrates the source case main body feature information into the source case mapping relation information, obtains the most similar source case shooting angle, and calls and outputs the newly integrated most similar source case to guide a user to adjust the shooting angle; and finally, the source case storage unit calls the target feature codes and the target mapping relation codes in the code acquisition unit, and stores the target feature codes and the target mapping relation codes as the feature codes and the mapping relation codes of the newly added source case.

2. The intelligent shooting system based on case-based reasoning, as claimed in claim 1, wherein: the focus acquisition unit uses an algorithm g (i, j) ═ sqrt ((f (i, j) -f (i +1, j)) ^2+ (f (i +1, j) -f (i, j +1)) ^2), wherein f (i-1, j-1), f (i-1, j +1), f (i, j-1), f (i, j +1), f (i +1, j-1), f (i +1, j +1) and f (i +1, j +1) are to-be-processed image pixels, and g (i, j) is a processed pixel.

3. An intelligent shooting method based on case-based reasoning is characterized in that: the method comprises the following steps:

step 1, acquiring a camera preview, and intercepting and caching the preview after a user executes focusing operation;

step 2, analyzing the preview image background, determining an image main body and the background, mapping relations of the image main body and the background, and attribute characteristics of the main body, and encoding;

and step 3, prompting the user whether the source case is needed: if the user needs the source case, entering step 4; if the user does not need the source case, clicking a cancel case button displayed in the interface to automatically complete composition, and entering step 8;

step 4, searching a case base, matching the case base with a target case, and respectively matching and outputting the optimal source case main body characteristic information and the mapping relation information between the optimal source case main body and the background;

step 5, replacing and integrating the characteristic information of the optimal source case main body into the mapping relation information between the optimal source case main body and the background to form a new optimal source case;

step 6, displaying the new and optimal source case main body outline on a shooting interface;

step 7, according to the source case body contour, manually adjusting the angle by a user to enable the target body contour to be overlapped with the source case body contour as much as possible;

and 8, triggering a shooting button to finish shooting, storing the image and prompting a user whether to store the attribute characteristics of the subject and the mapping relation between the subject and the background as a source case.

4. The intelligent shooting method based on case-based reasoning, as claimed in claim 3, wherein: the step 2 comprises the following execution processes:

a. determining the basic position of a target image main body through focusing operation, and determining the outline of the target main body by using an edge detection method;

b. extracting the main feature attributes of the target image by using an SIFT algorithm;

c. determining a mapping relation between a target image background and a target shooting subject;

d. and coding the target subject characteristics and the target mapping relation so as to calculate the case similarity.

5. The intelligent shooting method based on case-based reasoning, as claimed in claim 4, wherein: the algorithm formula of the edge detection method is g (i, j) ═ sqrt ((f (i, j) -f (i +1, j)) ^2+ (f (i +1, j) -f (i, j +1)) ^2), wherein f (i-1, j-1), f (i-1, j +1), f (i, j-1), f (i, j +1), f (i +1, j-1), f (i +1, j +1) are all pixels of an image to be processed, and g (i, j) is the processed pixel.

6. An intelligent photographing method based on case-based reasoning, according to any one of claims 4-5, characterized in that: the SIFT algorithm comprises the following steps: a. firstly, constructing a scale space, detecting extreme points and obtaining scale invariance; b. then, filtering extreme value characteristic points and carrying out accurate positioning; c. then distributing a direction value for the extreme value characteristic point; d. and finally generating a feature descriptor.

7. The intelligent shooting method based on case-based reasoning, as claimed in claim 3, wherein: the step 4 comprises the following execution processes:

a. acquiring a feature code and a mapping relation code;

b. calculating the similarity between the target case main body feature codes and the source case main body feature codes, and pre-storing a plurality of source cases with high similarity according to a set threshold;

c. and performing mapping relation similarity calculation on the source case with high feature similarity, and outputting the corresponding shooting angle with the highest mapping relation similarity.

Images