WO2018201638A1

WO2018201638A1 - Image recognition based information collection method, mobile terminal and storage medium

Info

Publication number: WO2018201638A1
Application number: PCT/CN2017/096881
Authority: WO
Inventors: 袁晖; 李凝华; 杨洋
Original assignee: 深圳市科迈爱康科技有限公司
Priority date: 2017-05-05
Filing date: 2017-08-10
Publication date: 2018-11-08
Also published as: CN107256379A; CN107256379B

Abstract

An image recognition based information collection method, a mobile terminal and a storage medium. The method comprises: if the type of a target object is a test strip, determining, according to a first preset positioning identifier of the image to be recognized, a test area and a control area of the image to be recognized (S20), extracting first feature information of the test area, and extracting second feature information of the control area (S30), then determining, according to the first feature information and the second feature information, a corresponding indicator value, and using the determined indicator value as an information collection result (S40). The present invention can digitize the target object without increasing cost.

Description

Information acquisition method based on image recognition, mobile terminal and storage medium

Technical field

The present invention relates to the field of Internet of Things technologies, and in particular, to an image acquisition method based on image recognition, a mobile terminal, and a computer readable storage medium.

Background technique

The Internet of Things is an important part of the new generation of information technology and an important stage of development in the era of "informatization." As the name suggests, the Internet of Things is the Internet that connects things. The Internet of Things is widely used in the convergence of networks through communication-aware technologies such as intelligent sensing, identification technology and pervasive computing. It is also called the third wave of the development of the world information industry after computers and the Internet.

Information transmission in the field of Internet of Things, mostly using wired or wireless networks for digital information dissemination, usually requires the installation of specific digital conversion modules and communication modules, which are costly, but the detection results of some specific objects are difficult to digitize, for example: Various test strips in the medical field.

The description is only for assisting in understanding the technical solutions of the present invention, and does not represent that the above is prior art.

Summary of the invention

The main object of the present invention is to provide an image acquisition method based on image recognition, a mobile terminal and a computer readable storage medium, which aim to solve the technical problem that some specific objects in the prior art are difficult to digitize.

To achieve the above object, the present invention provides an image acquisition method based on image recognition, the method comprising the following steps:

Obtaining an image to be identified of the target object;

When the type of the target object is a test strip, the test area and the control area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Extracting first feature information in the test area, and extracting second feature information in the control area;

And determining, according to the first feature information and the second feature information, a corresponding indicator value, and using the determined indicator value as the information collection result.

In addition, in order to achieve the above object, the present invention further provides a mobile terminal, the mobile terminal comprising: a memory, a processor, and an information collecting program stored on the memory and operable on the processor, the information The acquisition program is configured to implement the steps of the image recognition based information collection method described.

Furthermore, in order to achieve the above object, the present invention also provides a computer readable storage medium having an information collection program stored thereon, the information acquisition program being implemented by a processor to implement the image recognition based The steps of the information collection method.

The present invention may determine a test area and a control area in the image to be identified according to a first preset positioning identifier in the image to be identified when the type of the target object is a test strip, and then extract the first in the test area. a feature information, and extracting second feature information in the comparison area, and then determining a corresponding indicator value according to the first feature information and the second feature information, and using the determined index value as an information collection result, The target object is digitized with increased costs.

DRAWINGS

1 is a schematic structural diagram of a mobile terminal in a hardware operating environment according to an embodiment of the present invention;

2 is a schematic flow chart of a first embodiment of a remote controller searching method according to the present invention;

3 is a schematic flow chart of a second embodiment of a remote controller searching method according to the present invention;

4 is a schematic flow chart of a third embodiment of a remote controller searching method according to the present invention;

FIG. 5 is a schematic flowchart diagram of a fourth embodiment of a remote controller searching method according to the present invention; FIG.

6 is a schematic flowchart of a fifth embodiment of a remote controller searching method according to the present invention;

7 is a schematic flowchart of a sixth embodiment of a remote controller searching method according to the present invention;

FIG. 8 is a schematic flowchart diagram of a seventh embodiment of a remote controller searching method according to the present invention.

The implementation, functional features, and advantages of the present invention will be further described in conjunction with the embodiments.

detailed description

It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

1 is a schematic structural diagram of a mobile terminal in a hardware operating environment according to an embodiment of the present invention.

As shown in FIG. 1, the mobile terminal may include a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to implement connection communication between these components. The user interface 1003 can include a display, an input unit such as a keyboard, and the optional user interface 1003 can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1005 may be a high speed RAM memory or a stable memory (non-volatile) Memory), such as disk storage. The memory 1005 can also optionally be a storage device independent of the aforementioned processor 1001.

It will be understood by those skilled in the art that the structure shown in FIG. 1 does not constitute a limitation of the mobile terminal, and may include more or less components than those illustrated, or a combination of certain components, or different component arrangements.

As shown in FIG. 1, an operating system, a network communication module, a user interface module, and an information collection program may be included in the memory 1005 as a computer storage medium.

In the mobile terminal shown in FIG. 1, the network interface 1004 is mainly used to connect to a server (the server may be a normal server or a cloud server, which is not limited in this embodiment), and performs data communication with the server; The interface 1003 is mainly configured to receive an input instruction of the user; the mobile terminal invokes the information collection program stored in the memory 1005 through the processor 1001, and performs the following operations:

Obtaining an image to be identified of the target object;

Further, the processor 1001 can call the information collection program stored in the memory 1005, and also perform the following operations:

Scanning the test area to obtain a first gray level integral value in the test area, and using the first gray level integral value as the first feature information;

Scanning the control area to obtain a second gray level integral value in the control area, and using the second gray level integral value as the second feature information;

Calculating a ratio value between the first feature information and the second feature information, determining an index value corresponding to the calculated proportional value, and using the determined index value as the information collection result.

Dividing the comparison area according to a color difference between adjacent pixels, obtaining each colorimetric part in the comparison area, obtaining a second gray level integral value of each colorimetric part, and obtaining the second gray level integral value As the second feature information;

And searching for the second feature information that matches the first feature information, determining the index value corresponding to the searched second feature information, and using the determined indicator value as the information collection result.

When the type of the target object is a test strip, the test area, the control area, and the background area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Scanning the background area by using a preset rectangle to obtain a third gray level integral value of each rectangle;

Calculating a variance between the third gray level integral values of the respective rectangles;

When the variance does not exceed the preset threshold, the step of extracting the first feature information in the test area and extracting the second feature information in the control area is performed.

When the type of the target object is a digital dial, determining a numerical area and a background area in the to-be-identified image according to the second preset positioning identifier in the to-be-identified image;

Dividing the numerical value area to obtain each digital part in the numerical value area;

Performing gray scale comparison between each digital part and the background area to obtain a combination of digital tube light and dark in each digital part;

Determining the corresponding dial value according to the combination of the digital tube light and dark in each digital part;

The dial value is used as the information collection result.

When the type of the target object is a digital dial, determining a numerical area, a background area, and a character area in the image to be recognized according to the second preset positioning identifier in the image to be identified;

Performing gray scale comparison between the character area and the background area to obtain brightness and dark information of each pixel in the character area, and determining corresponding character content according to the brightness and dark information of each pixel point in the character area and the dial feature distribution map;

The dial value and character content are used as information collection results.

When the type of the target object is a pointer dial, obtain a third preset positioning identifier and a center of the image to be recognized;

Level-correcting the image to be recognized by the third preset positioning identifier and the center of the circle;

Scanning the horizontally corrected image to be recognized by using a preset fan shape around the center of the circle to obtain a fourth gray level integral value of each sector shape;

The angle between the center line of the sector having the largest fourth gray level integral value and the horizontal direction is taken as the pointer deflection angle;

Determining a corresponding pointer value according to the pointer deflection angle;

The pointer value is used as the information collection result.

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.

In the above embodiment, when the type of the target object is the test strip, the test area and the control area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified, and then the The first feature information in the test area is extracted, and the second feature information in the comparison area is extracted, and then the corresponding indicator value is determined according to the first feature information and the second feature information, and the determined indicator value is used as information collection. As a result, the target object can be digitized without increasing the cost.

Based on the above hardware structure, an embodiment of the image acquisition method based on image recognition of the present invention is proposed.

Referring to FIG. 2, FIG. 2 is a schematic flowchart diagram of a first embodiment of an image acquisition method based on image recognition according to the present invention.

In a first embodiment, the image recognition based information collection method comprises the following steps:

S10: acquiring an image to be identified of the target object;

It should be understood that the mobile terminal is a terminal device that can be used for mobile, for example, a device such as a smart phone, a tablet computer or a notebook computer, which is not limited in this embodiment.

It should be noted that the target object is an object that needs to be identified, and is usually an object that is difficult to digitize the detection result.

It can be understood that the image to be recognized is an image obtained by capturing a target object.

S20: determining, when the type of the target object is a test strip, a test area and a comparison area in the image to be recognized according to the first preset positioning identifier in the image to be identified;

In a specific implementation, the test strip usually has a test area and a control area. In order to distinguish between the test area and the control area, a first preset positioning identifier may be preset on the test strip, thereby facilitating the waiting for the test strip. Determining the test area and the control area in the identification image, the first preset positioning identifier may be a positioning hole, or a locator having a distinct degree of discrimination, etc., of course, other identifiers may be used, which is not used in this embodiment. limit.

S30: extract first feature information in the test area, and extract second feature information in the control area;

It can be understood that the test area and the control area generally have feature information, and therefore, the first feature information in the test area can be extracted, and the second feature information in the control area can be extracted.

S40: Determine a corresponding indicator value according to the first feature information and the second feature information, and use the determined indicator value as the information collection result.

In this embodiment, when the type of the target object is a test strip, the test area and the control area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified, and then the test area is extracted. First feature information, and extracting second feature information in the comparison area, and then determining a corresponding indicator value according to the first feature information and the second feature information, and using the determined indicator value as an information collection result, The target object is digitized without increasing the cost.

Further, as shown in FIG. 3, a second embodiment of the image recognition-based information collection method of the present invention is proposed based on the first embodiment. In this embodiment, the step S30 includes:

S301: Scan the test area to obtain a first gray level integral value in the test area, and use the first gray level integral value as the first feature information;

S302: Scan the control area to obtain a second gray level integral value in the control area, and use the second gray level integral value as the second feature information;

Correspondingly, step S40 specifically includes:

S401: Calculate a ratio value between the first feature information and the second feature information, determine an index value corresponding to the calculated proportional value, and use the determined index value as the information collection result.

It can be understood that, in step S301, the test area may be scanned by using a preset rectangle. In step S302, the control area may be scanned by using a preset rectangle. Of course, in order to obtain the gray integral value, The image to be recognized may be subjected to gradation conversion in advance.

In a specific implementation, the test strip may have a detection result in the detection area, and also has a control information in the control area, for example, when the test strip is a pregnancy test strip, in the normal case, the test strip is detected. A red line may appear in the area, and a red line may appear all the time in the control area. Of course, the red line may not appear in the control area due to the test paper failure. Therefore, the test area may be scanned to obtain the first gray in the test area. a degree integral value, the first gray level integral value is used as the first feature information, the first feature information may reflect a red line occurrence of the detection area, and the control area may also be scanned to obtain the The second gray level integral value in the control area is used as the second feature information, and the second feature information may reflect the occurrence of the red line in the control area.

The first feature information may reflect the occurrence of the red line of the detection area, and the second feature information may reflect the occurrence of the red line of the control area. Therefore, calculating the ratio between the first feature information and the second feature information may determine the detection. As a result, in order to facilitate determining the index value corresponding to the calculated proportional value, the correspondence between the proportional value and the index value may be established in advance, and the index value corresponding to the calculated proportional value is determined according to the correspondence relationship, and the determined index value is used as the index value. Information collection results.

After obtaining the information collection result, the information collection result may be uploaded to a server, so that the server stores and analyzes the information collection result.

Further, as shown in FIG. 4, a third embodiment of the image recognition-based information collection method of the present invention is proposed based on the first embodiment. In this embodiment, the step S30 includes:

S303: Scan the test area to obtain a first gray level integral value in the test area, and use the first gray level integral value as the first feature information;

S304: dividing the comparison area according to a color difference between adjacent pixels, obtaining each colorimetric part in the comparison area, obtaining a second gray level integral value of each colorimetric part, and obtaining the second gray level An integral value as the second feature information;

Correspondingly, step S40 specifically includes:

S402: Search for second feature information that matches the first feature information, determine an indicator value corresponding to the searched second feature information, and use the determined indicator value as the information collection result.

It can be understood that, in step S303, the test area can be scanned by using a preset rectangle. In step S303, the control area can be scanned by using a preset rectangle. Of course, in order to obtain the gray integral value, The image to be recognized may be subjected to gradation conversion in advance.

In a specific implementation, the test strip may have a detection result in the detection area, and at the same time, the control area has a plurality of colorimetric portions for comparison with the detection result, for example, a pH detection test paper, under normal circumstances, The detection area of the PH value test strip may have a corresponding color, and the control area has various colors corresponding to different PH values (ie, a colorimetric part), and therefore, the test area may be scanned to obtain the test area. The first gray level integral value is used as the first feature information, and the first feature information can reflect the color of the detection area, and can be based on the color difference between adjacent pixels. And dividing the comparison area to obtain each colorimetric part in the comparison area, obtaining a second gray level integral value of each colorimetric part, and using the second gray level integral value as the second feature information, That is, the second feature information has a plurality of colors, and respectively reflects colors of the corresponding colorimetric portions;

The first feature information may reflect the color of the detection area, and the second feature information has a plurality of colors, and respectively reflect the color of the corresponding colorimetric portion. Therefore, the second feature information matching the first feature information may be searched for, and The second feature information can determine the detection result. To facilitate determining the index value corresponding to the searched second feature information, the correspondence between the position of each colorimetric portion and the index value can be established in advance, and can be determined according to the corresponding relationship. The index value corresponding to the second feature information is found, and the determined index value is used as the information collection result.

Further, as shown in FIG. 5, a fourth embodiment of the image recognition based image acquisition method of the present invention is proposed based on the second embodiment or the third embodiment. FIG. 5 is based on the second embodiment.

In this embodiment, step S20 specifically includes:

S201: determining, when the type of the target object is a test strip, a test area, a control area, and a background area in the image to be recognized according to the first preset positioning identifier in the image to be identified;

Before the step S30, the method further includes:

S2001: scanning the background area by using a preset rectangle to obtain a third gray level integral value of each rectangle;

S2002: calculating a variance between the third gray level integral values of each rectangle;

S2003: Perform the step of extracting first feature information in the test area and extracting second feature information in the control area when the variance does not exceed a preset threshold.

In step S211, the background area may be scanned left and right and up and down by using a preset rectangle to obtain a specific width (≤1 mm) or a small rectangular gray integral value in the length, and calculate a third gray level integral value of each rectangle. The variance, when the variance exceeds the preset threshold, indicates that the current light is uneven, which may result in inaccurate detection results. At this time, the user may be prompted to re-shoot, of course, when the variance does not exceed the preset threshold, Step S30, thereby further ensuring the accuracy of the detection result.

Further, as shown in FIG. 6, the fifth embodiment of the image recognition-based information collection method of the present invention is proposed based on the first embodiment. In this embodiment, after the step S10, the method further includes:

S211: determining, when the type of the target object is a digital dial, the numerical area and the background area in the to-be-identified image according to the second preset positioning identifier in the to-be-identified image;

S212: Dividing the numerical value area to obtain each digital part in the numerical value area;

S213: performing gray scale comparison on each digital part and the background area to obtain a combination of digital tube light and dark in each digital part;

S214: Determine a corresponding dial value according to a digital tube light and dark combination in each digital part;

S215: The dial value is used as the information collection result.

It should be understood that the digital dial also belongs to an object that is difficult to digitize, such as a weight scale. In this embodiment, the dial value of the digital dial can be read, and the weight scale can be conveniently recorded by directly scanning the weight scale. Grease and other values.

In a specific implementation, the digital dial usually has a numerical area and a background area. In order to distinguish between the numerical area and the background area, a second preset positioning identifier may be preset on the digital dial, thereby facilitating the number. The value area and the background area in the dial are determined. The second preset positioning identifier may be a positioning hole, or a locator with a clear distinction, and of course, other identifiers may be used, which is not limited in this embodiment. .

It should be noted that the digital dial usually uses a 7-segment digital tube for digital display, and the area where the number is displayed is a numerical area. Since a plurality of numbers are usually displayed in the numerical area, the numerical area can be performed. Dividing, obtaining the digital parts in the numerical value area, performing gray scale comparison between each digital part and the background area, and obtaining the combination of the digital tube light and dark in each digital part, because the different light and dark combinations of the 7-segment digital tube respectively correspond to the number “0”~ "9", so the correspondence between the number and the combination of light and dark can be set in advance, and the corresponding dial value is determined according to the digital tube light and dark combination and the corresponding relationship in each digital part.

In order to facilitate gray scale comparison between each digital part and the background area, the image to be recognized may be gray-scale transformed in advance.

It should be noted that, in the digital dial, a character for characterizing a numerical unit or an operating state is also set. In order to facilitate the identification of the character, in the embodiment, step S21 may further include:

S211: determining, when the type of the target object is a digital dial, a numerical area, a background area, and a character area in the image to be recognized according to the second preset positioning identifier in the image to be identified;

Correspondingly, before the S25, the method further includes:

Correspondingly, the S25 specifically includes:

It can be understood that the dial feature map can be set on the server side. When character content determination is required, the corresponding character content is determined according to the brightness and dark information of each pixel in the character area and the dial feature map.

Further, as shown in FIG. 7 , a sixth embodiment of the image recognition-based information collection method of the present invention is proposed based on the first embodiment. In this embodiment, after the step S10, the method further includes:

S221: When the type of the target object is a pointer dial, obtain a third preset positioning identifier and a center of the image to be recognized;

S222: Perform horizontal correction on the image to be identified by using the third preset positioning identifier and a center of the circle;

S223: Scan a horizontally corrected image to be recognized by using a preset fan shape around the center to obtain a fourth gray integrated value of each sector;

S224: taking an angle between a center line of the sector having the largest fourth gray level integral value and a horizontal direction as a pointer deflection angle;

S225: Determine a corresponding pointer value according to the pointer deflection angle;

S226: The pointer value is used as the information collection result.

It should be understood that the pointer dial also belongs to an object that is difficult to digitize. In this embodiment, the pointer value of the pointer dial can be read.

It can be understood that the third preset positioning identifier may be a positioning hole, or a locator with a clear distinction, and of course, other identifiers may be used, which is not limited in this embodiment.

In a specific implementation, the digital dial in the to-be-identified image may not be in the horizontal direction, thereby affecting the detection result. To ensure the detection result, in this embodiment, the third preset in the to-be-identified image may be obtained. Positioning the mark and the center of the circle, and correcting the image to be recognized by the third preset positioning mark and the center of the circle, and adopting a preset fan shape (the angle of the fan shape may be set to be less than or equal to 1 degree, and the radius is the center of the circle The distance to the locator is scanned around the center of the horizontally corrected image to be recognized, and the fourth gray integrated value of each sector is obtained. Since the pointer is usually dark, the fourth sector of the pointer is located. The gray level integral value is usually the largest. Therefore, the angle between the center line of the sector with the largest fourth gray level integral value and the horizontal direction can be used as the pointer deflection angle, in order to facilitate determining the pointer corresponding to the pointer deflection angle. For the numerical value, a correspondence relationship between the deflection angle and the pointer value may be established in advance, and the corresponding pointer value is determined according to the pointer deflection angle and the correspondence relationship.

Further, as shown in FIG. 8 , a seventh embodiment of the image recognition based information collection method of the present invention is proposed based on any one of the first embodiment to the sixth embodiment. FIG. 8 is based on the first embodiment. In this embodiment, before the step S10, the method further includes:

S01: Scan the code information bound to the target object, and obtain an object identification number and factory information in the graphic code information;

S02: verify the object identification number and the factory information;

S03: When the verification is passed, determining the type of the target object according to the object identification number and the factory information, and performing the step of acquiring the image to be recognized of the target object.

In a specific implementation, the code information may be a barcode or a two-dimensional code. Of course, other graphic codes may be used. This embodiment does not limit this.

It can be understood that, in order to facilitate verification of the object identification number and the factory information, the object identification number and the factory information may be stored on the server side in advance. Of course, the type of the target object and the measurement object may also be stored for the convenience of the user.

When the verification is passed, a subsequent step may be performed. To facilitate determining the type of the target object, the server may determine the type of the target object according to the object identification number and the factory information, and feed back the type of the target object to the mobile terminal.

In addition, an embodiment of the present invention further provides a computer readable storage medium, where the information storage program is stored, and when the information collection program is executed by the processor, the following operations are implemented:

Obtaining an image to be identified of the target object;

Further, when the information collection program is executed by the processor, the following operations are also implemented:

The dial value is used as the information collection result.

The pointer value is used as the information collection result.

Verifying the object identification number and the factory information;

It is to be understood that the term "comprises", "comprising", or any other variants thereof, is intended to encompass a non-exclusive inclusion, such that a process, method, article, or Also includes other elements not explicitly listed, or Includes elements inherent to such a process, method, item, or system. In the absence of more restrictions, an element defined by the phrase "including one..." is not excluded from the process of including the element, There are additional identical elements in the method, item or system.

The serial numbers of the embodiments of the present invention are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

Those skilled in the art can clearly understand the above by the description of the above embodiments. The embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course Hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solution of the present invention may be in the form of a software product in essence or in part contributing to the prior art. It is now apparent that the computer software product is stored in a storage medium (such as ROM/RAM, disk, light) as described above. The disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the methods described in various embodiments of the present invention.

The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the present invention and the drawings are directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Claims

An image recognition based information collection method, characterized in that the method comprises the following steps:

Obtaining an image to be identified of the target object;

When the type of the target object is a test strip, the test area and the control area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Extracting first feature information in the test area, and extracting second feature information in the control area;

And determining, according to the first feature information and the second feature information, a corresponding indicator value, and using the determined indicator value as the information collection result.
The method of claim 1, wherein the extracting the first feature information in the test area and extracting the second feature information in the control area comprises:

Scanning the test area to obtain a first gray level integral value in the test area, and using the first gray level integral value as the first feature information;

Scanning the control area to obtain a second gray level integral value in the control area, and using the second gray level integral value as the second feature information;

Correspondingly, the determining the corresponding indicator value according to the first feature information and the second feature information, and using the determined indicator value as the information collection result, specifically includes:

Calculating a ratio value between the first feature information and the second feature information, determining an index value corresponding to the calculated proportional value, and using the determined index value as the information collection result.
The method of claim 1, wherein the extracting the first feature information in the test area and extracting the second feature information in the control area comprises:

Scanning the test area to obtain a first gray level integral value in the test area, and using the first gray level integral value as the first feature information;

Dividing the comparison area according to a color difference between adjacent pixels, obtaining each colorimetric part in the comparison area, obtaining a second gray level integral value of each colorimetric part, and obtaining the second gray level integral value As the second feature information;

Correspondingly, the determining the corresponding indicator value according to the first feature information and the second feature information, and using the determined indicator value as the information collection result, specifically includes:

And searching for the second feature information that matches the first feature information, determining the index value corresponding to the searched second feature information, and using the determined indicator value as the information collection result.
The method according to claim 2, wherein when the type of the target object is a test strip, the test in the image to be recognized is determined according to the first preset positioning identifier in the image to be recognized. District and control area, including:

When the type of the target object is a test strip, the test area, the control area, and the background area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Correspondingly, before the extracting the first feature information in the test area and extracting the second feature information in the control area, the method further includes:

Scanning the background area by using a preset rectangle to obtain a third gray level integral value of each rectangle;

Calculating a variance between the third gray level integral values of the respective rectangles;

When the variance does not exceed the preset threshold, the step of extracting the first feature information in the test area and extracting the second feature information in the control area is performed.
The method according to claim 3, wherein when the type of the target object is a test strip, the test in the image to be recognized is determined according to the first preset positioning identifier in the image to be recognized. District and control area, including:

When the type of the target object is a test strip, the test area, the control area, and the background area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Correspondingly, before the extracting the first feature information in the test area and extracting the second feature information in the control area, the method further includes:

Scanning the background area by using a preset rectangle to obtain a third gray level integral value of each rectangle;

Calculating a variance between the third gray level integral values of the respective rectangles;

When the variance does not exceed the preset threshold, the step of extracting the first feature information in the test area and extracting the second feature information in the control area is performed.
The method of claim 1, wherein after the acquiring the image to be identified of the target object, the method further comprises:

When the type of the target object is a digital dial, determining a numerical area and a background area in the to-be-identified image according to the second preset positioning identifier in the to-be-identified image;

Dividing the numerical value area to obtain each digital part in the numerical value area;

Performing gray scale comparison between each digital part and the background area to obtain a combination of digital tube light and dark in each digital part;

Determining the corresponding dial value according to the combination of the digital tube light and dark in each digital part;

The dial value is used as the information collection result.
The method according to claim 6, wherein when the type of the target object is a digital dial, determining a value in the image to be recognized according to a second preset positioning identifier in the image to be identified District and background area, including:

When the type of the target object is a digital dial, determining a numerical area, a background area, and a character area in the image to be recognized according to the second preset positioning identifier in the image to be identified;

Correspondingly, before the using the dial value as the information collection result, the method further includes:

Performing gray scale comparison between the character area and the background area to obtain brightness and dark information of each pixel in the character area, and determining corresponding character content according to the brightness and dark information of each pixel point in the character area and the dial feature distribution map;

Correspondingly, the using the dial value as the information collection result includes:

The dial value and character content are used as information collection results.
The method of claim 1, wherein after the acquiring the image to be identified of the target object, the method further comprises:

When the type of the target object is a pointer dial, obtain a third preset positioning identifier and a center of the image to be recognized;

Level-correcting the image to be recognized by the third preset positioning identifier and the center of the circle;

Scanning the horizontally corrected image to be recognized by using a preset fan shape around the center of the circle to obtain a fourth gray level integral value of each sector shape;

The angle between the center line of the sector having the largest fourth gray level integral value and the horizontal direction is taken as the pointer deflection angle;

Determining a corresponding pointer value according to the pointer deflection angle;

The pointer value is used as the information collection result.
The method of claim 1, wherein before the acquiring the image to be identified of the target object, the method further comprises:

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.
The method of claim 2, wherein before the acquiring the image to be identified of the target object, the method further comprises:

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.
The method of claim 3, wherein before the acquiring the image to be identified of the target object, the method further comprises:

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.
The method of claim 5, wherein before the acquiring the image to be identified of the target object, the method further comprises:

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.
The method of claim 6, wherein the method further comprises: before acquiring the image to be identified of the target object:

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.
The method of claim 7, wherein the method further comprises: before acquiring the image to be identified of the target object:

Scanning the code information bound to the target object to obtain an object identification number and factory information in the graphic code information;

Verifying the object identification number and the factory information;

When the verification is passed, the type of the target object is determined according to the object identification number and the factory information, and the step of acquiring the image to be recognized of the target object is performed.
A mobile terminal, comprising: a memory, a processor, and an information collecting program stored on the memory and operable on the processor, wherein the information collecting program is configured to implement the following steps :

Obtaining an image to be identified of the target object;

When the type of the target object is a test strip, the test area and the control area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Extracting first feature information in the test area, and extracting second feature information in the control area;

And determining, according to the first feature information and the second feature information, a corresponding indicator value, and using the determined indicator value as the information collection result.
A computer readable storage medium, wherein the computer readable storage medium stores an information collection program, and when the information collection program is executed by the processor, the following steps are implemented:

Obtaining an image to be identified of the target object;

When the type of the target object is a test strip, the test area and the control area in the image to be recognized are determined according to the first preset positioning identifier in the image to be identified;

Extracting first feature information in the test area, and extracting second feature information in the control area;

And determining, according to the first feature information and the second feature information, a corresponding indicator value, and using the determined indicator value as the information collection result.