JP2020109610A - Plant classification system using deep running and method therefor - Google Patents

Abstract

To provide a plant classification system using deep running and a method therefor.SOLUTION: The method confirms feature points based on a monthly growth state of plant by using deep running about the leaf, trunk, branch, flower, fruit, or the like of the plant, confirms feature points of the plant based on a flowering time, a fruiting time, or the like, and confirms feature points to varieties of the plant. In the case where there is a classification request about the plant included in a specific image after converting information about the confirmed feature points into a database, the degrees of accuracy of classification about the plant in the present state are increased by providing plant information corresponding to an image from information converted into the database on the basis of meta information in the image and additional information corresponding to the plant information, and a user's satisfaction level can be increased by providing information of good quality.SELECTED DRAWING: Figure 3

Description

The present invention relates to a plant classification system using deep running and a method thereof, and particularly for leaves, stems, branches, flowers, fruits, etc. of a plant, using deep running to confirm characteristic points according to the monthly growth state of the plant, and the flowering time. , Confirm the characteristic points of the corresponding plant depending on the fruit setting time, confirm the characteristic points for the varieties of the corresponding plant, and after creating a database of information on the confirmed characteristic points, regarding the plants included in the specific image. If there is a classification request, plants that use deep running to provide plant information corresponding to the relevant image and additional information corresponding to the plant information from the information stored in the database based on the meta information in the relevant image, A classification system and method.

A wide variety of plants can be easily found around us, and more and more new plants are encountered, especially as field activity increases.

However, it is difficult for general people to identify new plants due to limited knowledge and experience of plants, and it is not easy for experts to identify all plants. ..

Although there are some examples that provide information related to the plant in a picture taken using a picture book or a mobile phone to identify the plant, it is simply a plant centered on flowers or leaves. Therefore, there is a disadvantage that the accuracy of the plant classification is low due to the fact that there are no flowers, leaves cannot be photographed well, or the state of the plant.

Korean Published Patent No. 10-2012-0076491 "Plant information providing service system and method"

The purpose of the present invention is to confirm the characteristic points according to the monthly growth state of the plant using deep running for leaves, stems, branches, flowers, fruits, etc. of the plant, and the characteristic points of the relevant plant depending on the flowering time, the fruit setting time, etc. After confirming the characteristic points for the varieties of the relevant plant and creating a database of information on the confirmed characteristic points, if there is a classification request for the plants included in a specific image, the meta It is an object of the present invention to provide a plant classification system and method using deep running, which provides plant information corresponding to the corresponding image and additional information corresponding to the plant information from the information stored in the database based on the information.

A plant classification system using deep running according to an embodiment of the present invention obtains image information including the plant for the same plant by month, and leaves, stems, branches, and flowers of plants in the obtained image information. And extracting a plurality of feature points depending on the monthly growth state for the fruit, calculating a correlation vector by the correlation between the plurality of extracted feature points, leaves, stems, branches, flowers of the plant in the acquired video information And confirm the hue and morphology respectively against the fruit, a plurality of feature point information by the monthly growth state of the extracted plant, a correlation vector by the correlation between the plurality of feature points, the leaf of the corresponding plant confirmed, stem, A server for storing a database of plant information including hues and forms of branches, flowers, fruits, etc., detailed information related to the plant and additional information about the management method of the plant; and other images related to the specific plant. A terminal for transmitting the plant classification request information including the information and the identification information of the terminal to the server may be included.

As an example related to the present invention, the correlation vector may include distance and direction information between feature points.

As an example related to the present invention, the server may include one or more feature points associated with the extracted leaf, one or more feature points associated with the extracted trunk, and one or more feature points associated with the extracted branch. A leaf, a stem, a branch, and a flower are calculated by calculating one or more feature points, one or more feature points associated with the extracted flower, and one or more correlation vectors between the one or more feature points associated with the extracted fruit. And you can check the actual characteristics.

As an example related to the present invention, the server confirms the meta information in the other image information included in the plant classification request information, and the object in the other image information included in the plant classification request information is a plant. If the object in the other image information is a plant as a result of the determination, the server causes the leaves, trunks, branches, flowers and fruits to the object in the other image information. A plurality of other feature points to, and calculates another correlation vector by the correlation between the extracted plurality of other feature points, of the object in the other video information included in the plant classification request information Confirming the hue and morphology of leaves, stems, branches, flowers and fruits, a plurality of feature points associated with a plurality of plants by month in the plant information stored in the database and a correlation vector associated with the plurality of relevant feature points. From among the at least one characteristic point associated with a plurality of plants corresponding to the specific month corresponding to the confirmed meta-information and the correlation vector associated with at least one corresponding characteristic point is confirmed, and the confirmed specific month At least one feature point associated with a plurality of plants corresponding to and a plurality of other feature points associated with the extracted specific plant from among the correlation vectors associated with the relevant at least one feature point and the calculated other The similarity between correlation vectors is calculated respectively, the plant information having the highest similarity among the calculated plurality of similarities is confirmed, and detailed information and additional information included in the confirmed plant information are transmitted to the terminal. However, the terminal may display detailed information and additional information related to the specific plant transmitted from the server in response to the transmitted plant classification request information.

A plant classification method using deep running according to an embodiment of the present invention includes a step of acquiring video information including the plant for the same plant by a server by month; the server includes the plants in the acquired video information. Extracting a plurality of feature points according to monthly growth conditions for leaves, trunks, branches, flowers, and fruits; calculating a correlation vector based on the correlation between the extracted plurality of feature points by the server; the server Confirming the hue and morphology of the leaves, stems, branches, flowers, and fruits of the plant in the acquired image information according to the above; , A correlation vector by a correlation between the plurality of characteristic points, the hue and morphology of the leaves, stems, branches, flowers, fruits and the like of the identified corresponding plant, detailed information related to the plant and a method for managing the plant. The method may include a step of storing the plant information including the additional information in a database.

As an example related to the present invention, the step of calculating the correlation vector includes a step of calculating a correlation vector between a feature point of a leaf central portion and at least one other adjacent feature point adjacent to the relevant feature point; Calculating a correlation vector between the feature point of the part and at least one other adjacent feature point adjacent to the corresponding feature point; the feature point of the central part of the branch and at least one other adjacent feature point adjacent to the corresponding feature point Calculating a correlation vector between the feature points of the central portion of the flower and at least one other adjacent feature point adjacent to the relevant feature point; and corresponding to the feature point of the actual central portion The method may include at least one step of calculating a correlation vector between at least one other adjacent feature point adjacent to the feature point.

As an example related to the present invention, the terminal transmits the plant classification request information including other image information related to a specific plant and the identification information of the terminal to the server; the server transmits the identification information of the plant classification information from the terminal. Confirming the meta information in the other video information included in the plant classification request information; the server determines whether the object in the other video information included in the plant classification request information is a plant. When the result of the determination is that the object in the other video information is a plant, the server causes a plurality of other characteristics of leaves, trunks, branches, flowers, and fruits for the object in the other video information. Extracting points; calculating another correlation vector according to the correlation between the extracted plurality of other feature points by the server; other image information included in the plant classification request information by the server The hues and morphology of leaves, stems, branches, flowers and fruits of the objects in the above; a plurality of characteristic points and corresponding plurality associated with a plurality of plants in each month in the plant information stored in the database by the server From among the correlation vectors associated with the feature points, at least one feature point associated with a plurality of plants corresponding to the specific month corresponding to the confirmed meta-information and a correlation vector associated with the corresponding at least one feature point, A step of confirming; by the server, the specific plant extracted from at least one feature point associated with the plurality of plants corresponding to the identified specific month and the correlation vector associated with the corresponding at least one feature point; Calculating a similarity between a plurality of other related feature points and the calculated other correlation vector; checking the plant information having the largest similarity among the calculated plurality of similarities by the server Transmitting the detailed information and additional information included in the confirmed plant information to the terminal by the server; and transmitting from the server in response to the transmitted plant classification request information by the terminal. The method may further include displaying detailed information and additional information related to the specific plant.

The present invention confirms the characteristic points of the plant according to the monthly growth state of the plant using deep running for leaves, stems, branches, flowers, fruits, etc. of the plant, and confirms the characteristic points of the corresponding plant depending on the flowering time and the fruit setting time. Then, after confirming the characteristic points for the varieties of the relevant plant, and after making a database of information on the confirmed characteristic points, if there is a classification request for the plants included in a specific image, the meta information in the relevant image By providing additional information corresponding to the plant information and the plant information corresponding to the image from the information in the database based on the above, the classification accuracy of the plant in the current state is increased, and high-quality information is provided. There is an effect that can be provided to increase user satisfaction.

The block diagram which showed the structure of the plant classification system which used the deep running which concerns on the Example of this invention. Block diagram showing the configuration of a server according to an embodiment of the present invention Flowchart showing a plant classification method using deep running according to an embodiment of the present invention Explanatory diagram showing an example of the screen of the terminal according to the embodiment of the present invention

The technical terms used in the present invention are merely used to describe specific embodiments, and are not intended to limit the present invention. Further, the technical terms used in the present invention are generally understood by a person having ordinary knowledge in the technical field to which the present invention belongs, unless otherwise defined in the present invention, and are interpreted in an excessively comprehensive sense. Not be interpreted or interpreted in a way that is excessively reduced. When the technical terms used in the present invention are incorrect technical terms that cannot accurately express the idea of the present invention, they are understood by being replaced with technical terms that can be understood by those skilled in the art. Also, the general terms used in the present invention shall be interpreted as defined in the dictionary or in the context of the context, and should not be interpreted in an excessively reduced sense.

Also, the singular expressions used in the present invention include plural expressions unless the context clearly dictates otherwise. In the present invention, terms such as "constituted" or "including" should not be construed as necessarily including all the various components or various steps described in the invention, and some of the components or Some steps may not be included or may additionally include additional components or steps.

Also, terms including ordinal numbers such as the first, second, etc. used in the present invention may be used to describe components, but the components should not be limited by the terms. The term is used only to distinguish one element from another. For example, the first component may be named the second component and similarly the second component may be labeled the first component without departing from the scope of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. To do.

Further, in the description of the present invention, a detailed description of known related art will be omitted when it may make the subject matter of the present invention unclear. Further, the attached drawings are only for making the idea of the present invention easily understandable, and the idea of the present invention is not limited by the attached drawings.

FIG. 1 is a block diagram showing a configuration of a plant classification system 10 using deep running according to an exemplary embodiment of the present invention.

As shown in FIG. 1, a plant classification system 10 using deep running includes a server 100 and a terminal 200. Not all of the components of the plant classification system 10 illustrated in FIG. 1 are essential components, and the plant classification system 10 may be embodied by more components than the components illustrated in FIG. 1. The plant classification system 10 may be embodied with fewer components.

Further, as illustrated in FIG. 2, the server 100 includes a communication unit 110, a storage unit 120, a display unit 130, a voice output unit 140, and a control unit 150. Not all of the components of the server 100 illustrated in FIG. 2 are indispensable components, and the server 100 may be embodied with more components than the components illustrated in FIG. 2, or less. The server 100 may be embodied by the components.

The communication unit 110 connects communication with any internal component or at least one external terminal through a wired/wireless communication network. At this time, the external terminal may include the terminal 200, another terminal (not shown), or the like. Here, as the wireless internet technology, a wireless LAN (WLAN), a DLNA (registered trademark) (Digital Living Network Alliance), a wireless broadband (Wireless Broadband: Wibro (registered trademark)), and a WiMAX (World Interoperability). Access: Wimax), HSDPA (High Speed Downlink Packet Access), HSUPA (High Speed Uppack Access), IEEE 80g, Long Term Evolution (Long Term), Long Term Evolution (Long Term), Long Term Evolution (Long Term), HSEPA (High Speed Uplink Packet Access), IEEE 802. There is a broadband wireless mobile communication service (WMBS), etc., and the communication unit 110 transmits/receives data by at least one wireless internet technology within a range including internet technologies not listed above. .. In addition, as short-distance communication technology, Bluetooth (registered trademark) (Bluetooth (registered trademark)), RFID (Radio Frequency Identification), infrared communication (Infrared Data Association: IrDA), UWB (Ultra Wideband, B), jig (BIG). Adjacent magnetic field communication (Near Field Communication: NFC), ultrasonic communication (Ultra Sound Communication: USC), visible light communication (Visible Light Communication: VLC), Wi-Fi (Wi-Fi), Wi-Fi Direct, etc. May be included. In addition, the wire communication technology may include power line communication (PLC), USB communication, Ethernet (registered trademark) (Ethernet), serial communication (serial communication), optical/coaxial cable, and the like.

In addition, the communication unit 110 may transmit information to and from an arbitrary terminal through a universal serial bus (USB).

Also, the communication unit 110 may be a technical standard or a communication method for mobile communication (eg, GSM (registered trademark) (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access). EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (registered trademark) (Wideband CDMA), HSDPA (High Speed DownHackPlace) ), LTE-A (Long Term Evolution-Advanced), etc.), a radio signal is transmitted/received to/from a base station, the terminal 200, the other terminal, or the like on a mobile communication network.

Also, the communication unit 110 receives various information transmitted from the terminal 200, including plant classification request information including image information related to a specific plant, identification information of the terminal 200, and the like.

The storage unit 120 stores various user interfaces (UI), graphic user interfaces (GUI), and the like.

In addition, the storage unit 120 stores data and programs necessary for the operation of the server 100.

That is, the storage unit 120 may store a large number of application programs or applications driven by the server 100, data for operating the server 100, and command words. At least some of such applications may be downloaded from an external server via wireless communication. In addition, at least a part of such application programs may exist on the server 100 from the beginning of shipping due to the basic functions of the server 100. Meanwhile, the application may be stored in the storage unit 120, installed in the server 100, and driven by the control unit 150 to perform the operation (or function) of the server 100.

In addition, the storage unit 120 may include a flash memory type (Flash Memory Type), a hard disk type (Hard Disk Type), a multimedia card micro type (Multimedia Card Micro Type), a card type memory (for example, SD or XD memory), Own memory, magnetic disk, optical disk, ram (Random Access Memory: RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory Memory: ROM), EEPROM (Electrically Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM) The storage medium may include at least one storage medium of Read-Only Memory). In addition, the server 100 may operate a web storage that performs a storage function of the storage unit 120 on the Internet, or may operate in association with the web storage.

In addition, the storage unit 120 stores the received various information under the control of the control unit 150.

The display unit (or display unit) 130 is controlled by the control unit 150 and uses the user interface and/or the graphic user interface stored in the storage unit 120 to perform various contents such as various menu screens. Can be displayed. Here, the content displayed on the display unit 130 includes various text or image data (including various information data) and a menu screen including data such as icons, list menus, and combo boxes. In addition, the display unit 130 may be a touch screen.

In addition, the display unit 130 includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED) flexible display (OLED), and a thin film transistor liquid crystal display (TFT LCD). At least one of a flexible display, a three-dimensional display (3D display), an electronic ink display (e-ink display), and an LED (Light Emitting Diode) may be included.

In addition, the display unit 130 displays various received information under the control of the control unit 150.

The audio output unit 140 outputs audio information included in a signal processed into a predetermined signal by the control unit 150. Here, the audio output unit 140 may include a receiver, a speaker, a buzzer, and the like.

Also, the voice output unit 140 outputs the guide voice generated by the control unit 150.

Also, the voice output unit 140 outputs voice information (or a sound effect) corresponding to the various information received by the control unit 150.

The controller 150 or the micro controller unit (MCU) 150 performs general control functions of the server 100 for the radar system.

In addition, the control unit 150 uses the programs and data stored in the storage unit 120 to execute general control functions of the server 100. The controller 150 may include a RAM, a ROM, a CPU, a GPU, and a bus, and the RAM, the ROM, the CPU, and the GPU may be connected through the bus. The CPU may access the storage unit 120 and perform booting using the O/S stored in the storage unit 120, and may store various programs, contents, data, etc. stored in the storage unit 120. It can be used to perform various actions.

In addition, the control unit 150 acquires (or captures) image information including the corresponding plant for the same plant by month (or by season/by season).

That is, the control unit 150 acquires image information including plants so that the state of the plants can be confirmed monthly for one year and 12 months. At this time, the server 100 may acquire image information including an arbitrary plant through a camera unit (not shown) included in the corresponding server 100, or an arbitrary plant provided from another terminal or another server. The image information including the information may be received through the communication unit 110.

In addition, the control unit 150 extracts (or confirms) a plurality of feature points according to the monthly growth state of leaves, stems, branches, flowers, fruits, etc. of the plant in the captured (or acquired) image information.

That is, the control unit 150 extracts a plurality of feature points for each image information of the same plant photographed for each month.

The controller 150 also calculates a correlation vector based on the correlation between the extracted plurality of feature points. At this time, the correlation vector includes information such as a distance (or size) between feature points and a direction based on an arbitrary reference feature point.

That is, the control unit 150 calculates a correlation vector between the feature point of the center part of the leaf (or one side of the leaf) and at least one other adjacent feature point adjacent to the corresponding feature point, and determines the feature of the center part of the trunk. A correlation vector between a point and at least one other adjacent feature point adjacent to the corresponding feature point, and a correlation vector between the feature point at the center of the branch and at least one other adjacent feature point adjacent to the relevant feature point. Then, a correlation vector between the feature point of the central part of the flower and at least one other adjacent feature point adjacent to the corresponding feature point is calculated, and the feature point of the actual center part and at least one adjacent to the corresponding feature point are calculated. Calculate the correlation vector between two other adjacent feature points to identify features (or morphology) such as leaves, stems, branches, flowers, and fruits.

The control unit 150 may include one or more feature points associated with the extracted leaf, one or more feature points associated with the extracted trunk, one or more feature points associated with the extracted branch, and Calculate one or more feature points associated with the extracted flowers and one or more correlation vectors between the one or more feature points associated with the extracted fruits, and calculate the relationship between leaves, stems, branches, flowers, and fruits. Check the characteristics (or morphology).

At this time, the control unit 150 not only performs a function of extracting a feature point and a correlation vector of a relevant plant according to image information of the same plant photographed each month, but also a specific time associated with the relevant plant. It is also possible to perform the function of extracting the characteristic points of the relevant plant and calculating the related correlation vector with respect to the flowering time and the fruit setting time.

In addition, the control unit 150 not only extracts the monthly characteristic points of the corresponding plant corresponding to the original and calculates the related correlation vector, but also when there is a variety plant related to the plant, leaves associated with the variety plant It is also possible to extract a plurality of feature points for the trunk, branches, flowers, fruits, etc., and to calculate a correlation vector for the plurality of feature points associated with the extracted variety plant.

In addition, the control unit 150 can also confirm (or detect) the hue and morphology (or shape) of leaves, stems, branches, flowers, fruits, etc. of the corresponding plant through a preset image analysis method.

In this way, the controller 150 analyzes the image information and acquires (or collects) various information related to the plant.

In addition, the control unit 150 can grasp (or confirm) characteristics of leaves, stems, branches, flowers, fruits, etc. of a corresponding plant by time (or by month) through the corresponding image information analysis. The plant classification (or plant judgment/search) for a specific plant can be easily performed based on the obtained information (or characteristics).

In addition, the control unit 150 includes a plurality of feature point information according to the confirmed growth status of the plant by month, a correlation vector based on a correlation between the plurality of feature points, leaves, stems, branches, flowers, fruits, etc. of the confirmed corresponding plant. The plant information including the hue and morphology, detailed information related to the relevant plant, and additional information regarding the management method of the relevant plant is converted into a database and stored in the storage unit 120. At this time, the control unit 150 may also store the plant-specific plant information in the database in a separate independent database (DB) (not shown).

As described above, the controller 150 may provide an image of leaves, stems, branches, flowers, fruits, etc. of a plant for any plant by month and/or by a specific time (including a flowering time, a fruit setting time, etc.) After extracting a plurality of feature points based on the information, a correlation vector can be calculated based on the correlation between the extracted plurality of feature points.

In addition, as described above, the control unit 150 continuously outputs information about the corresponding feature points and the correlation vector through the deep running learning method to the plurality of monthly feature points and the correlation vector extracted for the arbitrary plant. Can be updated (or managed).

In addition, the controller 150 acquires the monthly and/or specific point-in-time image information according to plant varieties through a deep running learning method, extracts a plurality of feature points in the acquired image information, and associates the related vector. It is possible to provide a systematic management function for plant information based on big data by executing the process of calculating.

Also, the controller 150 receives plant classification request information including image information related to a specific plant transmitted from the terminal 200, identification information of the terminal 200, and the like through the communication unit 110.

Also, the controller 150 confirms (or extracts) the meta information in the video information included in the received plant classification request information. At this time, the meta information includes shooting date and time information (or month information at the time of shooting), illuminance information, and the like when the corresponding video information is shot.

That is, the controller 150 confirms the meta information in the corresponding image information in order to confirm the time when the image information included in the corresponding plant classification request information is captured, and determines the month when the corresponding image information is captured. ) Confirm.

Also, the controller 150 extracts a plurality of feature points associated with an object (or a specific plant) in the image information included in the received plant classification request information.

Further, the control unit 150 calculates another correlation vector between the extracted plurality of feature points.

That is, the controller 150 determines whether the object in the image information included in the received plant classification request information is a plant.

As described above, the control unit 150 confirms the characteristics of the corresponding object in the image information included in the received plant classification request information through a preset object recognition algorithm or the like, and confirms the confirmed object. Whether or not the object is a plant can be determined based on the characteristics of.

If the object in the image information included in the received plant classification request information is not a plant as a result of the determination, the controller 150 determines that the object in the image information included in the corresponding plant classification request information is not a plant. The information indicating that is provided to the corresponding terminal 200 through the communication unit 110, and the whole process is completed.

As a result of the determination, if the object in the image information included in the received plant classification request information is a plant, the controller 150 determines whether the object in the image information includes leaves, trunks, branches, flowers, and fruits. On the other hand, a plurality of feature points are extracted (or confirmed).

Also, the control unit 150 calculates the other correlation vector based on the correlation between the extracted plurality of feature points. At this time, the other correlation vector includes information such as a distance (or size) between feature points and a direction based on an arbitrary reference feature point.

That is, the control unit 150 calculates and extracts another correlation vector between the feature point of the central portion of the leaf associated with the extracted object and at least one other adjacent feature point adjacent to the corresponding feature point. Calculate another correlation vector between the feature point of the central part of the trunk associated with the target object and at least one other adjacent feature point adjacent to the target feature point, and extract the correlation vector of the extracted central part of the branch associated with the target object. Another correlation vector between the feature point and at least one other adjacent feature point adjacent to the feature point is calculated, and the feature point of the central portion of the flower associated with the extracted object of interest and at least adjacent to the feature point of interest. Another correlation vector between one other adjacent feature point is calculated, and another between the extracted feature point of the actual central part associated with the corresponding object and at least one other adjacent feature point adjacent to the corresponding feature point. The correlation vector of is calculated to confirm the characteristics (or morphology) of the target object such as leaves, stems, branches, flowers, and fruits.

In addition, the controller 150 may include at least one feature point associated with the leaf corresponding to the extracted target object, at least one feature point associated with the trunk corresponding to the extracted target object, and the extracted corresponding object. One or more feature points associated with the branch corresponding to, one or more feature points associated with the flower corresponding to the extracted object, one or more features associated with the fruit corresponding to the extracted object One or more other correlation vectors between points are calculated to identify the features (or morphology) between leaves, stems, branches, flowers and fruits.

As described above, the control unit 150 may confirm the characteristics of the object plant in the image information included in the corresponding plant classification request information by using the parameters that can confirm the characteristics of the corresponding plant (for example, extraction of a feature point, a part It is possible to calculate (or confirm) the correlation between different feature points and the like.

In addition, the controller 150 determines the hue and shape (or shape) of the object leaf, trunk, branch, flower, fruit, etc. in the image information included in the relevant plant classification request information through the preset image analysis method. It can also be confirmed (or detected).

In addition, the control unit 150 may select a month corresponding to the confirmed (or extracted) meta information from the plant information stored in the database of the storage unit 120 (or a preset interval based on the relevant month (for example, (1 month) only period/range including before/after), the plurality of feature points associated with the extracted specific plant and the calculated other correlation vector (or the specified specific plant) Confirm (or search) the plant information corresponding to another correlation vector calculated based on a plurality of feature points associated with.

That is, the control unit 150 identifies the extracted feature points from a plurality of feature points associated with a plurality of plants for each month in the plant information stored in the storage unit 120 and a correlation vector associated with the plurality of feature points. A plurality of feature points associated with the plant and the similarity between the calculated other correlation vectors are respectively calculated, and the plant information having the highest similarity among the calculated plurality of similarities is confirmed (or searched).

At this time, the control unit 150, in order to reduce the confirmation time and improve the accuracy of the search, a plurality of feature points associated with a plurality of monthly plants in the database of plant information and a plurality of relevant feature points. At least one characteristic point associated with a plurality of plants corresponding to a specific month (or a specific period including the specific month) corresponding to the confirmed (or extracted) meta information from the related correlation vectors, and corresponding at least From each of the correlation vectors associated with one feature point, a plurality of feature points associated with the extracted specific plant and the calculated similarity between the other correlation vectors, respectively, are calculated. You can also check the plant information that has the highest degree of similarity. Here, the plant information is a plurality of feature point information, a correlation vector based on the correlation between a plurality of feature points, the hue and morphology of the confirmed relevant plant leaves, stems, branches, flowers, fruits, etc., related to the relevant plant. Detailed information and additional information on the management method of the plant in question. In addition, detailed information related to the plant is the general name (or distribution name), scientific name, English name, family name, place of origin, classification, growth form, growth height (cm), growth width (cm), ecology of the plant. Includes pattern, leaf pattern, leaf color, scent, breeding method, etc. Further, the additional information includes management level, management requirement, light requirement, location, growth rate, optimum temperature for growth, minimum temperature in winter, humidity, fertilizer, soil, watering (for example, according to spring, summer, autumn, winter). Watering), pest damage, pest management, functional information, etc.

In addition, the control unit 150 transmits detailed information, additional information, etc. included in the confirmed (or searched) plant information to the terminal 200 through the communication unit 110.

Further, the control unit 150 outputs detailed information, additional information, etc. included in the confirmed (or searched) plant information through the display unit 130 and/or the voice output unit 140.

The terminal 200 is a smartphone (Smart Phone), a portable terminal (Portable Terminal), a mobile terminal (Mobile Terminal), a portable terminal (Foldable Terminal), a personal information terminal (Personal Digital Assistant: PDAT), PMP (PAT). Player terminal, Telematics terminal, Navigation terminal, Personal computer, Laptop PC, Slate PC, Tablet PC (Tablet PC), Ultrabook (Ultrabook), Wearable. Devices (Wearable Devices, for example, watch type terminals (Smartwatch), glass type terminals (Smart Glass), HMDs (Head Mounted Display), etc.), wireless broadband (Wibro) terminals, IPTV (Internet Protocol) terminals. Terminal, smart TV, digital broadcasting terminal, AVN (Audio Video Navigation) terminal, A/V (Audio/Video) system, flexible terminal (Flexible Terminal), digital signage device, etc. Can be applied.

In addition, the terminal 200 may be configured to include respective components corresponding to the communication unit 110, the storage unit 120, the display unit 130, the voice output unit 140, and the control unit 150, which configure the server 100. it can.

Also, the terminal 200 communicates with the server 100, another terminal, and the like.

In addition, the terminal 200 acquires (or captures) image information related to a specific plant through a camera (not shown) included in the terminal 200. At this time, the image information related to the specific plant may be in the form of an image or a moving image, and may be image information of the specific plant photographed by the corresponding terminal 200 or another terminal (not shown). It may be video information including the specific plant provided by.

That is, when the detailed information about a specific plant in the acquired image information is to be confirmed, the terminal 200 generates plant classification request information including image information related to the specific plant.

Also, the terminal 200 transmits the generated plant classification request information, the identification information of the terminal 200, etc. to the server 100. Here, the identification information of the terminal 20 includes MDN (Mobile Directory Number), mobile IP, mobile MAC, Sim (subscriber identity module) card unique information, and serial number.

In addition, the terminal 200 receives the detailed information and the additional information related to the specific plant transmitted from the server 100 in response to the plant classification request information transmitted in advance.

In addition, the terminal 200 displays the received detailed information, additional information, image information related to a specific plant included in the plant classification request information, and the like.

In the embodiment of the present invention, the terminal 200 transmits the plant classification request information including the image information related to the specific plant to the server 100, and the related plant information and additional information from the server 100 are transmitted. However, the present invention is not limited to this, and the terminal 200 may receive the plant classification request information transmission function and the response information reception through a dedicated application installed in the corresponding terminal 200. The plant classification request information transmitting function and the response information receiving function may be performed by connecting to a website provided by the server 100.

In this way, by using deep running on the leaves, stems, branches, flowers, fruits, etc. of the plant, the characteristic points of the plant according to the monthly growth state are confirmed, and the characteristic points of the relevant plant depending on the flowering time, fruit setting time, etc. are confirmed. Then, after confirming the characteristic points for the varieties of the relevant plant, and after making a database of information on the confirmed characteristic points, if there is a classification request for the plants included in a specific image, the meta information in the relevant image Based on the information stored in the database, it is possible to provide plant information corresponding to the corresponding image and additional information corresponding to the plant information.

Hereinafter, a plant classification method using deep running according to the present invention will be described in detail with reference to FIGS.

FIG. 3 is a flowchart showing a plant classification method using deep running according to an embodiment of the present invention.

First, the server 100 obtains (or shoots) video information including a corresponding plant for the same plant by month (or by season/by season).

That is, the server 100 acquires image information including plants so that the state of the plants can be confirmed monthly for 1 year and 12 months.

In addition, the server 100 extracts (or confirms) a plurality of feature points depending on a monthly growth state of leaves, trunks, branches, flowers, fruits, etc. of the plant in the captured (or acquired) image information.

That is, the server 100 extracts a plurality of feature points for each image information of the same plant photographed each month.

The server 100 also calculates a correlation vector based on the correlation between the extracted feature points. At this time, the correlation vector includes information such as a distance (or size) between feature points and a direction based on an arbitrary reference feature point.

That is, the server 100 calculates a correlation vector between the feature point of the central part of the leaf (or one side of the leaf) and at least one other adjacent feature point adjacent to the corresponding feature point, and the feature point of the central part of the trunk is calculated. And a correlation vector between at least one other adjacent feature point adjacent to the relevant feature point, and a correlation vector between the feature point at the center of the branch and at least one other adjacent feature point adjacent to the relevant feature point. Calculate the correlation vector between the feature point of the central part of the flower and at least one other adjacent feature point adjacent to the relevant feature point, and calculate the correlation vector between the feature point of the actual central part and at least one adjacent feature point. By calculating the correlation vector between other adjacent feature points, the features (or morphology) of leaves, trunks, branches, flowers, fruits, etc. are confirmed.

The server 100 may include one or more feature points associated with the extracted leaf, one or more feature points associated with the extracted trunk, one or more feature points associated with the extracted branch, and the extraction. One or more feature points associated with the extracted flower and one or more correlation vectors between the one or more feature points associated with the extracted fruit, and the feature between the leaves, the trunk, the branches, the flower, and the fruit. Check (or form).

At this time, the server 100 not only performs a function of extracting a feature point and a correlation vector of a corresponding plant according to image information of the same plant photographed each month, but also performs a flowering at a specific time associated with the plant. It is also possible to perform the function of extracting the characteristic points of the corresponding plant with respect to the time, the fruit setting time, etc. and calculating the related correlation vector.

In addition, the server 100 not only extracts the monthly characteristic points of the corresponding plant corresponding to the original and calculates the related correlation vector, but also when there is a variety plant related to the plant, leaves associated with the variety plant, It is also possible to extract a plurality of feature points for stems, branches, flowers, fruits, etc. and to calculate a correlation vector for a plurality of feature points associated with the extracted variety plant.

In addition, the server 100 may also confirm (or detect) the hue and morphology (or shape) of leaves, stems, branches, flowers, fruits, etc. of the corresponding plant through a preset image analysis method.

In this way, the server 100 analyzes the image information and acquires (or collects) various information related to the plant.

As an example, the server 100 captures image information including each plant from January to December for each plant type on the first day of every month. At this time, the plant in question may be in a natural state or in an artificial facility.

Also, the server 100 extracts a plurality of feature points for each month from leaves, trunks, branches, flowers, fruits, etc. of the plant in the image information photographed each month.

In addition, the server 100 may include one or more feature points associated with the leaves extracted by the month, one or more feature points associated with the trunk extracted by the month, and one or more feature points associated with the branches extracted by the month. , One or more feature points associated with the flowers extracted by the month, and one or more correlation vectors between the one or more feature points associated with the fruit extracted by the month. At this time, the calculated correlation vector may be in a state of being arranged monthly (for example, a correlation between leaves, stems, branches, flowers, and fruits for each of January to December).

In addition, the server 100 confirms the hue and morphology of the leaves, stems, branches, flowers, fruits, etc. of the plant in the image information photographed for each month (S310).

After that, the server 100 stores a plurality of characteristic point information according to the confirmed monthly growth status of the plant, a correlation vector based on a correlation between the plurality of characteristic points, leaves, stems, branches, flowers, fruits, etc. of the confirmed corresponding plant. The plant information including the hue and morphology, detailed information related to the relevant plant, and additional information on the management method of the relevant plant is stored in a database.

As described above, the server 100 may provide image information on leaves, stems, branches, flowers, fruits, etc. of a plant for any plant by month and/or at a specific time point (including flowering time, fruit setting time, etc.). After extracting a plurality of feature points based on the above, a correlation vector can be calculated based on the correlation between the extracted plurality of feature points.

Further, as described above, the server 100 continuously updates the information on the feature points and the correlation vector for the plurality of monthly feature points and the correlation vector extracted for the arbitrary plant through the deep running learning method. (Or managed).

Also, the server 100 obtains the image information for each month and/or a specific time point according to the variety of the plant through the deep running learning method, extracts a plurality of feature points in the obtained image information, and associates the associated correlation vector. By performing a calculation process and the like, it is possible to provide a systematic management function for plant information based on big data.

As an example, the server 100 may extract feature numbers of fortune numbers extracted by month according to plant varieties, correlation vectors associated with the corresponding feature points, and hues and shapes of leaves, stems, branches, flowers, and fruits of the plants. , Detailed information related to the relevant plant, additional information about the method of feeding the relevant plant, and the like are stored as a database (S320).

Then, the terminal 200 transmits the plant classification request information including the image information related to the specific plant, the identification information of the terminal 200, etc. to the server 100. At this time, the image information related to the specific plant may be in the form of an image or a moving image, and may be image information of the specific plant photographed by the corresponding terminal 200 or another terminal (not shown). It may be image information including the specific plant provided by. Further, the identification information of the terminal 200 includes MDN, mobile IP, mobile MAC, SIM (subscriber identification module) card unique information, serial number and the like.

As an example, the first terminal 200 captures first image information including a first plant (eg, Sansevieria) through a camera (not shown) included in the corresponding first terminal under user control of the corresponding first terminal, and First plant classification request information for requesting detailed information for the first plant is generated based on the first image information including the captured first plant.

In addition, the first terminal transmits the generated first plant classification request information, identification information of the first terminal, etc. to the server 100 (S330).

Thereafter, the server 100 receives plant classification request information including image information related to a specific plant, identification information of the terminal 200, etc. transmitted from the terminal 200.

Also, the server 100 confirms (or extracts) the meta information in the image information included in the received plant classification request information. At this time, the meta information includes shooting date and time information (or month information at the time of shooting), illuminance information, and the like when the corresponding video information is shot.

Also, the server 100 extracts a plurality of feature points associated with an object (or a specific plant) in the image information included in the received plant classification request information.

Further, the server 100 calculates another correlation vector between the extracted plurality of feature points.

That is, the server 100 determines whether the object in the image information included in the received plant classification request information is a plant.

As a result of the determination, if the object in the image information included in the received plant classification request information is a plant, the server 100 determines that the object in the image information includes leaves, trunks, branches, flowers, and fruits. To extract (or confirm) multiple feature points.

Also, the server 100 calculates the other correlation vector based on the correlation between the extracted plurality of feature points. At this time, the other correlation vector includes information such as a distance (or size) between feature points and a direction based on an arbitrary reference feature point.

That is, the server 100 calculates another correlation vector between the feature point of the central portion of the leaf related to the extracted target object and at least one other adjacent feature point adjacent to the corresponding feature point, and extracts the extracted corresponding vector. The feature of the central portion of the branch associated with the extracted target object is calculated by calculating another correlation vector between the feature point of the central portion of the trunk associated with the object and at least one other adjacent feature point adjacent to the corresponding feature point. Another correlation vector between the point and at least one other adjacent feature point adjacent to the relevant feature point is calculated, and the feature point of the central portion of the flower associated with the extracted relevant object and at least one adjacent to the relevant feature point are calculated. Another correlation vector between two other adjacent feature points is calculated, and another feature vector between the extracted feature point of the actual central part and the at least one other adjacent feature point adjacent to the relevant object is extracted. The correlation vector is calculated to confirm the characteristics (or morphology) of the target object such as leaves, trunks, branches, flowers, and fruits.

In addition, the server 100 may include one or more feature points associated with the leaf corresponding to the extracted target object, one or more feature points associated with the trunk corresponding to the extracted target object, and the extracted target object. One or more feature points associated with the corresponding branch, one or more feature points associated with the flower corresponding to the extracted target object, one or more feature points associated with the fruit corresponding to the extracted target object One or more other intervening correlation vectors are calculated to identify features (or morphology) between leaves, stems, branches, flowers and fruits.

Also, the server 100 confirms the hue and form (or shape) of the object leaf, trunk, branch, flower, fruit, etc. in the image information included in the relevant plant classification request information through the preset image analysis method. (Or detected).

For example, the server 100 receives the first plant classification request information, the identification information of the first terminal, etc. transmitted from the first terminal.

Also, the server 100 confirms the meta information (eg, December 01, 2018 03:30:15 PM) in the first video information included in the first plant classification request information.

In addition, the server 100 determines whether the object in the first image information included in the first plant classification request information is a plant, and determines that the object is a plant when the object is a plant. Extract multiple feature points for leaves, trunks, branches, flowers, fruits, etc.

In addition, the server 100 may include one or more feature points associated with a leaf for the extracted object, one or more feature points associated with a trunk, one or more feature points associated with a branch, and one feature point associated with a flower. Compute one or more feature points and one or more other correlation vectors between one or more feature points associated with the fruit, respectively.

In addition, the server 100 confirms the hue and form of the object leaf, trunk, branch, flower, fruit, etc. in the first image information (S340).

After that, the server 100 selects a month corresponding to the confirmed (or extracted) meta information from the plant information stored in the database (or only a preset interval (for example, one month) based on the relevant month). A plurality of feature points related to the extracted specific plant and the calculated other correlation vectors (or a plurality of related vectors related to the specified specific plant) are used for the plant information related to the period/range including before/after). Confirm (or search) the plant information corresponding to another correlation vector calculated based on the feature points.

That is, the server 100 is associated with the extracted specific plant from a plurality of feature points associated with a plurality of monthly plants in the database information stored in the database and a correlation vector associated with the plurality of relevant feature points. The similarity between the plurality of feature points and the calculated other correlation vector is calculated, and the plant information having the highest similarity among the calculated plurality of similarities is confirmed (or searched). At this time, the server 100 relates to a plurality of feature points associated with a plurality of monthly plants in the database of plant information and a plurality of relevant feature points in order to reduce the confirmation time and increase the accuracy of the search. At least one characteristic point associated with a plurality of plants corresponding to a specific month (or a specific period including the specific month) corresponding to the confirmed (or extracted) meta information from the correlation vector and at least one corresponding The similarity between the plurality of feature points associated with the extracted specific plant and the calculated other correlation vectors from the correlation vectors associated with the feature points is calculated, and the similarity among the plurality of calculated similarities is calculated. You can also check the plant information with the highest degree. Here, the plant information is a plurality of feature point information, a correlation vector based on the correlation between a plurality of feature points, the hue and morphology of the confirmed relevant plant leaves, stems, branches, flowers, fruits, etc., related to the relevant plant. Detailed information and additional information on the management method of the plant in question. In addition, detailed information related to the relevant plant is the general notation name (or distribution name), scientific name, English name, family name, place of origin, classification, growth form, birth height (cm), growth width (cm), of the relevant plant. Includes ecotype, leaf pattern, leaf color, scent, breeding method, etc. Further, the additional information includes management level, management requirement, light requirement, location, growth rate, optimum temperature for growth, minimum temperature in winter, humidity, fertilizer, soil, watering (for example, according to spring, summer, autumn, winter). Watering), pest damage, pest management, functional information, etc.

Further, the server 100 transmits detailed information, additional information, etc. included in the confirmed (or searched) plant information to the terminal 200.

As an example, the server 100 may include a plurality of feature points associated with a plurality of plants for each month in the plant information stored in the database and a correlation vector associated with the plurality of feature points in the confirmed first image information. 12 associated with a specific month (for example, December) corresponding to the meta information (for example, 03:30:15 pm, December 01, 2018) (or November-January around December, which is the corresponding specific month) Leaves, trunks, branches, and flowers for the object extracted from at least one feature point associated with the plurality of plants and the correlation vector associated with the at least one feature point extracted based on the image information acquired in the month , A similarity between a plurality of feature points associated with the actual and one or more other correlation vectors associated with the corresponding feature points is calculated, and the similarity is the highest among the calculated plurality of similarities. Confirm the 11th plant information (for example, plant information related to Sansevieria).

In addition, the server 100 may include, from the plant information stored in the database, the eleventh detailed information for the corresponding Sansevieria included in the confirmed eleventh plant information (for example, plant information related to Sansevieria), and a management method for the corresponding Sansevieria. 11th additional information and the like are confirmed.

Further, the server 100 transmits the confirmed eleventh detailed information (for example, detailed information related to Sansevieria), eleventh additional information related to the corresponding eleventh detailed information, and the like to the first terminal (S350).

Then, the terminal 200 receives the detailed information and the additional information related to the specific plant transmitted from the server 100 in response to the plant classification request information transmitted previously.

In addition, the terminal 200 displays the received detailed information, additional information, image information related to a specific plant included in the plant classification request information, and the like.

As an example, the first terminal may respond to the first plant classification request information transmitted in advance, and the eleventh detailed information related to Sansevieria transmitted from the server 100, and the eleventh additional information regarding the management method of the corresponding Sansevieria. Etc.

In addition, as illustrated in FIG. 4, the first terminal may include the first plant in the first video information included in the first plant classification request information, the received eleventh detailed information, and the eleventh additional information. Both are displayed 400 (S360).

As described above, the examples of the present invention, as described above, confirm the characteristic points by the monthly growth state of the plant by utilizing deep running for leaves, stems, branches, flowers, fruits, etc., depending on the flowering time, the fruit setting time, etc. After confirming the characteristic points of the corresponding plant, confirming the characteristic points for the varieties of the corresponding plant, and making a database of information on the confirmed characteristic points, if there is a classification request for the plants included in the specific image, it is applicable. Providing plant information corresponding to the corresponding image and additional information corresponding to the plant information from the information stored in the database based on the meta information in the image to improve the classification accuracy of the plant in the current state. Providing good quality information can increase user satisfaction.

The above contents can be modified and changed by those skilled in the art to which the present invention pertains without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are intended to be explained, and the scope of the technical idea of the present invention is limited by such embodiments. Not a thing. The protection scope of the present invention is construed according to the following claims, and all technical ideas within the scope equivalent thereto are included in the scope of rights of the present invention.

10: Plant classification system using deep running 100: Server 200: Terminal 110: Communication unit 120: Storage unit 130: Display unit 140: Voice output unit 150: Control unit

Claims (7)

Image information including the plant is acquired for the same plant for each month, and a plurality of characteristic points according to the monthly growth state are extracted for leaves, stems, branches, flowers and fruits of the plant in the acquired image information, and Calculate a correlation vector by the correlation between the plurality of extracted feature points, and confirm the hue and morphology of the leaves, stems, branches, flowers and fruits of the plant in the acquired video information, respectively, and Information on a plurality of characteristic points according to monthly growth state, a correlation vector based on a correlation between the plurality of characteristic points, hues and forms of leaves, stems, branches, flowers, fruits, etc. of the confirmed corresponding plants, details related to the plants A server that stores information and plant information including additional information about the plant management method in a database; and plant classification request information including other image information related to a specific plant and identification information of the terminal to the server. A plant classification system using deep running characterized by including a transmitting terminal. The correlation vector is
The plant classification system using deep running according to claim 1, including distance and direction information between feature points. The server is
One or more feature points associated with the extracted leaf, one or more feature points associated with the extracted trunk, one or more feature points associated with the extracted branch, one associated with the extracted flower The one or more correlation vectors between the one or more feature points and the one or more feature points associated with the extracted fruit are calculated to confirm the feature between the leaves, the trunk, the branches, the flowers, and the fruit. A plant classification system using deep running described in. The server is
The meta information in the other video information included in the plant classification request information is confirmed, and it is determined whether the object in the other video information included in the plant classification request information is a plant. As a result, when the object in the other video information is a plant, the server extracts a plurality of other feature points for leaves, trunks, branches, flowers and fruits for the object in the other video information, Another correlation vector is calculated based on the correlation between the extracted plurality of other feature points, and the hue of the object leaf, trunk, branch, flower, and fruit in the other video information included in the plant classification request information is calculated. And the morphology are confirmed, and among the plurality of feature points associated with a plurality of plants for each month in the plant information stored in the database and the correlation vector associated with the plurality of relevant feature points, corresponding to the confirmed meta information. At least one feature point associated with a plurality of plants corresponding to a specific month and a correlation vector associated with the corresponding at least one feature point are confirmed, and at least one associated with a plurality of plants corresponding to the confirmed specific month is identified. Calculating a similarity between a plurality of other feature points related to the extracted specific plant and the calculated other correlation vector from among the correlation vectors associated with one feature point and the corresponding at least one feature point, Confirm the plant information with the highest similarity among the calculated plurality of similarities, and transmit detailed information and additional information included in the confirmed plant information to the terminal,
The terminal is
The plant classification system using deep running according to claim 1, wherein detailed information and additional information related to the specific plant transmitted from the server are displayed in response to the transmitted plant classification request information. Obtaining image information including the plant for the same plant by the server by month;
The server extracts a plurality of feature points according to a monthly growth condition for leaves, stems, branches, flowers, and fruits in the acquired image information.
Calculating a correlation vector according to the correlation between the extracted plurality of feature points by the server;
The server confirms the hue and morphology of the leaves, stems, branches, flowers and fruits of the plants in the acquired image information; and the server determines a plurality of features according to the monthly growth state of the extracted plants. Point information, correlation vector by correlation between the plurality of feature points, hue and morphology of leaves, stems, branches, flowers, fruits, etc. of the identified corresponding plant, detailed information related to the plant and management method of the plant A plant classification method using deep running, characterized by including a step of creating a database of plant information including additional information regarding to store. The step of calculating the correlation vector comprises
Calculating a correlation vector between the feature point of the central portion of the leaf and at least one other adjacent feature point adjacent to the feature point;
Calculating a correlation vector between the feature point of the central portion of the trunk and at least one other adjacent feature point adjacent to the feature point;
Calculating a correlation vector between the feature point at the center of the branch and at least one other adjacent feature point adjacent to the feature point;
Calculating a correlation vector between the feature point of the central portion of the flower and at least one other adjacent feature point adjacent to the relevant feature point; and the feature point of the actual central portion and at least one other adjacent to the relevant feature point The plant classification method using deep running according to claim 5, including at least one step of calculating a correlation vector between adjacent feature points of the above. Transmitting, to the server, plant classification request information including other image information related to a specific plant and identification information of the terminal, by the terminal;
The server confirms meta information in other image information included in the plant classification request information transmitted from the terminal;
The server determines whether the object in the other image information included in the plant classification request information is a plant;
As a result of the determination, when the object in the other image information is a plant, the server extracts a plurality of other feature points for leaves, trunks, branches, flowers, and fruits for the object in the other image information. Stage of doing;
Calculating another correlation vector according to the correlation between the extracted other feature points by the server;
The server confirms the hue and morphology of the leaves, trunks, branches, flowers, and fruits in the other image information included in the plant classification request information;
By the server, from among a plurality of feature points associated with a plurality of monthly plants in the database of plant information and the correlation vector associated with the plurality of relevant feature points, a specific corresponding to the confirmed meta information. Identifying at least one feature associated with a plurality of plants of the month and a correlation vector associated with the at least one feature of interest;
By the server, at least one feature point associated with a plurality of plants corresponding to the confirmed specific month and a plurality of correlation vectors associated with the particular plant extracted from among correlation vectors associated with the corresponding at least one feature point. Calculating similarities between other feature points and the calculated other correlation vectors, respectively;
The server confirms the plant information having the highest similarity among the calculated similarities;
The server transmits detailed information and additional information included in the confirmed plant information to the terminal; and the terminal transmits the detailed information and the additional information from the server in response to the transmitted plant classification request information. The plant classification method using deep running according to claim 5, further comprising a step of displaying detailed information and additional information related to a specific plant.

Images