Test result recognition method and test result recognition device

Abstract

This invention provides a method and apparatus for identifying test results. The method includes: controlling an imaging device to capture a first image of a display screen according to imaging parameters; in response to determining that a reference image region including a first specified string exists in the first image, controlling the imaging device to capture a first test image of the display screen according to the imaging parameters; obtaining a first image region corresponding to the reference image region from the first test image, and performing a text segmentation operation on the first image region to convert the first image region into a second image region; and performing a text recognition operation on the second image region to obtain a first test result corresponding to the first test image. This increases the reliability of automated testing.

Description

Technical Field

[0001] This invention relates to an image recognition technology, and more particularly to a test result recognition method and a test result recognition device. Background Technology

[0002] In existing technology, when a display device is used to display a test screen, the display device can also display various current display parameters on the test screen, such as frames per second (fps). In this test scenario, the test screen can be captured by an image capturing device, and the captured image can be analyzed / recognized by another test device to obtain the aforementioned display parameters.

[0003] However, in the above scenarios, the testing device often fails to obtain good image recognition / analysis results during the image analysis / recognition process due to the poor quality of the captured images. Summary of the Invention

[0004] In view of this, the present invention provides a test result recognition method and a test result recognition device, which can be used to solve the above-mentioned technical problems.

[0005] This invention provides a test result recognition method, suitable for a test result recognition device, comprising: controlling an image capturing device to capture a first image of a display screen of a display device under test according to at least one image capturing parameter, wherein the display screen of the display device under test includes a first specified string; in response to determining that a reference image region including the first specified string exists in the first image, controlling the image capturing device to capture a first test image of the display screen of the display device under test according to at least one image capturing parameter; obtaining a first image region corresponding to the reference image region from the first test image, and performing a text segmentation operation on the first image region to convert the first image region into a second image region; and performing a text recognition operation on the second image region to obtain a first test result corresponding to the first test image.

[0006] This invention provides a test result recognition device, comprising a storage circuit and a processor. The storage circuit stores program code. The processor is coupled to the storage circuit and accesses the program code to execute: controlling an image capturing device to capture a first image of a display screen of a display device under test according to at least one image capturing parameter, wherein the display screen of the display device under test includes a first specified string; in response to determining that a reference image region including the first specified string exists in the first image, controlling the image capturing device to capture a first test image of the display screen of the display device under test according to at least one image capturing parameter; obtaining a first image region corresponding to the reference image region from the first test image, and performing a text segmentation operation on the first image region to convert the first image region into a second image region; and performing a text recognition operation on the second image region to obtain a first test result corresponding to the first test image. Attached Figure Description

[0007] The accompanying drawings are included to further illustrate the invention, and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0008] Figure 1 This is a schematic diagram of a test result recognition device, an image acquisition device, and a test display device according to an embodiment of the present invention;

[0009] Figure 2 This is a flowchart illustrating a test result identification method according to an embodiment of the present invention;

[0010] Figure 3 This is a schematic diagram illustrating the adjustment of imaging parameters according to an embodiment of the present invention;

[0011] Figure 4 This is a schematic diagram illustrating the execution of a text segmentation operation according to the first embodiment of the present invention;

[0012] Figure 5 This is a schematic diagram illustrating the execution of a text cutting operation according to the second embodiment of the present invention. Detailed Implementation

[0013] Reference will now be made in detail to exemplary embodiments of the invention, examples of which are illustrated in the accompanying drawings. Wherever possible, the same component reference numerals are used in the drawings and description to denote the same or similar parts.

[0014] Please refer to Figure 1 This is a schematic diagram illustrating a test result recognition device, an image acquisition device, and a display device to be tested, according to embodiments of the present invention. Figure 1 In this context, the test result recognition device 100 may be, for example, various computer devices and / or smart devices, and may include storage circuitry 102 and processor 104.

[0015] The storage circuit 102 may be, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk or other similar device or combination of these devices, and may be used to record multiple program codes or modules.

[0016] Processor 104 is coupled to storage circuit 102 and may be a general purpose processor, special purpose processor, conventional processor, digital signal processor, multiple microprocessors, one or more microprocessors incorporating a digital signal processor core, controller, microcontroller, application specific integrated circuit (ASIC), field programmable gate array (FPGA), any other type of integrated circuit, state machine, processor based on advanced RISC machine (ARM), and the like.

[0017] In one embodiment, the display screen 120a of the display device 120 under test can be used to display the test image stream, and the display screen 120a can also display related display parameters, such as the FPS when displaying the test image stream, but it is not limited to this.

[0018] In one embodiment, the test result recognition device 100 may be coupled to the image capturing device 110 (which is, for example, a photographic device including various cameras), and may control the image capturing device 110 to capture images of the display screen 120a. Subsequently, the test result recognition device 100 may recognize / analyze the images captured by the image capturing device 110 to obtain relevant display parameters of the display device 120 under test (e.g., the aforementioned FPS), but may not be limited to this.

[0019] In an embodiment of the present invention, the processor 104 can access the modules and program code recorded in the storage circuit 102 to implement the test result identification method proposed in the present invention, the details of which are described below.

[0020] Please refer to Figure 2 This is a flowchart illustrating a test result identification method according to an embodiment of the present invention. The method of this embodiment can be derived from... Figure 1 The test result recognition device 100 performs the following steps: Figure 1 Component description shown Figure 2 Details of each step.

[0021] First, in step S210, the processor 104 controls the image capturing device 110 to capture a first image IM1 of the display screen 120a of the display device 120 under test according to the image capturing parameters. In different embodiments, the aforementioned image capturing parameters may include, for example, the exposure value, focus setting parameters, and zoom setting parameters of the image capturing device 110.

[0022] In general, the processor 104 can determine the image quality of the first image IM1 based on whether a reference image region including the first specified string can be identified in the first image IM1. If a reference image region including the first specified string cannot be found in the first image IM1, it means that the quality of the first image IM1 is poor. In this case, the processor 104 can adjust the imaging parameters of the imaging device 110 accordingly (e.g., reduce the exposure value) and control the imaging device 110 to capture an image of the display screen 120a again according to the adjusted imaging parameters. The processor 104 will repeatedly adjust the imaging parameters of the imaging device 110 according to the above teaching until a reference image region including the first specified string can be identified in the image captured by the imaging device 110, but it is not limited to this.

[0023] On the other hand, if a reference image region containing the first specified string can be found in the first image IM1, it means that the quality of the first image IM1 is acceptable. In this case, the processor 104 can control the imaging device 110 to capture one or more subsequent test images based on the current imaging parameters for further identification of each test image. Further explanation follows.

[0024] In one embodiment, after acquiring the first image IM1, the processor 104 may perform relevant preprocessing on the first image IM1 to improve its image quality. In some embodiments, the preprocessing may include, for example, converting the first image IM1 into a binary image (e.g., a black and white image) and / or filtering out noise in the first image IM1 by means of, for example, median filtering, but is not limited thereto.

[0025] In one embodiment, after acquiring (preprocessed) the first image IM1, the processor 104 may determine whether there is a reference image region in the first image IM1 that includes a first specified string.

[0026] In different embodiments, the designer may determine the state of the first specified string as needed. For example, assuming the display parameter of interest is FPS, the designer may set the first specified string to "fps". In this case, the processor 104 can determine whether there is a reference image region in the first image IM1 that includes "fps".

[0027] In one embodiment, the processor 104 may perform optical character recognition operations on the first image IM1 based on Microsoft's optical character recognition library, for example, to find multiple text image regions in the first image IM1, wherein each text image region may include at least one string.

[0028] Then, the processor 104 can determine whether the string in any of the above-mentioned text image regions includes the first specified string. In one embodiment, in response to determining that the string in one of the above-mentioned text image regions (hereinafter referred to as the first text image region) includes the first specified string, the processor 104 can determine that the first text image region is a reference image region in the first image IM1, and can continue to execute step S220.

[0029] On the other hand, in response to the determination that none of the strings in each text image region include the first specified string, the processor 104 can determine that there is no image region in the first image IM1 that includes the first specified string. In one embodiment, in response to the determination that there is no image region in the first image IM1 that includes the first specified string, the processor 104 can adjust the imaging parameters of the imaging device 110 (e.g., reduce the exposure value) and control the imaging device 110 to capture a second image of the display screen 120a of the display device 120 under test according to the adjusted imaging parameters. Afterwards, the processor 104 can further determine whether there is a reference image region in the second image that includes the first specified string. If so, the processor 104 can control the imaging device 110 to capture a first test image TM1 of the display screen 120a of the display device 120 under test according to the imaging parameters.

[0030] To make the above concepts easier to understand, the following pairings are provided. Figure 3 For further explanation, please refer to [link / reference]. Figure 3 This is a schematic diagram illustrating the adjustment of imaging parameters according to an embodiment of the present invention. Figure 3 In the example, assume that the image capturing device 110 captures an image 311 on the display screen 120a with an exposure value of -7. Image 311 contains strings such as "fps:60", "canvas width:1024", and "canvas height:1024". However, after the processor 104 performs preprocessing on image 311 to generate image 311a, the processor 104 may not be able to identify any text image areas in image 311a. Therefore, the processor 104 can reduce the exposure value to -8 and then control the image capturing device 110 to capture an image 312 on the display screen 120a again.

[0031] exist Figure 3In this scenario, the above actions can be repeated until the processor 104 reduces the exposure value to -11. In this case, the processor 104 can control the image capturing device 110 to capture an image of the display screen 120a, thereby obtaining image 313. Afterwards, the processor 104 can preprocess image 313 to obtain image 313a.

[0032] In one embodiment, the processor 104 may perform the above-described optical character recognition operation on the image 313a to find the text image regions 321 to 323 in the image 313a. The text image region 321 may include the string "fps:53", the text image region 322 may include the string "canvas width:1024", and the text image region 323 may include the string "canvasheight:1024", but may not be limited to these.

[0033] In this case, since the text image region 321 includes the first specified string (i.e., "fps"), the processor 104 can determine that the text image region 321 is a reference image region in the image 313a, and can accordingly continue to execute step S220.

[0034] For ease of explanation, it is assumed below that the processor 104 can directly find the reference image region including the first specified string in the first image IM1, but it is not limited to this.

[0035] Therefore, in step S220, in response to the determination that a reference image region including the first specified string exists in the first image IM1, the processor 104 can control the imaging device 110 to capture the first test image TM1 on the display screen 120a of the display device 120 under test according to the imaging parameters. Figure 3 For example, processor 104 may control image capturing device 110 to capture a first test image TM1 on display screen 120a of display device 120 under test based on an exposure value of -11, but may not be limited to this.

[0036] Next, in step S230, the processor 104 can obtain a first image region corresponding to the reference image region from the first test image TM1, and perform a text segmentation operation on the first image region to convert the first image region into a second image region.

[0037] In one embodiment, the first relative position of the reference image region and the first image IM1 may correspond to the second relative position of the first image region and the first test image TM1.

[0038] by Figure 3For example, if the first image IM1 has the same pattern as image 313a, then its corresponding reference image region is, for example, text image region 321. In this case, assuming the position of text image region 321 in the first image IM1 can be represented as ((x1,y1),(x2,y2)), where (x1,y1) is, for example, the coordinates of the upper left corner of text image region 321 in the first image IM1 (which can be obtained in the above-mentioned optical character recognition operation), and (x2,y2) is, for example, the coordinates of the upper left corner of text image region 321 in the first image IM1 (which can also be obtained in the above-mentioned optical character recognition operation). Based on this, the processor 104 can extract the region ((x1,y1),(x2,y2)) in the first test image TM1 as the aforementioned first image region.

[0039] Furthermore, since the first specified string "fps" should be displayed in the same position in the display screen 120a, the first image area obtained by the processor 104 in the above manner will also include the string "fps".

[0040] After obtaining the first image region, the processor 104 can perform a text segmentation operation on it to convert the first image region into a second image region.

[0041] Please refer to Figure 4 This is a schematic diagram illustrating the execution of a text segmentation operation according to the first embodiment of the present invention. Figure 4 In this context, it is assumed that the first image region acquired by processor 104 is the first image region 411 shown, which includes the string "fps:44". However, by Figure 4 It can be seen that there are connected line segments between the characters "44" in the first image area 411, and these line segments may cause the subsequent image recognition by the processor 104 to have lower accuracy. Therefore, embodiments of the present invention can segment the connected characters through the following mechanism.

[0042] exist Figure 4 In the first image region 411, the processor 104 can identify a first pixel row within these pixel rows. Each first pixel row can include multiple pixels, and only a single first specific pixel in each first pixel row has a first specified color. In different embodiments, the first specified color can be any color specified by the designer. For ease of explanation, it is assumed below that the first specified color is black, but it is not limited to this. In this case, the processor 104 can identify a pixel row in the first image region 411 that includes only a single black pixel as the aforementioned first pixel row. Figure 4 In this context, the first pixel row found by the processor 104 may be, for example, a pixel row including pixels 412a to 412f (i.e., the first specific pixel), but may not be limited to this.

[0043] Then, the processor 104 can find a second specific pixel in each first specific pixel row, wherein the adjacent pixels on both sides of each second specific pixel have a first specified color. In short, the processor 104 can find a second specific pixel in pixels 412a-412f, and the pixels to the left and right of this second specific pixel are both black. Figure 4 In this scenario, the processor 104 may, for example, identify pixels 412b to 412e from pixels 412a to 412f as the second specific pixels.

[0044] Next, the processor 104 can find a third specific pixel in the second specific pixel (i.e., pixels 412b to 412e), wherein a specific pixel row exists on a designated side of each third specific pixel, wherein the specific pixel row is separated from the corresponding third specific pixel by a preset number of rows, and the specific pixel row includes N consecutive pixels with a first specified color, where N is a positive integer. In different embodiments, N can be set to a positive integer greater than half the height of the first image region 411, but is not limited to this.

[0045] For ease of explanation, in Figure 4 The assumption is that the specified side is the left side, the preset number of rows is 4, and N is 7. In this case, if the fourth pixel row from the left of a pixel among pixels 412b to 412e includes 7 consecutive black pixels, the processor 104 can define this pixel as the third specific pixel.

[0046] exist Figure 4 In the process, since the fourth pixel row to the left of pixel 412d (i.e., pixel row 420) includes seven consecutive black pixels, the processor 104 may regard pixel 412d as a third specific pixel, but may not be limited to this.

[0047] Then, the processor 104 can replace each third specific pixel with a second specified color that is different from the first specified color. For example, the processor 104 can replace a pixel 412d that was originally black with white (i.e., the second specified color). In this way, the text "44" in the first image area 411 can be segmented accordingly to convert the first image area 411 into the second image area 430.

[0048] Please refer to Figure 5 This is a schematic diagram illustrating the execution of a text segmentation operation according to a second embodiment of the present invention. Figure 5 In this context, it is assumed that the first image region acquired by processor 104 is the first image region 411 shown, which includes the string "13FPS(0-16)". However, by Figure 5It can be seen that there are connected line segments between the characters "13" in the first image area 511, and these line segments may cause the subsequent image recognition by the processor 104 to have lower accuracy. Therefore, embodiments of the present invention can use the following mechanism to cut the connected characters.

[0049] exist Figure 5 In the image, the first image region 411 may include multiple pixel rows, and the processor 104 can identify the first pixel row among these pixel rows. Each first pixel row may include multiple pixels, and only a single first specific pixel in each first pixel row has a first specified color. Further details can be found in [reference needed]. Figure 4 The explanation will not be repeated here.

[0050] exist Figure 5 In this context, the first pixel row identified by processor 104 is, for example, a pixel row including pixels 512a to 512k (i.e., the first specific pixel), but is not limited to this. Figure 5 It can be seen that each pixel 512a to 512k can have 8 surrounding pixels, and the processor 104 can find the fourth specific pixel from the pixels 512a to 512k based on the surrounding pixels of each pixel 512a to 512k.

[0051] For example, for a specific first pixel 520, the processor 104 can classify its eight surrounding pixels into a first group G1 and a second group G2. Figure 5 In the first group G1, the surrounding pixels of the first specific pixel 520 may include the upper left, left and lower left surrounding pixels, while the second group G2 may include the surrounding pixels of the first specific pixel 520 may include the upper right, right, lower right and lower surrounding pixels.

[0052] Then, the processor 104 can determine whether only one specified surrounding pixel in the second group G2 of the first specific pixel 520 has the first specified color. Figure 5 In this context, the specified surrounding pixels are, for example, the surrounding pixels to the upper right of the first specific pixel 520. That is, the processor 104 can determine whether only the surrounding pixels to the upper right of the first specific pixel 520 are black in the second group G2. If so, the processor 104 can consider the first specific pixel 520 as the fourth specific pixel; otherwise, it can consider the first specific pixel 520 not as the fourth specific pixel.

[0053] exist Figure 5 Of the pixels 512a to 512k shown (i.e., the first specific pixel), only pixel 512c meets the above conditions. Therefore, the processor 104 may regard pixel 512c as the fourth specific pixel, but it may not be limited to this.

[0054] Then, the processor 104 can replace each fourth specific pixel with a second specified color that is different from the first specified color. For example, the processor 104 can replace a pixel 512c that was originally black with white (i.e., the second specified color). In this way, the text "13" in the first image area 511 can be segmented accordingly to convert the first image area 511 into the second image area 530.

[0055] Please refer to this again. Figure 2 After converting the first image region into the second image region according to the above instructions, in step S240, the processor 104 may perform a character recognition operation on the second image region to obtain a first test result corresponding to the first test image TM1. In different embodiments, the processor 104 may perform a character recognition operation on the second image region according to any existing image character recognition algorithm.

[0056] by Figure 4 For example, processor 104 can perform text recognition on the second image region 430 to obtain a first test result of "fps:44". Then, taking... Figure 5 For example, the processor 104 can perform text recognition on the second image region 530 to obtain a first test result of "13 FPS (0-16)", but it is not limited to this.

[0057] In some embodiments, after obtaining the first test result, the processor 104 may also correct the first test result to a second test result based on a text correction table.

[0058] In one embodiment, the text correction table may include multiple preset error identification results and corresponding multiple preset correction results. In this case, in response to determining that the first test result corresponds to the first preset correction result among the preset correction results, the processor 104 may find the first preset correction result corresponding to the first preset correction result among the preset correction results and define the first preset correction result as the second test result.

[0059] To make the above concepts easier to understand, the text correction table shown in Table 1 is provided below for further explanation.

[0060] Preset recognition results Preset calibration results TPS fps fps, fps: FPS. fps: FPS! fps: B 8 S 5 ？ 7 l 1 g 9 b 6 -.\"‘, Replace with spaces

[0061] Table 1

[0062] As shown in Table 1, when the processor 104 determines that the obtained first test result includes a string corresponding to the preset recognition result "tps", the processor 104 can find the preset correction result "fps" corresponding to this preset recognition result and replace the aforementioned string with this preset correction result "fps" to generate a second test result. For another example, when the processor 104 determines that the obtained first test result includes a string corresponding to the preset recognition result "fps,", the processor 104 can find the preset correction result "fps:" corresponding to this preset recognition result and replace the aforementioned string with this preset correction result "fps:" to generate a second test result. Furthermore, when the processor 104 determines that the obtained first test result includes a string corresponding to the preset recognition result "-", ".", "\", "", "'", or ",", the processor 104 can find the preset correction result (i.e., a space) corresponding to this preset recognition result and replace the aforementioned string with this preset correction result to generate a second test result.

[0063] In some embodiments, the processor 104 may further control the imaging device 110 to capture a second test image of the display screen 120a of the display device 120 under test according to previously determined imaging parameters (e.g., an exposure value of -11). Then, the processor 104 may obtain a fourth image region corresponding to the reference image region from the second test image, and perform a text segmentation operation on the fourth image region to convert it into a fifth image region. Next, the processor 104 may perform a text recognition operation on the fifth image region to obtain a third test result corresponding to the second test image. Details of these operations can be found in the description of the previous embodiments and will not be repeated here.

[0064] In short, the processor 104 can repeatedly execute steps S220 to S240 until the required number of test images and their corresponding test results have been obtained, but it is not limited to this.

Claims

1. A method for identifying test results, characterized in that, Suitable for test result recognition devices, including: The image capturing device is controlled to capture a first image of the display screen of the display device under test according to at least one image capturing parameter, wherein the display screen of the display device under test includes a first specified string; An optical character recognition operation is performed on the first image to identify multiple text image regions in the first image, wherein each text image region includes at least one string; The reaction is that the first text image region in the plurality of text image regions includes the first specified string, and the first text image region is determined to be a reference image region in the first image. The reaction is that if none of the at least one string in each of the text image regions includes the first specified string, then it is determined that there is no image region in the first image that includes the first specified string. In response to determining that the first image contains the reference image region including the first specified string, the imaging device is controlled to capture a first test image of the display screen of the display device under test according to the at least one imaging parameter; A first image region corresponding to the reference image region is obtained from the first test image, and a text segmentation operation is performed on the first image region to convert the first image region into a second image region; and Perform text recognition operation on the second image region to obtain a first test result corresponding to the first test image.

2. The method of claim 1, wherein in response to determining that no image region in the first image contains the first specified string, the method further comprises: Adjust the at least one image acquisition parameter of the image acquisition device, and control the image acquisition device to capture a second image of the display screen of the display device under test according to the at least one image acquisition parameter; In response to the determination that the reference image region including the first specified string exists in the second image, the imaging device is controlled to capture the first test image on the display screen of the display device under test according to the at least one imaging parameter.

3. The method according to claim 1, wherein the first relative position of the reference image region and the first image corresponds to the second relative position of the first image region and the first test image.

4. The method according to claim 1, wherein the first image region comprises a plurality of pixel rows, and the step of performing the text segmentation operation on the first image region to convert the first image region into the second image region includes: Find at least one first pixel row among the plurality of pixel rows, wherein each first pixel row includes a plurality of pixels, and only a single first specific pixel among the plurality of pixels in each first pixel row has a first specified color; In each of the first specific pixels in the first pixel row, at least one second specific pixel is found, wherein the adjacent pixels on both sides of each second specific pixel have the first specified color; Find at least one third specific pixel among the at least one second specific pixel, wherein a specific pixel row exists on a designated side of each third specific pixel, wherein the specific pixel row is separated from the corresponding third specific pixel by a preset number of rows, and the specific pixel row includes N consecutive pixels with the first specified color, where N is a positive integer; and Each of the third specific pixels is replaced with a second specified color that is different from the first specified color.

5. The method according to claim 1, wherein the first image region comprises a plurality of pixel rows, and the step of performing the text segmentation operation on the first image region to convert the first image region into the second image region includes: Find at least one first pixel row among the plurality of pixel rows, wherein each first pixel row includes a plurality of pixels, only a single first specific pixel among the plurality of pixels in each first pixel row has a first specified color, and the first specific pixel in each first pixel row has 8 surrounding pixels; The eight surrounding pixels of the first specific pixel in each first pixel row are divided into a first group and a second group, and at least one fourth specific pixel is found in the first specific pixel in each first pixel row, wherein only the specified surrounding pixels in the second group corresponding to each fourth specific pixel have the first specified color. Each of the fourth specific pixels is replaced with a second specified color that is different from the first specified color.

6. The method of claim 1, wherein after obtaining the first test result corresponding to the first test image, the method further comprises: The first test result is corrected to the second test result based on the text correction table.

7. The method according to claim 6, wherein the text correction table includes a plurality of preset error recognition results and corresponding plurality of preset correction results, and the step of correcting the first test result to the second test result based on the text correction table includes: The reaction is to determine that the first test result includes a string corresponding to the first preset correction result among the plurality of preset correction results, and to find the first preset correction result corresponding to the first preset correction result among the plurality of preset correction results; as well as The string is replaced with the first preset correction result to generate the second test result.

8. The method according to claim 1, further comprising: The imaging device is controlled to capture a second test image of the display screen of the display device under test according to the at least one imaging parameter; Obtain a fourth image region corresponding to the reference image region from the second test image, and perform the text cutting operation on the fourth image region to convert the fourth image region into a fifth image region; as well as The text recognition operation is performed on the fifth image region to obtain a third test result corresponding to the second test image.

9. A test result recognition device, characterized in that, include: Storage circuitry that stores program code; A processor, coupled to the storage circuitry, accesses and executes the program code: The image capturing device is controlled to capture a first image of the display screen of the display device under test according to at least one image capturing parameter, wherein the display screen of the display device under test includes a first specified string; An optical character recognition operation is performed on the first image to identify multiple text image regions in the first image, wherein each text image region includes at least one string; The reaction is that the first text image region in the plurality of text image regions includes the first specified string, and the first text image region is determined to be a reference image region in the first image. The reaction is that if none of the at least one string in each of the text image regions includes the first specified string, then it is determined that there is no image region in the first image that includes the first specified string. In response to determining that the first image contains the reference image region including the first specified string, the imaging device is controlled to capture a first test image of the display screen of the display device under test according to the at least one imaging parameter; A first image region corresponding to the reference image region is obtained from the first test image, and a text segmentation operation is performed on the first image region to convert the first image region into a second image region; as well as Perform text recognition operation on the second image region to obtain a first test result corresponding to the first test image.

Images