阅读说明：本技术 一种图像搜索方法、装置、电子设备及存储介质 (Image searching method and device, electronic equipment and storage medium ) 是由 聂砂 王竹萌 盛耀聪 王洋 杨美红 贺潇铮 王静逸 于 2020-06-28 设计创作，主要内容包括：本发明实施例公开了一种图像搜索方法、装置、电子设备及存储介质。该方法包括：获取待搜索图像信息；其中所述待搜索图像信息包括基于至少两种候选图像类别确定的待搜索图像类别；确定与所述待搜索图像类别关联的图像搜索算法对；其中,所述图像搜索算法对为特征提取-特征匹配算法对；根据所述图像搜索算法对对待搜索图像进行图像特征处理,以得到图像搜索结果。通过运行本发明实施例所提供的技术方案,可以解决由于对所有待搜索图像采用固定的深度学习等算法进行处理,获取图像搜索结果,缺乏对待搜索图像的针对性的问题,达到了提高图像搜索的针对性和准确率的效果。(The embodiment of the invention discloses an image searching method, an image searching device, electronic equipment and a storage medium. The method comprises the following steps: acquiring image information to be searched; wherein the image information to be searched comprises an image category to be searched which is determined based on at least two candidate image categories; determining an image searching algorithm pair associated with the image category to be searched; wherein the image search algorithm pair is a feature extraction-feature matching algorithm pair; and carrying out image characteristic processing on the image to be searched according to the image searching algorithm to obtain an image searching result. By operating the technical scheme provided by the embodiment of the invention, the problem that the pertinence of the image to be searched is lacked because all the images to be searched are processed by adopting algorithms such as fixed deep learning and the like to obtain the image searching result can be solved, and the effect of improving the pertinence and the accuracy of image searching is achieved.)

1. An image search method, comprising:

acquiring image information to be searched; wherein the image information to be searched comprises an image category to be searched which is determined based on at least two candidate image categories;

determining an image searching algorithm pair associated with the image category to be searched; wherein the image search algorithm pair is a feature extraction-feature matching algorithm pair;

and carrying out image characteristic processing on the image to be searched according to the image searching algorithm to obtain an image searching result.

2. The method of claim 1, wherein performing image feature processing on an image to be searched according to the image search algorithm to obtain an image search result comprises:

acquiring a first image characteristic of the image to be searched and a second image characteristic of the image in an image library according to a characteristic extraction algorithm in the image search algorithm pair;

and matching the first image characteristic with the second characteristic data according to a characteristic matching algorithm in the image searching algorithm pair to obtain the image searching result.

3. The method according to claim 1, before acquiring the image information to be searched, further comprising:

establishing an incidence relation between the candidate image category and the image searching algorithm pair;

and providing options of candidate image categories to determine the image categories to be searched related to the image information to be searched according to the selection result of the options.

4. The method of claim 3, wherein associating the candidate image category with the image search algorithm pair comprises:

if the candidate image category is known, determining an image search algorithm pair associated with the candidate image category according to an algorithm pair designated result;

and if the candidate image category is unknown, determining an image search algorithm pair associated with the candidate image category according to an image search test result.

5. The method of claim 4, wherein the image search test procedure comprises:

determining a target feature extraction algorithm from candidate feature extraction algorithms to obtain a feature vector of the test image;

determining a target feature matching algorithm from the candidate feature matching algorithms to obtain a test image search result according to the feature vector of the test image;

and if the search result of the test image meets the test condition, determining the image search algorithm pair formed by the target feature extraction algorithm and the target feature matching algorithm.

6. An image search apparatus characterized by comprising:

the information acquisition module is used for acquiring the information of the image to be searched; wherein the image information to be searched comprises an image category to be searched which is determined based on at least two candidate image categories;

the algorithm pair determining module is used for determining an image searching algorithm pair associated with the image category to be searched; wherein the image search algorithm pair is a feature extraction-feature matching algorithm pair;

and the image processing module is used for carrying out image characteristic processing on the image to be searched according to the image searching algorithm so as to obtain an image searching result.

7. The apparatus of claim 6, wherein the image processing module comprises:

the image feature acquisition unit is used for acquiring a first image feature of the image to be searched and a second image feature of the image in the image library according to a feature extraction algorithm in the image search algorithm pair;

and the feature matching unit is used for matching the first image feature with the second feature data according to a feature matching algorithm in the image search algorithm pair to obtain the image search result.

8. The apparatus of claim 6, further comprising:

the relation establishing module is used for establishing the incidence relation between the candidate image category and the image searching algorithm pair before the information acquiring module;

and the option providing module is used for providing options of candidate image categories so as to determine the image categories to be searched related to the image information to be searched according to the selection result of the options.

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the image search method of any one of claims 1-5.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out an image search method according to any one of claims 1 to 5.

Technical Field

The present invention relates to computer technologies, and in particular, to an image searching method and apparatus, an electronic device, and a storage medium.

Background

With the development of computer technology, the searching function is more and more powerful, and besides searching pictures through texts, a user can acquire image sources or similar images in a picture searching mode.

Disclosure of Invention

The embodiment of the invention provides an image searching method, an image searching device, electronic equipment and a storage medium, and aims to improve the pertinence and accuracy of image searching.

In a first aspect, an embodiment of the present invention provides an image searching method, where the method includes:

acquiring image information to be searched; wherein the image information to be searched comprises an image category to be searched which is determined based on at least two candidate image categories;

determining an image searching algorithm pair associated with the image category to be searched; wherein the image search algorithm pair is a feature extraction-feature matching algorithm pair;

and carrying out image characteristic processing on the image to be searched according to the image searching algorithm to obtain an image searching result.

In a second aspect, an embodiment of the present invention further provides an image search apparatus, including:

the information acquisition module is used for acquiring the information of the image to be searched; wherein the image information to be searched comprises an image category to be searched which is determined based on at least two candidate image categories;

the algorithm pair determining module is used for determining an image searching algorithm pair associated with the image category to be searched; wherein the image search algorithm pair is a feature extraction-feature matching algorithm pair;

and the image processing module is used for carrying out image characteristic processing on the image to be searched according to the image searching algorithm so as to obtain an image searching result.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the image search method as described above.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the image search method as described above.

The embodiment of the invention obtains the information of the image to be searched; wherein the image information to be searched comprises an image category to be searched which is determined based on at least two candidate image categories; determining an image searching algorithm pair associated with the image category to be searched; wherein the image search algorithm pair is a feature extraction-feature matching algorithm pair; and carrying out image characteristic processing on the image to be searched according to the image searching algorithm to obtain an image searching result. The method solves the problem that the pertinence of the images to be searched is lacked because all the images to be searched are processed by adopting algorithms such as fixed deep learning and the like to obtain the image searching result, and achieves the effect of improving the pertinence and the accuracy of image searching.

Drawings

Fig. 1 is a flowchart of an image searching method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of an image searching method according to an embodiment of the present invention;

fig. 3 is a flowchart of an image searching method according to a second embodiment of the present invention;

FIG. 4 is a diagram illustrating an image search testing process according to a second embodiment of the present invention;

fig. 5 is a schematic structural diagram of an image searching apparatus according to a third embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.