TW201342093A - Method and system for image searching - Google Patents

Abstract

A method and system for image searching are disclosed. Target images can be obtained according to an initial image from a plurality of images. A user selects an initial object from the initial image, and then the system gets at least one initial keyword corresponding to the initial object. Finally, the system finds target images according to initial keywords.

Description

Image search method and system

The present invention relates to an image search method and system; and more particularly to an image search method and system for finding an associated at least one target image from a plurality of pictures through an initial picture.

The existing network search method mainly involves the user returning data according to the keyword after the keyword is input by the user. This method is mostly structured in the search of text, and the search engine compares the various materials according to the keywords, and identifies the corresponding webpage, file or image and provides it to the user.

Text-based searches are good for searching for text-based files such as articles, news, or books, but they are not effective for searching image files. In the known image search method, for example, U.S. Patent No. 6,851,802 uses a user feedback method to perform image search. Specifically, if the user wants to search for images of "grape", the user first uploads several pictures with "grapes" to the system, and the system analyzes the common features of the pictures (such as boundary values, colors or textures). Etc.), it is found that there are "grapes" characteristics, so images containing "grapes" can be retrieved and provided to users. This method relies heavily on the ability to discriminate between picture features, and is prone to situations where the common features of the picture cannot be analyzed.

In addition, the image search system disclosed in Taiwan Patent Publication No. 201117027 searches for a more accurate contrast image based on the overlap ratio of the original image and the contrast image, the contour matching ratio, and the color matching ratio. However, it is well known that the characteristics of an image are not limited to the overlap ratio, the contour matching ratio, and the color matching ratio; simply searching for these features may not find the image desired by the user.

Therefore, it is necessary to provide an image search method and system to solve the lack of prior art.

The main object of the present invention is to provide an image search method having the effect of finding an associated at least one target picture from a plurality of pictures through an initial picture.

Another main object of the present invention is to provide an image search system having the effect of finding an associated at least one target picture from a plurality of pictures through an initial picture.

In order to achieve the above object, according to an embodiment of the present invention, an image search method of the present invention searches for an associated at least one target image from a plurality of pictures through an initial picture, wherein each of the plurality of pictures includes at least one The items can be clicked, and each of the selectable items each corresponds to at least one keyword. The image searching method includes: receiving a selection of an initial object in the initial picture, wherein the initial object is one of the at least one selectable object included in the initial picture; and the initial object is obtained from the database according to the initial object. At least one initial keyword corresponding to the object, the at least one initial keyword is the at least one keyword corresponding to the initial object; obtaining the at least one target image from the database according to the at least one initial keyword; and providing the at least A target picture.

According to an embodiment of the present invention, the comparison module transmits the at least one keyword corresponding to each of the at least one initial keyword and the at least one selectable object included in the plurality of images. The at least one target picture.

According to an embodiment of the present invention, the ordering of the at least one target picture is performed from a person including more matching objects to a person including less matching objects, wherein the matching object refers to at least one of the at least one keywords corresponding to An object that matches the at least one initial keyword.

According to an embodiment of the present invention, the image search method further includes: receiving a search keyword; and providing at least one corresponding picture according to the search keyword, the initial picture being one of the at least one corresponding picture.

According to an embodiment of the invention, an image search system includes a database, a processing module, an index module, a comparison module, and a providing module. The database is configured to store a plurality of pictures, wherein each picture includes at least one clickable item, and each of the selectable items each corresponds to at least one keyword. The processing module is configured to receive a selection of an initial object in one of the plurality of initial images, wherein the initial object is one of the at least one selectable objects included in the initial image. The indexing module is configured to obtain at least one initial keyword corresponding to the initial object from the database according to the initial object, wherein the at least one initial keyword is the at least one keyword corresponding to the initial object. The comparison module is configured to obtain at least one target image from the database according to the at least one initial keyword. A module is provided for providing the at least one target picture.

According to an embodiment of the present invention, the comparison module transmits the at least one keyword corresponding to each of the at least one initial keyword and the at least one selectable object included in the plurality of images. The at least one target picture.

According to an embodiment of the present invention, the providing module is further configured to sort the at least one target image, wherein the sorting of the at least one target image is performed from a person including more matching objects to a person including less matching objects, wherein the matching An object is an object corresponding to at least one of the at least one keyword and the at least one initial keyword.

According to an embodiment of the present invention, the processing module is further configured to receive a search keyword, and provide at least one corresponding image according to the search keyword, where the initial image is one of the at least one corresponding image.

The above and other objects, features and advantages of the present invention will become more <

Please refer to FIG. 1 below, which is a schematic diagram of a usage environment of an image searching method according to an embodiment of the present invention. As shown in FIG. 1 , the user 110 uses the computer 112 to connect to the image search system 1 through the network 120 for image search, and the image search system 1 provides the searched target image back to the computer 112.

According to an embodiment of the present invention, the computer 112 is a general desktop computer, but the invention is not limited thereto; and may be any electronic device connected to the network such as a notebook computer, a smart phone or a tablet computer. It should also be noted that the computer 112 may also include other more detailed modules or components.

Next, please refer to FIG. 2, which is a system architecture diagram of an image search system according to an embodiment of the present invention. As shown in FIG. 2, the image search system 1 of the present invention includes a database 10, a processing module 20, an indexing module 30, a comparison module 40, and a providing module 50, in accordance with an embodiment of the present invention. It should be noted that, in addition to being configurable as a hardware device, a software program, a firmware, or a combination thereof, each of the above modules may also be configured by a circuit loop or other suitable type; and, in addition, each module may be configured in a separate type. It can also be combined with the type configuration. In addition, the present embodiment is merely illustrative of preferred embodiments of the present invention, and in order to avoid redundancy, all possible combinations of variations are not described in detail. However, those of ordinary skill in the art will appreciate that the various modules or components described above are not necessarily required. In order to implement the invention, other well-known modules or elements of more detail may also be included. Each module or component may be omitted or modified as needed, and no other modules or components may exist between any two modules.

Referring to FIG. 3 and FIG. 4, respectively, a schematic diagram of an image and a schematic diagram of a database according to an embodiment of the present invention are shown. In accordance with an embodiment of the present invention, a plurality of images are stored in the database 10, and each image is analyzed into a plurality of objects, each of which corresponds to at least one keyword. As shown in FIG. 3, according to an embodiment of the present invention, the image 101 is analyzed to include four objects 101a, 101b, 101c, and 101d, each of which is indicated by an elliptical outer frame. For the analysis of the objects included in the image, the scope of the prior art can be automatically determined by the program according to the boundary value, color or texture, and the object can be manually marked, and will not be described here.

As shown in FIG. 4, the database 10 is divided into a plurality of fields, and the related information of each image is recorded separately. According to an embodiment of the present invention, the image number 11 field records the index of each image. If the image 101 is the image numbered No. 1 in the database 10, the number is 101; the remaining image numbers may be So on and so forth.

The number of objects in the 12 fields records the number of objects included in each image. If the image 101 is analyzed to contain 4 objects, the number of objects is 4.

The item number 13 field records the item number of each object of each image. If the image 101 is analyzed to contain 4 objects, the numbers are 101a, 101b, 101c, and 101d, respectively.

The keyword 14 field records the corresponding keyword of each object of each image. For example, the corresponding keywords of the object 101a are "helmet" and "head". It should be noted that the keyword corresponding to the object may be one or more. The corresponding keyword for how to set the image object can be manually set, but the invention is not limited thereto.

Next, please refer to FIG. 5, which is a flow chart of steps of an image searching method according to an embodiment of the present invention; and please refer to FIG. 2 and FIG. 6 to FIG. 8 together with respect to an embodiment of the present invention. The image search method of the present invention will be described below with the image search system 1 shown in FIG. It should be noted, however, that the image search method of the present invention is not limited to use in the image search system 1 shown in FIG. 2.

First, step 501 is performed: receiving a search keyword.

Please refer to FIG. 6, which is a schematic diagram of an image search page according to an embodiment of the present invention. In accordance with an embodiment of the present invention, the user uses the computer 112 to connect to the image search system 1 to search for images. Computer 112 includes a screen 114 that can be used to display a picture.

As shown in FIG. 6, after the computer 112 is connected to the image search system 1, an image search page 600 is displayed on the screen 114, which includes a search keyword input area 601 and a search key 602. The user can transmit the search keyword to the image search system 1 by inputting the search keyword in the keyword input area 601 and pressing the search key 602, and the image search system 1 receives the search module 20 by the processing module 20. Search for keywords. For example, in this example, the user has entered "playing baseball" as a search keyword.

Then proceed to step 502: providing a corresponding picture according to the search keyword.

Please refer to FIG. 7, which is a schematic diagram of a corresponding picture according to an embodiment of the present invention. After the image search system 1 receives the search keyword, the processing module 20 may further provide at least one corresponding picture according to the search keyword.

As shown in FIG. 7, the processing module 20 searches the database 10 for the images 101, 102, 103, and 104 related to "baseball" as corresponding pictures according to the search keyword "baseball", and transmits the network 120 through the network 120. It is transmitted to the computer 112 and displayed on the screen 114, and the user can select one of them as the initial picture. It should be noted that how to provide a corresponding picture according to the search keyword is well-known to those skilled in the art and will not be described here.

Next, step 503 is performed: receiving a selection of one of the initial objects in the initial picture.

Referring to FIG. 7, the user can select one of the images 101, 102, 103, and 104 as the initial picture and select one of the objects as the initial object, and transmit it to the image search system 1, and the image search system 1 This selection is received by the processing module 20.

According to an embodiment of the present invention, when the corresponding module provides the corresponding image according to the search keyword, the processing module 20 also displays the object included in each corresponding image on the screen 114 in the form of an item that can be clicked, and has an elliptical shape. The box indicates that you can click on the item. Therefore, the user can directly select an object, and the processing module 20 recognizes the object as the initial object after receiving the click instruction, and the picture including the object is regarded as the initial picture. For example, in this embodiment, the user selects the object 101d of the image 101, and after receiving the click instruction, the processing module 20 recognizes the object 101d as the initial object, and identifies the image 101 as the initial picture. It should be noted that how the object is presented in the form of a selectable object is well known to those of ordinary skill in the art and will not be further described herein.

Then proceed to step 504: obtaining at least one initial keyword corresponding to the initial object from the database according to the initial object.

After the image search system 1 receives the instruction to select the initial object, the index module 30 can obtain the initial keyword corresponding to the initial object from the database 10 according to the initial object, where the initial keyword is the initial object. The corresponding keyword.

Referring to FIG. 4, after determining that the object 101d is the initial object, the index module 30 can obtain the keyword "bat" corresponding to the object 101d in the database 10 as the initial keyword. It should be noted that the initial keywords are not limited to one set. If there are multiple groups of keywords corresponding to the initial object, all corresponding keywords will be used as the initial keywords.

Then proceed to step 505: obtaining at least one target picture from the database according to the at least one initial keyword.

After the image search system 1 obtains the initial keyword, the comparison module 40 can then obtain the target image from the database 10 based on the initial keyword. According to an embodiment of the present invention, the comparison module 40 transmits the keywords corresponding to the clickable objects included in the initial keywords and the plurality of pictures stored in the database 10 to obtain the target picture.

Please refer to FIG. 8, which is a schematic diagram of a target picture according to an embodiment of the present invention. In this embodiment, the images 105, 106 and the images are found by comparing the initial keyword "bat" with the keywords corresponding to the selectable objects included in the plurality of pictures stored in the database 10. There are also "bats" among the keywords corresponding to the clickable objects included in the three images of 102. Therefore, three images of images 105, 106, and 102 are used as the target images.

Finally, step 506 is performed: providing the at least one target picture.

Finally, the target module is provided by the providing module 50, for example, the target image is transmitted to the computer 112 via the network 120, and displayed on the screen 114. According to an embodiment of the present invention, the providing module 50 may further sort the target pictures, from those including more matching objects to those containing less matching objects, wherein the matching objects refer to at least one of the corresponding keywords. The object that matches the initial keyword.

Referring to FIG. 8, the images 105, 106, and 102 respectively include three, two, and one matching objects, and the keywords corresponding to the matching objects also have "balls", so the images 105, 106, and 102 are three. The image is the target image. According to an embodiment of the invention, the target picture is based on the number of matching objects included. Thus, as shown in FIG. 8, displayed at the top is an image 105 containing three matching objects, followed by an image 106 containing two matching objects, and finally an image 102 containing one matching object. However, it should be noted that the method for ordering the target image in the present invention is not limited thereto.

According to an embodiment of the present invention, as shown in FIG. 8, when the target image is displayed, the matching object included in the target image is marked with an elliptical outer frame to indicate the position of the matching object. However, the image searching method of the present invention is not limited thereto, and the position of the matching object may be marked in other ways or may not be marked.

It should be noted here that the image searching method of the present invention is not limited to the above-described order of steps, and the order of the above steps may be changed as long as the object of the present invention can be achieved.

To sum up, the present invention, regardless of its purpose, means and efficacy, shows its distinctive features of the prior art. You are requested to review the examination and express the patent as soon as possible. It should be noted that the various embodiments described above are merely illustrative for ease of explanation, and the scope of the invention is intended to be limited by the scope of the claims.

1. . . Image search system

10. . . database

11. . . Image number

12. . . Number of objects

13. . . Object number

14. . . Keyword

20. . . Processing module

30. . . Index module

40. . . Alignment module

50. . . Provide module

101. . . image

101a, 101b, 101c, 101d. . . object

102,103,104,105,106. . . image

110. . . user

112. . . computer

114. . . Screen

120. . . network

600. . . Image search page

601. . . Keyword input area

602. . . Search key

1 is a schematic diagram of a usage environment of an image search method according to an embodiment of the present invention.

2 is a system architecture diagram of an image search system in accordance with an embodiment of the present invention.

3 is a schematic illustration of an image in accordance with an embodiment of the present invention.

4 is a schematic diagram of a database in accordance with an embodiment of the present invention.

Figure 5 is a flow chart showing the steps of an image search method in accordance with an embodiment of the present invention.

6 is a schematic diagram of an image search page in accordance with an embodiment of the present invention.

Figure 7 is a schematic illustration of a corresponding picture in accordance with an embodiment of the present invention.

Figure 8 is a schematic illustration of a target picture in accordance with an embodiment of the present invention.

Step 501: Receive a search keyword.

Step 502: Provide a corresponding picture according to the search keyword.

Step 503: Receive a selection of one of the initial objects in the initial picture.

Step 504: Acquire at least one initial keyword corresponding to the initial object from the database according to the initial object.

Step 505: Acquire at least one target picture from the database according to the at least one initial keyword.

Step 506: Provide the at least one target picture.

Claims (8)

An image searching method is to search for an associated at least one target image from a plurality of pictures through an initial picture, wherein each of the plurality of pictures includes at least one clickable object, and each of the selectable objects is Corresponding to the at least one keyword, the image searching method includes: receiving a selection of an initial object in the initial picture, the initial object being one of the at least one selectable object included in the initial picture The at least one initial keyword corresponding to the initial object is obtained from a database according to the initial object, and the at least one initial keyword is the at least one keyword corresponding to the initial object; And obtaining, by the comparison module, the at least one target image from the database according to the at least one initial keyword; and providing the at least one target image. The image search method of claim 1, wherein the comparison module is configured to correspond to each of the at least one selectable object included in the at least one initial keyword and the complex image. The at least one keyword to obtain the at least one target picture. The image searching method of claim 2, wherein the sorting of the at least one target image is arranged from a person including more matching objects to a person including less matching objects, wherein the matching object refers to the corresponding one. At least one of the at least one keyword that matches the at least one initial keyword. The image search method of claim 1, further comprising: receiving a search keyword; and providing at least one corresponding image according to the search keyword, the initial image being one of the at least one corresponding image . An image search system includes: a database for storing a plurality of images, wherein each of the images includes at least one clickable object, and each of the selectable objects corresponds to at least one keyword; and a processing module Receiving a selection of an initial object in one of the initial pictures of the plurality of pictures, wherein the initial object is one of the at least one selectable object included in the initial picture; an index mode a group, configured to obtain at least one initial keyword corresponding to the initial object from the database according to the initial object, wherein the at least one initial keyword is the at least one keyword corresponding to the initial object; a group for obtaining at least one target image from the database according to the at least one initial keyword; and a providing module for providing the at least one target image. The image search system of claim 5, wherein the comparison module is configured to correspond to each of the at least one selectable object included in the at least one initial keyword and the plurality of images. The at least one keyword to obtain the at least one target picture. The image search system of claim 6, wherein the providing module is further configured to sort the at least one target image, wherein the sorting of the at least one target image is arranged from the one containing more matching objects to the inclusion The less consistent object, wherein the matching object refers to an object corresponding to at least one of the at least one keyword and the at least one initial keyword. The image search system of claim 5, wherein the processing module is further configured to receive a search keyword, and provide at least one corresponding image according to the search keyword, where the initial image is the at least one corresponding image One of them.