TWI494864B - Method and system for searching image and computer program product using the method - Google Patents

Description

Image search method, system and computer program product used thereby

The present invention relates to an image search method, and more particularly to an image search method and system for outdoor shooting and a computer program product therefor.

With the rapid development of mobile communication technology, mobile value-added services provided by mobile communication operators are also all-encompassing. Life information such as news, finance, weather and entertainment are all within the scope of services provided by mobile communication operators. Among them, the weather forecast is closely related to our daily life. At present, the way to obtain weather forecast information by using a mobile phone includes directly connecting the user to the weather forecast website through the link of the wireless network to check the current weather.

Users often check and obtain weather information of a city in the current and future days through the weather website, and then decide on the out-of-wear based on the meteorological information obtained. However, meteorological information can only display the current weather conditions based on data or weather images estimated from these data, but it is not possible to know the actual weather conditions from these information alone. If the user is about to travel to a strange city, since the user has not lived there, he can only guess the actual weather conditions based on meteorological information. In this way, if the weather information does not match the actual weather conditions, it will cause users trouble.

In view of the above, the present invention provides an image search method for finding an image file that is taken at a specific location and taken outdoors, so that the user can know the actual outdoor weather condition of a specific place before going to the specific place.

The present invention provides an image search system that uses an image information file of an image file to search for an image file that meets the search criteria.

In particular, the present invention provides an image search method. First, receive location information. Then, connect to the Internet to search for image files that match the location information. Then, the image information file of the image file is queried, and the shooting time of each image file is obtained. After that, the shooting environment recognition operation is performed on these image files to identify the image files taken outdoors. Finally, at least one image file taken outdoors is listed based on the shooting time of the image files and the result of the shooting environment recognition action.

In an embodiment of the present invention, the step of listing the image files for outdoor shooting may be performed according to the shooting time of each image file, and the image files taken outdoors may be sequenced starting from the image file closest to the current time.

In an embodiment of the present invention, the shooting environment recognition operation is performed on the image file, and the image file is closest to the current time, and the image recognition operation is performed on the image files one by one according to the arrangement order of the image files. Identify image files taken outdoors.

In an embodiment of the present invention, the image search method further includes determining whether a shooting time of each image file meets a preset time range.

In an embodiment of the invention, the location information includes a search range. The steps of searching for the image file conforming to the location information include, for example, querying the image information file of each image file, obtaining the position coordinates of each image file when the image is taken, and then searching for the image file whose location coordinates are located in the search range. Here, the location information includes one of a keyword, a place name, an attraction name, a latitude and longitude, and an administrative area, and can be used to set a search range.

In one embodiment of the present invention, the step of connecting to the network to search for a plurality of image files conforming to the location information includes one of the information related to the location information in a message related to the image file in the network search. Image file of the keyword.

In an embodiment of the present invention, the step of performing the shooting environment recognition operation is to determine whether the image files are outdoor shooting by reading at least one shooting environment attribute of the image information files of each image file. The shooting environment attributes include one or a combination of lens aperture, exposure time, sensitivity, focus, shutter speed, and flash mode.

In an embodiment of the present invention, the step of performing the shooting environment recognition operation is performed by using a feature point identification method to identify whether there is a specific object; and screening an image file having a specific object.

In an embodiment of the present invention, after the step of performing the outdoor shooting recognition operation, a portrait recognition action may be performed to determine whether the image file taken outdoors has at least one portrait.

In an embodiment of the invention, the portrait recognition action includes a face recognition action to determine whether the image file taken outdoors has at least one face.

In an embodiment of the present invention, after the step of listing at least one image file taken outdoors, the image file whose shooting time is closest to the current time can be selected from the image files taken outdoors to display the image file. Weather information is associated.

In an embodiment of the present invention, the step of connecting to the wireless network to search for the image file conforming to the location information further includes: connecting at least one image database to search for the image file conforming to the location information in the image database. .

In addition, the present invention provides an image search system, which is configured in an electronic device. The system includes an input module, a connection module, a calculation module, an outdoor image recognition module, and a selection module. The image search module is connected to the network by using a connection module, and receives location information through the input module. The computing module searches for image files that meet the above-mentioned location information on the wireless network, and queries the image information files of each image file to obtain the shooting time of each image file. The outdoor image recognition module performs a shooting environment recognition action on the image files to identify image files taken outdoors. The selection module lists at least one image file taken outdoors according to the shooting time of the image file and the result of the shooting environment recognition action.

In an embodiment of the present invention, the computing module further includes connecting to at least one image database to search for image files conforming to the location information from the image database.

In an embodiment of the present invention, the selecting module further comprises: according to the shooting time of each image file, starting from the image file closest to the current time, sequentially outputting the image file taken outdoors. Furthermore, the selection module can also select an image file whose shooting time is closest to the current time from the image file taken outdoors to associate the image file with the weather information.

In an embodiment of the present invention, the outdoor image recognition module may also start with an image file that is closest to the current time. According to the order of the image files, the image files are subjected to shooting environment recognition actions one by one to identify the outdoors. The image file taken. And performing the shooting environment recognition operation by the outdoor image recognition module includes: reading at least one shooting environment attribute in the image information file of each image file (for example, one of a lens aperture, an exposure time, a sensitivity, a shutter speed, a focal length, and a flash mode) Or a combination thereof, to determine whether each image file is taken outdoors.

In an embodiment of the invention, the location information includes a search range. The computing module further includes querying the image information file of each image file, and obtaining the position coordinates of each image file when the image is taken, so as to search for the image file whose position coordinate is located in the search range. The location information includes one of keywords, location name, attraction name, latitude and longitude, and administrative area, and can be used to set the search range.

In an embodiment of the present invention, the image search system further includes a portrait recognition module for performing a portrait recognition operation to determine whether the image file taken outdoors has at least one portrait.

In an embodiment of the invention, the computing module can further determine whether the shooting time of the image files meets the preset time range.

The invention further provides a computer program product for performing the above image search method. The computer program product is basically composed of a plurality of code segments (for example, creating an organization chart code segment, signing a form code segment, setting a code segment, and deploying a code segment), and the code segments are After being loaded into the electronic device and executed, the steps of the image search method and the functions of the image search system described above can be completed.

Based on the above, the present invention uses a wireless network to search for image files that match the location information based on a location information, and determines whether the image files are outdoor shots, thereby finding image files that are taken at a specific location and taken outdoors. According to this, the user can know the actual outdoor weather condition of the specific location through the searched image file before going to the specific location.

The above described features and advantages of the present invention will be more apparent from the following description.

In general, it is common practice to use electronic devices or portable electronic devices (eg, home computers, mobile phones, personal digital assistants, etc.) to query weather information. Users can check and obtain weather information of a city in the current and future days through the weather website. However, weather information can only display the current weather conditions with data or simple predicted pictures. Users cannot judge and know the actual weather conditions from these information alone. To this end, the present invention provides an image search method and system, and a computer program product for use, by searching for image files similar to the current time, to provide actual weather conditions to the user for reference. In order to clarify the content of the present invention, the following specific examples are given as examples in which the present invention can be implemented.

FIG. 1 is a flowchart of an image search method applicable to an electronic device or a portable electronic device, such as a home computer, a notebook computer, a mobile phone, and a personal digital assistant (PDA) according to an embodiment of the invention. ), PDA phones, smart phones, multimedia players, handheld game consoles, navigation devices, car computers or other communication devices. Referring to FIG. 1, first, in step S105, location information is received by an electronic device. Then, as shown in step S110, the electronic device connects to the network to search for an image file conforming to the location information, wherein the network can be a wired network or a wireless network connected in any form.

In this embodiment, the location information may be a keyword, a place name, a name of a place, a latitude and longitude, or an administrative area, etc., to search for an image file by using a keyword, a place name, a name of a place, a latitude and longitude, or an administrative area. Condition or set the search range of an image file. For example, the received location information is directly used as a search condition or range, or the location information is used to set the search range. Specifically, the electronic device connects to the image database (for example, a web album, or an image database of a specific place or an attraction area, such as a webcam database) according to the received location information, for the image data. Search for image files that match location information, such as photo files, video files, or images taken from video files.

For example, the electronic device can determine whether the image file meets the location information by querying the image information file of the image file. The image information file is, for example, an Exchangeable Image File (EXIF).

In general, information about image files, such as photos, is stored in its EXIF file. This EXIF file is usually generated when a digital camera shoots an image. In addition to the thumbnail image displayed on the camera screen, it also includes the file name of the image file, the length of the file name, and the shooting time (for example). , shooting date, shooting time), shooting location information (such as latitude and longitude coordinates), image resolution, and other shooting environment properties (such as lens aperture, exposure time, sensitivity, shutter speed, focus, and flash mode) . Accordingly, by querying the EXIF file, it can be determined whether the image file conforms to the received location information.

In addition, the camera database usually has location information, such as latitude and longitude coordinates or location name, so that location information can be used to find a camera database that matches a specific location, so that the image file can be searched in the camera database.

For example, if the location information received by the electronic device is the keyword “Taipei 101”, the location coordinate of “Taipei 101” is used as a center point, and the range of the specific distance from the center point is set as the search range. Accordingly, the electronic device searches the image database for the image file whose position coordinates recorded in the EXIF file fall within the search range.

In addition, the electronic device may first use "Taipei 101" to search for image information files corresponding to each image file, such as EXIF, whether the file name recorded in the file includes the keyword or search for information related to each image file. Whether or not this keyword is included to search for photos related to "Taipei 101". After that, if a search range is to be set, the position coordinate of "Taipei 101" can be used as the center point, and the range within the specific distance from the coordinate distance of the position can be set as the search range. In addition, in other embodiments, the user may directly input the latitude and longitude or directly set a specific distance as the radius to set the search range, which is not limited herein.

Or, instead of setting the search range, you can directly find all the image files that match the location information. In the present embodiment, it is not limited whether or not the search range is to be set.

After searching for the image file conforming to the location information, in step S115, the electronic device further queries the image information file of each image file to obtain the shooting time of each image file. Specifically, the electronic device queries the EXIF file of each image file to obtain the shooting time, wherein the shooting time may include time information such as shooting date and shooting time.

Then, in step S120, the electronic device performs a shooting environment recognition operation on the image files to identify the image files taken outdoors. Further, the electronic device can read the shooting environment attribute of the EXIF file of each image file, thereby determining whether the image file is for outdoor shooting. For example, whether one of the image files is outdoor shooting can be determined by one of lens aperture, exposure time, sensitivity, focal length, and flash mode. For example, since the indoor light is generally darker than the outdoor, if the user does not want to use the built-in flash to shoot and destroy the atmosphere, the camera's automatic exposure system will automatically open the lens aperture to the maximum, and will also open the shutter value. Adjusted slowly. Accordingly, by querying the lens aperture and the shutter speed, it is possible to determine whether or not the image file is for outdoor shooting.

Alternatively, it is also possible to determine whether the image file is outdoor shooting by various image recognition methods, for example, using feature point identification methods to identify whether there is a specific object or the brightness of the analyzed image. For example, if you are shooting outdoors, there may be a specific building or car in the image, or the brightness of the image will be higher. Accordingly, by identifying whether an image of a particular building or a car exists in the image, or analyzing the brightness information of the image, it can be determined whether the image file is outdoor.

Finally, in step S125, the electronic device lists at least one image file taken outdoors according to the shooting time of the image files and the result of the shooting environment recognition action. For example, an image file taken outdoors can be sequenced starting from the image file closest to the current time. In addition, when the electronic device performs the shooting environment recognition operation, the image file closest to the current time can be started, and according to the arrangement order of the image files, the shooting environment recognition actions are performed one by one to identify the image taken outdoors. file.

It should be noted that in other embodiments, the electronic device may first determine whether the shooting time of the image file meets the preset time range (for example, the image file captured on the same day, or the image file captured within one week from the current time). In order to take out the image file whose shooting time is within one week from the current time. Then, the shooting environment recognition action is performed on these image files to identify the image files taken outdoors. Accordingly, the electronic device can select the image files whose shooting time meets the preset time range, and then download the image files to the electronic device to perform the shooting environment recognition action.

In addition, in order to improve the reference value of the selected image file, after performing the outdoor shooting recognition action, a portrait recognition action, such as a face recognition action, can be performed to determine whether the image file taken outdoors has at least one character. Accordingly, the user is more able to use the wearing of the person or the crowd in the image file as the basis for the outing.

For example, FIG. 2A and FIG. 2B are schematic diagrams of an image file according to an embodiment of the invention. In the present embodiment, it is assumed that the location information is "Taipei 101." In addition, for convenience of explanation, FIG. 2A and FIG. 2B are described here, and it is assumed that FIG. 2A and FIG. 2B are image files conforming to the above-mentioned location information, and are taken outdoors. In order to further screen out the more valuable image files, the electronic device can perform the portrait recognition action on the two image files to further filter out the more valuable image files. After performing the portrait recognition action, the electronic device will filter out FIG. 2B. For example, although the user can know the outdoor weather conditions of "Taipei 101" at this time and know that there is no rain through the images of Figs. 2A and 2B, the image file of Fig. 2B can clearly know the outdoor of "Taipei 101" at this time. The weather is suitable for short sleeves. In this way, the selected image files will be more helpful to the user as an important reference for dressing.

In addition, in order to facilitate the combination with meteorological information and increase the reference accuracy of the image data, the electronic device can select the image file whose shooting time is closest to the current time from the image file taken outdoors to associate the image file with the weather information. . Here, in FIG. 2B, the image file of FIG. 2B is associated with weather information, as shown in FIG. FIG. 3 is a schematic diagram of a display screen according to an embodiment of the invention. In Figure 3, the weather information and video files are combined to allow the user to know more clearly the actual weather conditions of the destination point. For example, the weather information in Figure 3 is a shower, and the temperature range of the predicted temperature is 21~30 °C, so it is difficult for the user to judge whether there is current rain and the actual temperature. However, the user can find that the weather condition at this time is not raining and the temperature is suitable for wearing short sleeves from the image file whose search time is closest to the current time.

In addition, the present invention further provides an image search system. 4 is a block diagram of an image search system in accordance with an embodiment of the present invention. Referring to FIG. 4 , the image search system 400 includes an input module 410 , a connection module 420 , an operation module 430 , an outdoor image recognition module 440 , and a selection module 450 . In addition, in the embodiment, the image search system 400 further includes a portrait recognition module 460.

Here, the image search system 400 is connected to the wireless network through the connection module 420. The input module 410 is used to receive location information. The computing module 430 searches for an image file that conforms to the location information in the wireless network. For example, the computing module 430 is coupled to at least one image database to search for image files conforming to the location information from the image database. Moreover, the computing module 430 queries the image information files of the image files, such as the EXIF file, to obtain the shooting time of the image files.

The outdoor image recognition module 440 performs a shooting environment recognition operation on the image files to identify image files that are taken outdoors. Here, the shooting environment identification operation is as described in the above step S120, and therefore will not be described herein.

After discriminating the image files taken outdoors, the selection module 450 lists at least one image file taken outdoors according to the shooting time of the image files and the result of the shooting environment recognition action. For example, according to the shooting time of each image file, the image file taken outdoors is sequenced starting from the image file closest to the current time.

It should be noted that, after searching for the image files conforming to the location information, the computing module 430 can immediately sort the images according to the shooting time recorded in the EXIF file of each image file. Accordingly, the outdoor image recognition module 440 is started by the image file closest to the current time, and according to the arrangement order of the image files, the image recognition operations are performed one by one to identify the image files taken outdoors.

In addition, the computing module 430 can also determine whether the shooting time of the image file conforming to the location information meets the preset time range, so that the outdoor image recognition module 440 performs the shooting environment recognition action only on the image files.

It is worth mentioning that the image search system 400 further includes a portrait recognition module 460 in order to make the search result of the image have a high reference value. The portrait recognition module 460 performs a portrait recognition operation to determine whether the image file taken outdoors has at least one character. For example, the portrait recognition module 460 can be a face recognition module to perform a face recognition action, and if it can determine the presence of a human face in the image file, it can be judged to have at least one character. In this way, the user can decide to wear the local time by wearing the characters in the image file.

Furthermore, the computing module 430 can also select an image file whose shooting time is closest to the current time from the image file taken outdoors to associate the image file with the weather information.

The invention further provides a computer program product, comprising program instructions for performing the image search method, wherein the computer program product is basically composed of a plurality of code segments (for example, creating an organization chart code segment, signing a form) Code snippets, set code snippets, and deployment code snippets), and these code snippets are loaded into the mobile device and executed After the line, the steps of the image search method and the functions of the image search system described above can be completed.

In summary, the present invention uses a wireless network to search for image files conforming to the location information based on a location information, and determines whether the image files are outdoor shots, thereby finding image files that are taken at a specific location and taken outdoors. In addition, a face recognition action can be performed in the image files of the outdoor shooting to find an image file having at least one face. In this way, when the user goes to the specific location, the image file obtained by the image search method can be used to know the actual outdoor weather condition of the specific location.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the invention, and any one of ordinary skill in the art can make some modifications and refinements without departing from the spirit and scope of the invention. The scope of the invention is defined by the scope of the appended claims.

400‧‧‧Image Search System

410‧‧‧Input module

420‧‧‧Connection module

430‧‧‧ Computing Module

440‧‧‧Outdoor image recognition module

450‧‧‧Select module

460‧‧‧Portrait Identification Module

S105~S120‧‧‧ steps of the image searching method according to an embodiment of the present invention

1 is a flow chart of an image search method in accordance with an embodiment of the present invention.

2A and 2B are schematic diagrams of image files in accordance with an embodiment of the present invention.

FIG. 3 is a schematic diagram of a display screen according to an embodiment of the invention.

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

S105~S120. . . Each step of the image searching method according to an embodiment of the present invention

Claims (29)

An image search method includes: receiving a location information; connecting to at least one database of a network to search for a plurality of image files in the database that meet the location information; and querying images of each of the image files Information file, obtaining the shooting time of each of the image files; performing a shooting environment recognition action on the image files to identify image files taken outdoors; and according to the shooting time of the image files and the shooting environment Identifying the result of the action, listing at least one image file taken outdoors. The method of claim 1, wherein the step of listing at least one image file for outdoor shooting according to the shooting time of the image files and the result of the shooting environment recognition action comprises: according to each of the The shooting time of the image file begins with the image file closest to the current time, and the image file taken outdoors is sequenced. The method of claim 1, wherein the performing the image recognition operation on the image files to identify the image file taken outdoors comprises: starting from the image file closest to the current time, according to the The order of the image files is performed, and the shooting environment recognition actions are performed one by one for the image files to identify the image files taken outdoors. The method of claim 1, further comprising: determining whether the shooting time of each of the image files meets a preset time Within the range. The method of claim 1, wherein the location information includes a search range, and the step of searching for the image files that meet the location information includes: querying an image information file of each of the image files, and Obtaining a position coordinate of each of the image files at the time of shooting; and searching for an image file whose coordinates are located in the search range. The method of claim 5, wherein the location information comprises a keyword, a place name, a place name, a latitude and longitude, and an administrative area, by the keyword, the place name, The search range is set by the name of the attraction, the latitude and longitude, and one of the administrative regions. The method of claim 1, wherein the location information comprises a keyword, a place name, a place name, a latitude and longitude, and an administrative area. The method of claim 1, wherein the step of connecting to the network to search for the image files that meet the location information comprises: searching, in the network, a message related to the image file The image file of one of the keywords related to the location information. The method of claim 1, wherein the step of performing the shooting environment identification operation comprises: reading at least one shooting environment attribute in each of the image information files of the image files, thereby determining each of the images Whether the image file is taken outdoors. The method of claim 9, wherein the shots are The environmental properties include one of or a combination of lens aperture, exposure time, sensitivity, focal length, shutter speed, and flash mode. The method of claim 1, wherein the step of performing the shooting environment recognition action comprises: identifying whether a specific object is determined by a feature point identification method; and screening the image file having the specific object. The method of claim 1, wherein after the step of performing the outdoor shooting recognition action, the method further comprises: performing a portrait recognition action to determine whether each of the image files captured outdoors has at least one portrait . The method of claim 12, wherein the portrait recognition action comprises a face recognition action to determine whether each of the image files taken outdoors has at least one face. The method of claim 1, wherein after the step of listing at least one image file taken outdoors, the method further comprises: selecting, from the image files taken outdoors, the image having the closest shooting time to the current time. File to associate the image file with a weather message. A computer program product that loads the program via an electronic device and performs the following steps: receiving a location information; connecting to at least one database of the network to search the database for multiple image files that match the location information Query the image information files of each of the image files to obtain each The shooting time of the image files; performing a shooting environment recognition action on the image files to identify the image files taken outdoors; and according to the shooting time of the image files and the result of the shooting environment recognition action, listed in At least one image file taken outdoors. A network image search system is configured on an electronic device. The search system includes: an input module for receiving a location information; a connection module for connecting to at least one database of a network; and an operation module In the database, searching for a plurality of image files that meet the information of the location, and querying the image information files of each of the image files to obtain the shooting time of each of the image files; an outdoor image recognition module, Performing a shooting environment recognition operation on the image files to identify image files taken outdoors; and selecting a module, according to the shooting time of the image files and the result of the shooting environment recognition action, listed in the outdoor shooting At least one image file. The system of claim 16, wherein the selecting module further comprises: according to the shooting time of each of the image files, starting from the image file closest to the current time, the image files taken outdoors are sequentially sequenced. The system of claim 17, wherein the outdoor image recognition module further comprises an image file that is closest to the current time, and the image files are executed one by one according to the order of the image files. The shooting environment recognizes the action to identify image files that are taken outdoors. The system of claim 17, wherein the computing module further comprises determining whether a shooting time of each of the image files meets a predetermined time range. The system of claim 16, wherein the location information comprises a search range, and the computing module further comprises: querying an image information file of each of the image files, and obtaining each of the image files A position coordinate at the time of shooting to search for an image file whose coordinates are located in the search range. The system of claim 20, wherein the location information comprises a keyword, a place name, a place name, a latitude and longitude, and an administrative area, by the keyword, the place name, The search range is set by the name of the attraction, the latitude and longitude, and one of the administrative regions. The system of claim 16, wherein the location information comprises a keyword, a place name, a place name, a latitude and longitude, and an administrative area. The system of claim 16, wherein the computing module searches the network for the image files that match the location information, and includes, in the network, a message related to the image file. The image file of one of the keywords related to the location information. The system of claim 16, wherein the computing module reads at least one shooting environment attribute in each of the image information files of the image files, so that the outdoor image recognition module determines each of the images. files Whether the case is for outdoor shooting. The system of claim 24, wherein the photographing environment attributes include one or a combination of a lens aperture, an exposure time, a sensitivity, a shutter speed, a focal length, and a flash mode. The system of claim 16, wherein the outdoor image recognition module further comprises: identifying a specific object by using a feature point identification method, and screening the image file having the specific object to identify the image taken outdoors. file. The system of claim 16, further comprising: a portrait recognition module, performing a portrait recognition action to determine whether each of the image files captured outdoors has at least one portrait. The system of claim 27, wherein the portrait recognition action comprises a face recognition action to determine whether each of the image files taken outdoors has at least one face. The system of claim 16, wherein the computing module further comprises selecting, from the image files taken outdoors, the image file whose shooting time is closest to the current time, to associate the image file with a weather information. Union.