IMAGE ANALYZATION METHOD AND IMAGE ANALYZATION DEVICE

Abstract

An image analyzation method and an image analyzation device are disclosed. The method includes: obtaining a first image which presents at least a first object and a second object; analyzing the first image to detect a first central point between a first endpoint of the first object and a second endpoint of the second object; determining a target region based on the first central point as a center of the target region; capturing a second image located in the target region from the first image; and analyzing the second image to generate status information which reflects a gap status between the first object and the second object.

Claims

1. An image analyzation method, comprising: obtaining a first image, wherein at least a first object and a second object are presented in the first image; analyzing the first image to detect a first central point between a first endpoint of the first object and a second endpoint of the second object; determining a target region in the first image based on the first central point as a center of the target region; capturing a second image located in the target region from the first image; and analyzing the second image to generate status information, wherein the status information reflects a gap status between the first object and the second object.

2. The image analyzation method according to claim 1, wherein there is a physical gap between the first object and the second object, and the first endpoint of the first object and the second endpoint of the second object are adjacent to each other through the physical gap.

3. The image analyzation method according to claim 1, wherein a third object is further presented in the first image, and the image analyzation method further comprises: analyzing the first image to detect a second central point between the second endpoint of the second object and a third endpoint of the third object; and determining a coverage range of the target region according to a distance between the first central point and the second central point.

4. The image analyzation method according to claim 3, wherein the distance between the first central point and the second central point is positively correlated with an area of the coverage range of the target region.

5. The image analyzation method according to claim 1, wherein capturing the second image located in the target region from the first image comprises: filtering out an image of at least a portion of endpoints or edges of the first object that is not located in the target region in the first image.

6. An image analyzation device, comprising: a storage circuit; and a processor coupled to the storage circuit, wherein the processor is configured to: obtain a first image, wherein at least a first object and a second object are presented in the first image; analyze the first image to detect a first central point between a first endpoint of the first object and a second endpoint of the second object; determine a target region in the first image based on the first central point as a center of the target region; capture a second image located in the target region from the first image; and analyze the second image to generate status information, wherein the status information reflects a gap status between the first object and the second object.

7. The image analyzation device according to claim 6, wherein there is a physical gap between the first object and the second object, and the first endpoint of the first object and the second endpoint of the second object are adjacent to each other through the physical gap.

8. The image analyzation device according to claim 6, wherein a third object is further presented in the first image, and the processor is further configured to: analyze the first image to detect a second central point between the second endpoint of the second object and a third endpoint of the third object; and determine a coverage range of the target region according to a distance between the first central point and the second central point.

9. The image analyzation device according to claim 8, wherein the distance between the first central point and the second central point is positively correlated with an area of the coverage range of the target region.

10. The image analyzation device according to claim 6, wherein an operation of capturing the second image located in the target region from the first image comprises: filtering out an image of at least a portion of endpoints or edges of the first object that is not located in the target region in the first image.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0008] FIG. 1 is a schematic view of an image analyzation device according to an embodiment of the disclosure.

[0009] FIG. 2 is a schematic view of a first image according to an embodiment of the disclosure.

[0010] FIG. 3 is a schematic view of detecting distances between multiple adjacent central points according to an embodiment of the disclosure.

[0011] FIG. 4 is a schematic view of determining a target region in a first image according to an embodiment of the disclosure.

[0012] FIG. 5 is a schematic view of a second image according to an embodiment of the disclosure.

[0013] FIG. 6 is a flowchart of an image analyzation method according to an embodiment of the disclosure.

DETAILED DESCRIPTION OF DISCLOSED EMBODIMENTS

[0014] FIG. 1 is a schematic view of an image analyzation device according to an embodiment of the disclosure. Referring to FIG. 1, a device (also referred to as an image analyzation device) 10 may be any electronic device or computer device with image analyzation and calculation functions. In an embodiment, the device 10 may also be an X-ray inspection device or an X-ray scanner (referred to as an X-ray machine).

[0015] The device 10 includes a processor 11, a storage circuit 12, and an input/output (I/O) device 13. The processor 11 is coupled to the storage circuit 12 and the I/O device 13. The processor 11 is configured to be responsible for the overall or partial operation of the device 10. For example, the processor 11 may include a central processing unit (CPU), a graphics processing unit (GPU), other programmable general-purpose or special-purpose microprocessors, a digital signal processor (DSP), a programmable controller, an application specific integrated circuit (ASIC), a programmable logic device PLD), other similar devices, or a combination of the devices.

[0016] The storage circuit 12 is configured to store data. For example, the storage circuit 12 may include a volatile storage circuit and a non-volatile storage circuit. The volatile storage circuit is configured to store the data volatilely. For example, the volatile storage circuit may include a random access memory (RAM) or similar volatile storage media. The non-volatile storage circuit is configured to store the data non-volatilely. For example, the non-volatile storage circuit may include a read only memory (ROM), a solid state disk (SSD), a traditional hard disk drive (HDD), or similar non-volatile storage media.

[0017] In an embodiment, the storage circuit 12 stores an image analyzation module 121 (also referred to as an image recognition module). The image analyzation module 121 may perform an image recognition operation such as machine vision. For example, the processor 11 may run the image analyzation module 121 to automatically recognize a specific object presented in a specific image file. In addition, the image analyzation module 121 may also be trained to improve a recognition accuracy. In an embodiment, the image analyzation module 121 may also be implemented as a hardware circuit. For example, the image analyzation module 121 may be implemented as an independent image processing chip (such as the GPU). In addition, the image analyzation module 121 may also be disposed inside the processor 11.

[0018] The I/O device 13 may include an input/output device of various signals such as a communication interface, a mouse, a keyboard, a screen, a touch screen, a speaker, and/or a microphone. The disclosure does not limit the type of the I/O device 13.

[0019] In an embodiment, the processor 11 may obtain an image (also referred to as a first image) 101. For example, the image 101 may be stored in the storage circuit 12. The image 101 may be an X-ray image. For example, the image 101 may be the X-ray image obtained by using the X-ray machine to perform X-ray irradiation or scanning on a specific part of a human body. Multiple objects may be presented in the image 101. For example, the objects include at least a first object and a second object.

[0020] In an embodiment, both the first object and the second object are skeletons of the human body. For example, the first object and the second object may include a vertebra (also referred to as an osteomere) of a neck or a back of the human body. For example, in an embodiment, the image 101 may be the X-ray image which may present a shape and an arrangement of the osteomeres of the neck or the back of the human body obtained by using the X-ray machine to perform the X-ray irradiation or scanning on the neck or the back of the human body.

[0021] In an embodiment, the processor 11 may analyze the image 101 through the image analyzation module 121, so as to detect an endpoint (also referred to as a first endpoint) of the first object and an endpoint (also referred to as a second endpoint) of the second object in the image 101. Next, the processor 11 may detect a central point (also referred to as a first central point) between the first endpoint and the second endpoint. The first central point may be located at a central position between the first endpoint and the second endpoint.

[0022] In an embodiment, the processor 11 may determine a region (also referred to as a target region) in the first image based on the first central point as a center of the target region, and capture an image (also referred to as a second image) 102 located in the target region from the first image. For example, a central position of the target region may be located at a position where the first central point is located and/or overlap with the first central point. For example, a shape of the target region may be a rectangle, a circle, or other shapes. In addition, the captured image 102 may also be stored in the storage circuit 12.

[0023] In an embodiment, the processor 11 may analyze the image 102 through the image analyzation module 121 to generate status information. In particular, the status information may reflect a status of a gap (also referred to as a gap status) between the first object and the second object. For example, if the first object and the second object are the two adjacently arranged osteomeres of the neck or the back of the human body, the status information may reflect the status of the gap between the two osteomeres (for example, a width of the gap between the two osteomeres or the closeness of the two osteomeres), a health status of the two osteomeres, whether the arrangement of the two osteomeres conforms to characteristics of a specific disease, and/or whether the gap between the two osteomeres conforms to the characteristics of the specific disease. For example, the specific disease may include ankylosing spondylitis or other diseases.

[0024] In an embodiment, the status information may include scoring information. The scoring information may reflect a health status of the human body or a risk of suffering from the specific disease. For example, in an embodiment, the scoring information may include mSASSS. The mSASSS may reflect a risk level of ankylosing spondylitis in the human body corresponding to the image 102 (or 101). In an embodiment, the scoring information may also reflect a risk level of other types of diseases in the human body. The disclosure is not limited thereto.

[0025] In an embodiment, the status information may be presented in a form of a report. For example, the status information may be presented on a display of the device 10. In an embodiment, the status information may be sent to other devices, such as a smart phone, a tablet computer, a notebook computer, or a desktop computer, so as to be viewed by a user of other devices.

[0026] FIG. 2 is a schematic view of a first image according to an embodiment of the disclosure. Referring to FIG. 2, in an embodiment, objects 21 to 26 arranged adjacently to one another may be present in the image 101. For example, the objects 21 to 26 may actually be the osteomeres (marked as A to F) of the specific part (such as the neck or back) of the human body. In addition, in the presented objects 21 to 26, there is a gap (also referred to as a physical gap) between every two of the adjacently arranged objects. It should be noted that the disclosure does not limit the total number and arrangement status of the objects 21 to 26 presented in the image 101.

[0027] In an embodiment, the processor 11 may analyze the image 101 to detect endpoints 201 to 210 on the objects 21 to 26. For example, the endpoint 201 is the endpoint at a lower left corner of the object 21. The endpoint 202 is the endpoint at an upper left corner of the object 22, and the endpoint 203 is the endpoint at a lower left corner of the object 22. The endpoint 204 is the endpoint at an upper left corner of the object 23, and the endpoint 205 is the endpoint at a lower left corner of the object 23. The endpoint 206 is the endpoint at an upper left corner of the object 24, and the endpoint 207 is the endpoint at a lower left corner of the object 24. The endpoint 208 is the endpoint at an upper left corner of the object 25, and the endpoint 209 is the endpoint at a lower left corner of the object 25. The endpoint 210 is the endpoint at an upper left corner of the object 26. It should be noted that the endpoints 201 to 210 are all located on the same side of the objects 21 to 26 (for example, the left side).

[0028] After finding the endpoints 201 to 210, the processor 11 may detect central points 211 to 251 between any two of the adjacent endpoints according to positions of the endpoints 201 to 210. For example, the central point 211 is located at a central position between the endpoints 201 and 202. The central point 221 is located at a central position between the endpoints 203 and 204. The central point 231 is located at a central position between the endpoints 205 and 206. The central point 241 is located at a central position between the endpoints 207 and 208. The central point 251 is located at a central position between the endpoints 209 and 210. After finding the central points 211 to 251, the processor 11 may detect a distance between any two of the adjacent central points among the central points 211 to 251.

[0029] FIG. 3 is a schematic view of detecting distances between multiple adjacent central points according to an embodiment of the disclosure. Referring to FIG. 3, following the embodiment of FIG. 2, the processor 11 may obtain distances D(1) to D(4) between any two of the adjacent central points among the central points 211 to 251. For example, the distance D(1) reflects a linear distance between the central points 211 and 221. The distance D(2) reflects a linear distance between the central points 221 and 231. The distance D(3) reflects a linear distance between the central points 231 and 241. The distance D(4) reflects a linear distance between the central points 241 and 251.

[0030] In an embodiment, the processor 11 may determine the target region in the image 101 based on one of the central points 211 to 251 as the center of the target region. In addition, the processor 11 may determine a coverage range of the target region according to at least one of the distances D(1) to D(4). For example, the at least one of the distances D(1) to D(4) may be positively correlated with an area of the coverage range of the target region. For example, if a value of the at least one of the distances D(1) to D(4) is larger, the area of the coverage range of the target region may also be larger.

[0031] In an embodiment, if the target region is a rectangle, the coverage range of the target region may be defined by a length and a width of the target region. Therefore, in an embodiment, the processor 11 may determine the length and/or the width of the target region according to the distance. In addition, if the target region is a circle, the coverage range of the target region may be defined by a radius of the target region. Therefore, in an embodiment, the processor 11 may determine the radius of the target region according to the distance.

[0032] FIG. 4 is a schematic view of determining a target region in a first image according to an embodiment of the disclosure. Referring to FIG. 4, following the embodiment of FIG. 3 and taking the central point 211 as an example, the processor 11 may determine a target region 41 based on the central point 211 as the center of the target region. A center of the target region 41 may be located at a position where the central point 211 is located and/or overlap with the central point 211. In an embodiment, the processor 11 may also determine the target region 41 based on any one of the central points 221 to 251 as the center of the target region. In addition, the processor 11 may determine a coverage range of the target region 41 according to the at least one of the distances D(1) to D(4).

[0033] In an embodiment, the processor 11 may determine a distance D(T) according to an average value (also referred to as an average distance) of at least two of the distances D(1) to D(4). The distance D(T) may be a half of a length and/or a width of the target region 41. In addition, in an embodiment, if the target region 41 is a circle, the distance D(T) may also be a radius of the target region 41. In an embodiment, the average distance may also be replaced by any one of the distances D(1) to D(4).

[0034] In an embodiment, the distance D(T) may also be fine-tuned through a function to slightly enlarge or reduce the distance D(T). In this way, even if a shape of at least one of the objects 21 to 26 is relatively irregular, and/or a size is quite different from the other objects, the fine-tuned distance D(T) may also provide higher operating tolerance for the objects 21 to 26.

[0035] After the distance D(T) is determined, the target region 41 may be determined in the image 101 according to the distance D(T). In addition, after determining the target region 41, the processor 11 may capture an image located in the target region 41 from the image 101 as the image 102.

[0036] FIG. 5 is a schematic view of a second image according to an embodiment of the disclosure. Referring to FIG. 5, following the embodiment of FIG. 4, the image 102 captured from the target region 41 may present at least a portion of the object 21 (i.e., the osteomere A) and at least a portion of the object 22 (i.e., the osteomere B). In particular, the image 102 may present a gap GP between the objects 21 and 22. Afterwards, the processor 11 may analyze the image 102 to generate status information that may reflect a status of the gap GP. For example, the status information may include the scoring information related to mSASSS or other useful information.

[0037] In an embodiment, in an operation of capturing the image 102 from the target region 41, the processor 11 may filter out an image of at least a portion of endpoints or edges of the objects 21 (and/or 22) that is not located in the target region 41 in the image 101. After filtering out the image of at least the portion of the endpoints or the edges of the objects 21 (and/or 22) that is not located in the target region 41, the remaining image is the image 102, as shown in FIG. 5. In this way, when the image 102 is subsequently analyzed by the image analyzation module 121, the image analyzation module 121 may focus on analyzing an image content related to the gap GP in the image 102 (such as a width and/or a shape of the gap GP, etc.) and generate the corresponding status information.

[0038] Compared with the image 101 which is analyzed directly in a large scale, information, in the image 102, which is irrelevant to the gap (such as the gap GP) between the osteomeres to be analyzed and may cause a misjudge of the image analyzation module 121 is filtered out (for example, a main display content of the image 102 is located at the gap GP between the two objects 21 and 22 (for example, the osteomeres A and B)). Therefore, the image analyzation module 121 may more accurately generate the status information that may reflect the status of the gap. In this way, an accuracy of automated image analyzation for the X-ray image may be effectively improved.

[0039] FIG. 6 is a flowchart of an image analyzation method according to an embodiment of the disclosure. Referring to FIG. 6, in step S601, the first image is obtained, and at least the first object and the second object are present in the first image. In step S602, the first image is analyzed to detect the first central point between the first endpoint of the first object and the second endpoint of the second object. In step S603, the target region is determined in the first image based on the first central point as the center of the target region. In step S604, the second image located in the target region is captured from the first image. In step S605, the second image is analyzed to generate the status information, and the status information reflects the gap status between the first object and the second object.

[0040] However, each of the steps in FIG. 6 has been described in detail as above. Thus, details in this regard will not be further reiterated in the following. It is worth noting that each of the steps in FIG. 6 may be implemented as multiple program codes or circuits, and the disclosure is not limited thereto. In addition, the method in FIG. 6 may be used in conjunction with the above exemplary embodiments, or may be used alone. The disclosure is not limited thereto.

[0041] Based on the above, in the embodiment of the disclosure, the information, in the original image (such as the X-ray image), which is irrelevant to the gap between the specific objects (such as the osteomeres) may be filtered out, and only the remaining image content is analyzed. In this way, the accuracy of the automated image analyzation for the image containing multiple objects may be effectively improved.

[0042] Although the disclosure has been described with reference to the above embodiments, they are not intended to limit the disclosure. It will be apparent to one of ordinary skill in the art that modifications to the described embodiments may be made without departing from the spirit and the scope of the disclosure. Accordingly, the scope of the disclosure will be defined by the attached claims and their equivalents and not by the above detailed descriptions.