Image acquisition device, image detection method and device

Abstract

The embodiment of the application discloses an image acquisition device, an image detection method and equipment, and belongs to the field of image processing. The image acquisition device comprises a first light source, a second light source, an image acquisition assembly and a placement plate, the material of the placement plate is a light-transmitting material; the first light source is located at a first side of the placement plate; the second light source is located at a second side of the placement plate, the first side is different from the second side; the image acquisition assembly is located at the second side of the placement plate, and the image acquisition assembly is opposite to the first light source. The image acquisition device can be used for acquiring the image of a target object and obtaining more information of the target object. Moreover, the information of the target object contained in the transmission image and the reflection image is not completely the same, so that more information quantity is obtained.

Description

Technical Field

[0001] This application relates to the field of image processing, and in particular to an image acquisition device, an image detection method and device. Background Technology

[0002] In daily life, we often need to process target objects to obtain processing results, which in turn allow us to perform corresponding follow-up operations. Target objects can be plant branches and leaves, human tissue, etc., and follow-up operations can include slicing, cutting, and disposal. For example, if the target object is a tissue block of human tissue, processing the tissue block can determine whether it contains diseased areas, and subsequent operations can be performed based on whether the tissue block contains diseased areas.

[0003] Currently, when processing target objects, technical personnel usually obtain observation results by directly observing the target objects. The observation results are somewhat subjective, and the amount of information that the human eye can obtain is relatively small. Summary of the Invention

[0004] This application provides an image acquisition device, an image detection method, and a device that acquire more information and improve detection accuracy. The technical solution is as follows:

[0005] On the one hand, an image acquisition device is provided, which includes a first light source, a second light source, an image acquisition component, and a mounting plate, wherein the mounting plate is made of a light-transmitting material;

[0006] The first light source is located on the first side of the shelf;

[0007] The second light source is located on the second side of the shelf, and the first side is different from the second side;

[0008] The image acquisition component is located on the second side of the shelf, and the image acquisition component is opposite to the first light source;

[0009] The image acquisition component is used to acquire a transmission image of a target object based on the light signal emitted by the first light source. The target object is placed on the second side of the shelf and has transparency.

[0010] The image acquisition component is also used to acquire the reflected image of the target object based on the light signal emitted by the second light source.

[0011] Optionally, the image acquisition device further includes a base, on which the first light source is fixedly mounted.

[0012] Optionally, the first light source and the second light source are any one of halogen lamps, incandescent lamps, or light-emitting diodes (LEDs).

[0013] Optionally, the shelf can be any one of frosted glass, frosted acrylic sheet, polycarbonate sheet, or white cardboard.

[0014] Optionally, the image acquisition component includes either a fixed-focus lens or a zoom lens.

[0015] On the other hand, an image acquisition method is provided, the method being applied to an image acquisition device; the image acquisition device includes a first light source, a second light source, an image acquisition component, and a mounting plate, the mounting plate being made of a light-transmitting material; the first light source is located on a first side of the mounting plate; the second light source is located on a second side of the mounting plate, the first side being different from the second side; the image acquisition component is located on the second side of the mounting plate, and the image acquisition component is opposite to the first light source; the method includes:

[0016] When the first light source is turned on and the second light source is turned off, the image acquisition component acquires a transmission image of the target object based on the light signal emitted by the first light source. The target object is placed on the second side of the shelf and has transparency.

[0017] When the first light source is turned off and the second light source is turned on, the image acquisition component acquires the reflected image of the target object based on the light signal emitted by the second light source.

[0018] Optionally, after acquiring the reflection image of the target object, the method further includes:

[0019] The transmitted image and the reflected image are detected to identify abnormal regions in the target object;

[0020] The abnormal region is displayed in the detection image of the target object, where the detection image refers to the transmission image or the reflection image.

[0021] On the other hand, an image detection system is provided, comprising an image acquisition device and an image detection device; the image acquisition device includes a first light source, a second light source, an image acquisition component, and a mounting plate, the mounting plate being made of a light-transmitting material; the first light source is located on a first side of the mounting plate; the second light source is located on a second side of the mounting plate, the first side being different from the second side; the image acquisition component is located on the second side of the mounting plate, and the image acquisition component is opposite to the first light source;

[0022] The image acquisition component is used to acquire a transmission image of a target object based on the light signal emitted by the first light source. The target object is placed on the second side of the shelf and has transparency.

[0023] The image acquisition component is also used to acquire the reflected image of the target object based on the light signal emitted by the second light source;

[0024] The image acquisition component is also used to send the transmitted image and the reflected image to the image processing device;

[0025] The image detection device is used to detect the transmitted image and the reflected image to determine abnormal regions in the target object;

[0026] The image detection device is also used to display the abnormal region in the detected image, wherein the detected image is the transmission image or the reflection image.

[0027] On the other hand, an image detection method is provided, the method comprising:

[0028] Acquire a transmission image and a reflection image of a target object. The transmission image is obtained based on a first light signal, and the reflection image is obtained based on a second light signal. The first light signal is the light signal obtained after the light emitted by the first light source is transmitted through the target object, and the second light signal is the light signal obtained after the light emitted by the second light source is reflected through the target object.

[0029] The transmitted image and the reflected image are detected to identify abnormal regions in the target object;

[0030] The abnormal region is displayed in the detection image of the target object, where the detection image refers to the transmission image or the reflection image.

[0031] Optionally, before detecting the transmitted image and the reflected image to determine the abnormal region in the target object, the method further includes:

[0032] The transmission image and the reflection image are preprocessed respectively to obtain the preprocessed transmission image and the preprocessed reflection image.

[0033] Optionally, displaying the abnormal region in the detected image of the target object includes:

[0034] The abnormal areas are marked with a preset color in the detected image; or,

[0035] The abnormal regions are marked with contour lines in the detected image.

[0036] Optionally, the image detection model is trained through the following steps:

[0037] Acquire a first sample image, a second sample image, and a third sample image. The first sample image is acquired based on a third optical signal, and the second sample image is acquired based on a fourth optical signal. The third optical signal is the optical signal obtained after the optical signal emitted by the first light source is transmitted through the sample object, and the fourth optical signal is the optical signal obtained after the optical signal emitted by the second light source is reflected by the sample object. The third sample image is an image of the sample object marked with sample abnormal areas.

[0038] The image detection model is trained based on the first sample image, the second sample image, and the third sample image.

[0039] Optionally, the method further includes:

[0040] If the proportion of the abnormal region is greater than a preset proportion, the target object is identified as an abnormal object.

[0041] On the other hand, an image detection apparatus is provided, the apparatus comprising:

[0042] The image acquisition module is used to acquire a transmission image and a reflection image of a target object. The transmission image is acquired based on a first light signal, and the reflection image is acquired based on a second light signal. The first light signal is the light signal obtained after the light emitted by the first light source is transmitted through the target object, and the second light signal is the light signal obtained after the light emitted by the second light source is reflected through the target object.

[0043] The detection module is used to detect the transmitted image and the reflected image to determine abnormal areas in the target object;

[0044] An abnormal region display module is used to display the abnormal region in the detection image of the target object, wherein the detection image refers to the transmission image or the reflection image.

[0045] Optionally, the detection module includes:

[0046] The first detection unit is used to detect the transmission image and obtain the transmission features corresponding to the transmission image;

[0047] The second detection unit is used to detect the reflection image and obtain the reflection features corresponding to the reflection image;

[0048] An abnormal region acquisition unit is used to detect the transmission features and the reflection features to obtain the abnormal region.

[0049] Optionally, the device further includes:

[0050] The preprocessing module is used to preprocess the transmission image and the reflection image respectively to obtain the preprocessed transmission image and the preprocessed reflection image.

[0051] Optionally, the abnormal area display module is used for:

[0052] The abnormal areas are marked with a preset color in the detected image; or,

[0053] The abnormal regions are marked with contour lines in the detected image.

[0054] Optionally, the detection module is used to call an image detection model to detect the transmission image and the reflection image to determine abnormal regions in the target object.

[0055] Optionally, the image detection model is trained through the following steps:

[0056] Acquire a first sample image, a second sample image, and a third sample image. The first sample image is acquired based on a third optical signal, and the second sample image is acquired based on a fourth optical signal. The third optical signal is the optical signal obtained after the optical signal emitted by the first light source is transmitted through the sample object, and the fourth optical signal is the optical signal obtained after the optical signal emitted by the second light source is reflected by the sample object. The third sample image is an image of the sample object marked with sample abnormal areas.

[0057] The image detection model is trained based on the first sample image, the second sample image, and the third sample image.

[0058] Optionally, the device further includes:

[0059] An abnormal object determination module is used to determine the target object as an abnormal object in response to the proportion of the abnormal area being greater than a preset proportion.

[0060] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one piece of program code, the at least one piece of program code being loaded and executed by the processor to perform the operations performed in the image detection method as described above.

[0061] On the other hand, a computer-readable storage medium is provided that stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed in the image detection method described above.

[0062] On the other hand, a computer program product or computer program is provided, the computer program product or computer program including computer program code stored in a computer-readable storage medium, wherein a processor of the computer device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the computer device to perform the operations performed in the image detection method described above.

[0063] The beneficial effects of the technical solutions provided in this application include at least the following:

[0064] The image acquisition device provided in this application embodiment has light sources set at different locations. By turning on different light sources, it can acquire both transmitted and reflected images of the target object. Compared with naked-eye observation in related technologies, this method of acquiring images of the target object can obtain more information about the target object. Furthermore, the information about the target object contained in the transmitted and reflected images is not entirely the same, thus obtaining a greater amount of information.

[0065] The image detection method provided in this application, when detecting transmitted and reflected images, recognizes that the information about the target object contained in the transmitted and reflected images is not entirely the same. By utilizing more information, a more accurate detection result can be obtained, thus improving the detection accuracy. Furthermore, compared to related technologies where observation is obtained by the human eye, the detection results obtained by the image detection device are more objective, further improving the detection accuracy. Attached Figure Description

[0066] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 This is a schematic diagram of the structure of an image acquisition device provided in an embodiment of this application;

[0068] Figure 2 This is a schematic diagram of the structure of another image acquisition device provided in an embodiment of this application;

[0069] Figure 3This is a schematic diagram of an image detection system provided in an embodiment of this application;

[0070] Figure 4 This is a flowchart of an image acquisition method provided in an embodiment of this application;

[0071] Figure 5 This is a flowchart of an image detection method provided in an embodiment of this application;

[0072] Figure 6 This is a schematic diagram of a transmission image provided in an embodiment of this application;

[0073] Figure 7 This is a schematic diagram of a reflected image provided in an embodiment of this application;

[0074] Figure 8 This is a schematic diagram of an image detection based on deep learning provided in an embodiment of this application;

[0075] Figure 9 This is a schematic diagram of a trained image detection model provided in an embodiment of this application;

[0076] Figure 10 This is a schematic diagram of the structure of an image detection device provided in an embodiment of this application;

[0077] Figure 11 This is a schematic diagram of another image detection device provided in an embodiment of this application;

[0078] Figure 12 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0079] Figure 13 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0081] It is understood that the terms "first," "second," etc., used in this application may be used to describe various concepts herein, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of this application, a first light source may be referred to as a second light source, and a second light source may be referred to as a first light source.

[0082] As used in this application, the terms "each," "multiple," etc., include "multiple" (two or more), and "each" refers to each of the corresponding multiple. For example, multiple sub-light sources include four sub-light sources, and "each sub-light source" refers to each of these four sub-light sources.

[0083] Artificial intelligence (AI) is the theory, methods, technology, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results. In other words, AI is a comprehensive technology within computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI studies the design principles and implementation methods of various intelligent machines, enabling them to possess the functions of perception, reasoning, and decision-making.

[0084] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0085] Computer vision (CV) is a science that studies how to enable machines to "see." More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes in recognizing and measuring targets, and further processes images to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, OCR (Optical Character Recognition), video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0086] Machine learning (ML) is a multidisciplinary field involving probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how computers can simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to endow computers with intelligence; its applications span all areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learn-by-doing.

[0087] With the research and advancement of artificial intelligence (AI) technology, AI is being studied and applied in various fields, such as smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, autonomous driving, drones, robots, smart healthcare, and smart customer service. It is believed that with the development of technology, AI will be applied in more fields and play an increasingly important role.

[0088] The solutions provided in this application involve artificial intelligence technologies such as computer vision or machine learning, which are specifically illustrated in the following embodiments.

[0089] Figure 1 This is a schematic diagram of the structure of an image acquisition device provided in an embodiment of this application. See also... Figure 1 The image acquisition device includes a first light source 11, a second light source 12, an image acquisition component 13, and a placement plate 14.

[0090] The first light source 11 is located on the first side of the shelf 14, the second light source 12 is located on the second side of the shelf 14, and the image acquisition component 13 is located on the second side of the shelf 14, wherein the first side and the second side are different.

[0091] exist Figure 1 In the image acquisition device shown, the first side of the mounting plate 14 refers to the side below the mounting plate 14, and the second side of the mounting plate 14 refers to the side above the mounting plate 14. That is, the first light source 11 is located below the mounting plate 14, and the second light source 12 and the image acquisition component 13 are located above the mounting plate 14.

[0092] In this image acquisition device, although both the second light source 12 and the image acquisition component 13 are located above the mounting plate 14, their relative positions to the mounting plate 14 are different to avoid the second light source 12 obstructing the image acquisition component 13 and affecting its image acquisition, or to avoid the image acquisition component 13 obstructing the second light source 12 and affecting the propagation of the light signal emitted by the second light source 12. For example, the image acquisition component 13 may be located directly above the mounting plate 14, while the second light source 12 may be located diagonally above the mounting plate 14.

[0093] The image acquisition component 13 is opposite to the first light source 11 so that the light signal emitted by the first light source 11 can be transmitted to the image acquisition component 13.

[0094] Image acquisition principle:

[0095] In this embodiment, the principle of the image acquisition device acquiring a transmission image is as follows: a first light source 11 is located on the first side of a mounting plate 14, a target object is placed on the second side of the mounting plate 14, and an image acquisition component 13 is located on the second side of the mounting plate 14. The light signal emitted by the first light source 11 propagates to the mounting plate 14, passes through the mounting plate 14 and the target object, and then a first light signal is obtained. This first light signal propagates to the image acquisition component 13, thereby enabling the image acquisition component 13 to acquire a transmission image of the target object. In other words, the image acquisition component 13 acquires a transmission image of the target object based on the light signal emitted by the first light source 11.

[0096] The shelf 14 and the target object are both transparent. The shelf 14 is made of a light-transmitting material, and the light signal emitted by the first light source 11 passes through the shelf 14 and the target object. For example, the target object is a light-transmitting object such as human tissue or plant leaves, and the light-transmitting material is a frosted glass, frosted acrylic sheet, polycarbonate (PC) sheet, or white cardboard.

[0097] Optionally, the shelf 14 includes a light-transmitting area and a non-light-transmitting area, and when placing a target object, the target object is placed in the light-transmitting area.

[0098] In addition, the size of the shelf 14 is larger than the preset size so that the target object can be placed completely on the shelf 14. The preset size is any size, and the shelf 14 is of any shape, such as a circle, rectangle, square, etc.

[0099] The principle of the image acquisition device for acquiring reflected images is as follows: the second light source 12 and the image acquisition component 13 are located on the same side of the target object. After the light signal emitted by the second light source 12 propagates to the target object, it is reflected by the target object to obtain a second light signal. The second light signal propagates to the image acquisition component 13, thereby enabling the image acquisition component 13 to acquire the reflected image of the target object. That is, the image acquisition component 13 acquires the reflected image of the target object based on the light signal emitted by the second light source 12.

[0100] Regarding the first and second supports:

[0101] In one possible implementation, the image acquisition device further includes a first bracket 15 and a second bracket 16. The placement plate 14 is disposed on the first bracket 15, and the image acquisition component 13 is disposed on the second bracket 16. The second bracket 16 can move relative to the first bracket 15, thereby moving the image acquisition component 13 relative to the placement plate 14. By moving the image acquisition component 13, the focal length between the lens in the image acquisition component 13 and the target object can be adjusted to capture a complete and clear target object.

[0102] The placement plate 14 is fixed on the first bracket 15, and the height of the placement plate 14 remains unchanged. The second bracket 16 is moved to change the distance between the image acquisition component 13 and the target object on the placement plate 14.

[0103] In one possible implementation, the first support 15 is fixed, while the second support 16 is moved, thereby enabling the second support 16 to move relative to the first support 15.

[0104] Optionally, the first support 15 is provided with a sliding rail, and the second support 16 is disposed in the sliding rail. When the second support 16 is subjected to an external force, it moves along the sliding rail. The sliding rail is located above the shelf 14, that is, the starting position of the sliding rail is the uppermost end of the first support 15, and the ending position is any position above the shelf 14 that is different from the starting position.

[0105] The length of the sliding track is the adjustable range of the focal length.

[0106] In another possible implementation, the first bracket 15 includes a first segment and a second segment, and the second segment is movable relative to the first segment. The second bracket 16 is disposed on the second segment. When the first segment is fixed and the second segment is moved, the second bracket 16 moves relative to the first segment of the first bracket 15, thereby driving the image acquisition component 13 disposed on the second bracket 16 to move relative to the placement plate 14.

[0107] Optionally, the first support 15 has a hollow structure inside, with the first segment nested inside the second segment. The size of the first segment is larger than that of the second segment, allowing the second segment to move inside the first segment.

[0108] Regarding the image acquisition component:

[0109] The image acquisition component 13 includes a lens, which can be a fixed-focus lens or a zoom lens. The focal length of the fixed-focus lens is constant, while the zoom lens can automatically adjust the focal length through optical zoom. If the lens is a fixed-focus lens, the focal length can be adjusted using the structure of the first bracket 15 and the second bracket 16 described above; if the lens is a zoom lens, the focal length can also be adjusted using the structure of the first bracket 15 and the second bracket 16 described above.

[0110] In another embodiment, the second bracket 16 is fixedly connected to the first bracket 15, and the lens is a zoom lens. When acquiring an image of the target object, the lens can automatically zoom to achieve focal length adjustment.

[0111] In addition, the image acquisition component 13 can be an industrial color camera, a low frame rate rolling shutter camera, a smartphone, or other shooting devices. When the image acquisition component 13 is a low frame rate rolling shutter camera, since the target object is stationary, compared to using other shooting devices, it ensures the quality of the acquired image while reducing costs. When the image acquisition component 13 is a smartphone, a shooting bracket for fixing the phone is also provided on the second bracket 16.

[0112] Regarding the first light source:

[0113] The first light source 11 provides light signals for acquiring the transmitted image of the target object. In one possible implementation, the image acquisition device also includes a base 18, on which the first light source 11 is fixedly mounted.

[0114] Optionally, the base 18 is connected to the first bracket 15.

[0115] Optionally, the first light source 11 includes multiple sub-light sources to provide sufficient light signals and avoid the problem that the light signals emitted by the first light source 11 are too weak and cannot pass through the target object.

[0116] Regarding the second light source and the third support:

[0117] In one possible implementation, see Figure 2 The schematic diagram of the image acquisition device shown includes a third bracket 17, a second light source 12 mounted on the third bracket 17, and the third bracket 17 fixedly connected to the first bracket 15.

[0118] In another possible implementation, the image acquisition device includes multiple third supports 17, and the second light source 12 includes multiple sub-light sources. These multiple third supports 17 are fixedly connected to the first support 15 and are symmetrical about the first support 15. Each sub-light source is positioned on one third support 17, so that when the second light source 12 is turned on, both sides of the target object can receive illumination, thus avoiding the problem of shadows appearing on the other side when only one side has a light source. One or more sub-light sources can be positioned on each third support 17.

[0119] For example, such as Figure 2 The image acquisition device shown has two third supports 17, and each third support 17 has a sub-light source.

[0120] Optionally, the number of sub-light sources set on each third bracket 17 can be the same or different.

[0121] Optionally, multiple third supports 17 can be set at the same height or at different heights.

[0122] In one possible implementation, each third support 17 includes a first part and a second part, connected by a connecting shaft. The first part is fixedly connected to a first support 15. A second light source 12 is disposed on the second part. Under the action of an external force, the second part rotates around the connecting shaft, causing the second light source 12 to rotate around the connecting shaft, thereby changing the angle between the second light source 12 and the shelf 14. The angle between the second light source 12 and the shelf 14 refers to the angle between the second light source 12 and the target object on the shelf 14, and this angle can be any angle between 0 degrees and 90 degrees.

[0123] Optionally, for multiple third supports 17, the angle between the sub-light source disposed on the multiple third supports 17 and the shelf 14 can be the same or different.

[0124] In another possible implementation, corresponding to the case where the first support 15 includes a first segment and a second segment, the third support 17 is fixedly connected to the first segment of the first support 15, that is, the position of the third support 17 is fixed.

[0125] In addition, in this embodiment, the first light source 11 and the second light source 12 are any light source covering the visible light band, such as halogen lamps, incandescent lamps, and LEDs (Light Emitting Diodes). Optionally, the first light source 11 and the second light source 12 can be the same or different.

[0126] In one possible implementation, the image acquisition device further includes a light-shielding box, inside which the first light source 11, the second light source 12, the image acquisition component 13, and the placement plate 14 are located. The light-shielding box can block external light signals, thereby ensuring that the image acquisition process is not affected by other light signals.

[0127] The image acquisition device provided in this application embodiment has light sources set at different locations. By turning on different light sources, it can acquire both transmitted and reflected images of the target object. Compared with naked-eye observation in related technologies, this method of acquiring images of the target object can obtain more information about the target object. Furthermore, the information about the target object contained in the transmitted and reflected images is not entirely the same, thus obtaining a greater amount of information.

[0128] Furthermore, the second bracket in the image acquisition device moves relative to the first bracket to adjust the focal length between the lens and the target object, ensuring that the image acquisition component can acquire a complete and clear image.

[0129] Furthermore, by placing each part of the image acquisition device in a light-shielding box, the influence of light signals emitted by external light sources can be blocked, making the acquired transmitted and reflected images more accurate.

[0130] Furthermore, compared to related technologies that use radiographic imaging equipment to acquire radiographic images of target objects, which involves ionizing radiation during image acquisition and can affect the human body, the image acquisition equipment in this application does not emit ionizing radiation, thus reducing the impact on the human body. Moreover, radiographic imaging equipment is expensive, leading to higher costs. The image acquisition equipment in this application employs a dual-modal illumination structure, resulting in lower costs and reducing the overall cost of image acquisition.

[0131] Figure 3 This is a schematic diagram of an image detection system provided in an embodiment of this application. See also... Figure 3 The image detection system includes an image acquisition device 301 and an image detection device 302.

[0132] The image acquisition device 301 includes a first light source, a second light source, an image acquisition component, and a mounting plate made of a light-transmitting material. The first light source is located on a first side of the mounting plate; the second light source is located on a second side of the mounting plate, and the first and second sides are different; the image acquisition component is located on the second side of the mounting plate and is opposite to the first light source. The structure of this image acquisition device 301 is the same as described above. Figure 1 The image acquisition devices shown in the embodiments have similar structures and will not be described again here.

[0133] The image acquisition component in the image acquisition device 301 is communicatively connected to the image detection device 302. The image acquisition component and the image detection device 302 can be directly or indirectly connected via wired or wireless communication, for example, via Bluetooth, Wi-Fi (Wireless Fidelity) or other means.

[0134] The image acquisition component is used to acquire a transmission image of the target object based on the light signal emitted by the first light source; the image acquisition component is also used to acquire a reflection image of the target object based on the light signal emitted by the second light source; the image acquisition component is also used to send the transmission image and the reflection image to the image processing device; the image detection device 302 is used to detect the transmission image and the reflection image to determine abnormal areas in the target object; the image detection device 302 is also used to display the abnormal areas in the detection image, where the detection image is a transmission image or a reflection image.

[0135] The implementation methods for acquiring transmission and reflection images by the image acquisition component are detailed below. Figure 4 The embodiment shown; the implementation method of image detection device 302 detecting transmission images and reflection images is detailed below. Figure 5 The embodiments shown will not be described in detail here.

[0136] In one possible implementation, the image detection device 302 is a terminal. The terminal can be a variety of types, such as portable, pocket-sized, or handheld, including smartphones, tablets, laptops, desktop computers, smart speakers, and smartwatches.

[0137] In another possible implementation, the image processing device 302 includes a server and a terminal. The server detects the transmission and reflection images, identifies abnormal regions in the target object, and sends the transmission image, reflection image, and abnormal regions to the terminal. The terminal displays the abnormal regions in the detected image. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Furthermore, the terminal and server can be directly or indirectly connected via wired or wireless communication; this application does not impose any limitations on this.

[0138] In another embodiment, if the image acquisition component is a smartphone and the smartphone is capable of detecting transmitted and reflected images, the smartphone is used as an image detection device. After the image acquisition component acquires the transmitted and reflected images, it directly detects the transmitted and reflected images without needing to send them to other devices.

[0139] The image detection system provided in this application embodiment allows the image acquisition device to acquire both transmitted and reflected images of the target object by activating different light sources. Since the transmitted and reflected images contain slightly different information about the target object, more information about it is obtained. When the image detection device detects the acquired images, it can obtain more accurate detection results based on this increased information, thus improving detection accuracy. Furthermore, compared to the human eye observation method in related technologies, the detection results obtained by the image detection device are more objective, further improving detection accuracy.

[0140] Figure 4 This is a flowchart of an image acquisition method provided in an embodiment of this application. See also... Figure 4 This method is applied to the above Figure 1 or Figure 2 In the image acquisition device shown, the method includes the following steps:

[0141] 401. When the first light source is turned on and the second light source is turned off, the image acquisition component acquires a transmission image of the target object based on the light signal emitted by the first light source.

[0142] In this embodiment, the first light source provides light signals for acquiring transmitted images, and the second light source provides light signals for acquiring reflected images.

[0143] When acquiring a transmission image, to avoid the influence of the light signal emitted by the second light source, the second light source is turned off, and only the first light source is turned on. After the light signal emitted by the first light source propagates to the target object, it passes through the target object to obtain the first light signal. The first light signal propagates to the image acquisition component, and the image acquisition component acquires the transmission image of the target object.

[0144] In one possible implementation, after turning off the second light source and turning on the first light source, the image acquisition component is moved up and down to adjust the focal length between the lens in the image acquisition component and the target object until a complete and clear transmission image can be acquired. The movement of the image acquisition component is then stopped, and the image acquisition component is fixed in the current position. Then, the transmission image of the target object is acquired.

[0145] 402. When the second light source is turned on and the first light source is turned off, the image acquisition component acquires the reflected image of the target object based on the light signal emitted by the second light signal.

[0146] When acquiring reflected images, to avoid the influence of the light signal emitted by the first light source, the first light source is turned off, and only the second light source is turned on. After the light signal emitted by the second light source propagates to the target object, it is reflected by the target object to obtain a second light signal. The second light signal propagates to the image acquisition component, and the image acquisition component acquires the reflected image of the target object.

[0147] In one possible implementation, if the focal length between the lens and the target object has already been adjusted when acquiring the transmission image, no further adjustment is needed; if the focal length between the lens and the target object has not been adjusted, the focal length between the lens and the target object is adjusted in a manner similar to that described in the above possible implementations.

[0148] In one possible implementation, for each target object, the image acquisition component can acquire one transmission image and one reflection image; alternatively, to avoid randomness, the image acquisition component can acquire multiple transmission images and multiple reflection images. Optionally, when acquiring multiple transmission images and multiple reflection images, the position of the target object on the placement plate can be changed to avoid poor image quality due to poor target object placement. Specifically, when acquiring a set of transmission and reflection images, the target object's position needs to be the same to avoid discrepancies in the information reflected in the transmission and reflection images due to position changes, which could affect subsequent detection processes.

[0149] In another possible implementation, after the image acquisition component acquires the transmission image and the reflection image, it can also detect the transmission image and the reflection image to determine abnormal regions in the target object and display the abnormal regions in the detected image of the target object, which is either a transmission image or a reflection image.

[0150] Optionally, when the image acquisition component has an image detection function, it can directly detect the transmitted and reflected images after acquiring them.

[0151] Optionally, if the image acquisition component does not have an image detection function, the image acquisition component will send the transmitted image and the reflected image to a device with an image detection function for detection.

[0152] It should be noted that the embodiments of this application are only illustrated by taking the example of acquiring the transmission image first and then the reflection image. In another embodiment, the reflection image can be acquired first and then the transmission image can be acquired. The embodiments of this application do not limit the order of acquisition of the transmission image and the reflection image.

[0153] In the image acquisition method provided in this application embodiment, when different light sources are turned on, the transmission image and reflection image of the target object can be acquired respectively. The information of the target object contained in the transmission image and the reflection image are not completely the same, thereby obtaining more information, so that the image of the target object can be detected based on more information.

[0154] Figure 5 This is a flowchart of an image detection method provided in an embodiment of this application. See also... Figure 5 This method, applied to an image detection device, includes the following steps:

[0155] 501. Obtain the transmission and reflection images of the target object.

[0156] The transmission image is obtained based on the first light signal, and the reflection image is obtained based on the second light signal. The first light signal is the light signal obtained after the light emitted by the first light source is transmitted through the target object, and the second light signal is the light signal obtained after the light emitted by the second light source is reflected through the target object.

[0157] In one possible implementation, the above-mentioned Figure 1 or Figure 2 The image acquisition device shown acquires both transmission and reflection images of the target object. Alternatively, transmission and reflection images can also be acquired using other devices.

[0158] Both transmission and reflection images can reflect the surface information of a target object. Taking human tissue as an example, when acquiring transmission images, different types of human tissue have different light transmittance. Some types of tissue have poor light transmittance, while others have good light transmittance. Therefore, when light signals pass through human tissue, areas with poor light transmit less light, while areas with good light transmit more light. In the transmission image acquired by the image acquisition device, the darker areas represent areas with poor light transmittance, and the brighter areas represent areas with good light transmittance. The boundary between the darker and brighter areas will also be more obvious. Therefore, transmission images can better reflect the division of areas containing different types of tissue.

[0159] When acquiring a reflected image, the light signal is reflected by the surface of the target object. Different areas of the target object reflect the light signal differently. Therefore, the texture of the target object's surface can be clearly seen in the reflected image acquired by the image acquisition device. Thus, the reflected image can reflect more of the texture information of the target object's surface.

[0160] For example, taking the target object as breast tissue removed, Figure 6A 600-degree transmission image of the excised breast tissue. Figure 7 This is a reflection image of the removed breast tissue at 700°. Figure 6 The upper right and lower right areas of the target object are fat, while the other areas are the lesion areas. Figure 6 The boundaries between the upper right and lower right areas and other areas are clearly visible in the text; Figure 7 The texture of the target object's surface can be seen, although the colors of different areas also differ, but... Figure 6 Compared to the transmission image 600 shown, Figure 6 The dividing line in the middle is more obvious.

[0161] 502. Detect the transmission and reflection images to identify abnormal areas in the target object.

[0162] Transmission images can better reflect the division of different regions within a target object. If only transmission images are inspected, darker and brighter areas can be detected, and the darker areas will be considered abnormal. However, not all darker areas are abnormal, making it impossible to accurately identify abnormal areas. Reflection images can better reflect the texture information of the target object's surface. If only reflection images are inspected, areas with different colors on the target object's surface can be detected. However, if an abnormality exists inside the target object but appears normal from the surface, that area will be considered normal, and it will also be impossible to accurately identify abnormal areas.

[0163] Therefore, in this embodiment of the application, both the transmission image and the reflection image are considered to determine the abnormal area in the target object.

[0164] An abnormal area refers to an area in the target object that has changed. For example, if the target object is human tissue, the abnormal area is the area in the human tissue that has become diseased; if the target object is a plant leaf, the abnormal area is the area in the leaf that has withered, and so on.

[0165] In one possible implementation, the image detection device detects the transmission image to obtain the transmission features corresponding to the transmission image; it also detects the reflection image to obtain the reflection features corresponding to the reflection image; and by detecting both the transmission and reflection features, it identifies abnormal regions. The transmission features represent different regions of varying brightness within the target object, while the reflection features represent the texture information of the target object's surface.

[0166] In one possible implementation, before detecting the transmission and reflection images, the transmission and reflection images are preprocessed respectively to remove irrelevant information in the images, resulting in preprocessed transmission and reflection images. Image preprocessing includes image denoising, image enhancement, image background correction, and image registration.

[0167] In one possible implementation, the image detection device invokes an image detection model to detect both the transmission and reflection images, identifying anomalous regions within the target object. For example, see... Figure 8 The schematic diagram shows that image preprocessing is performed on the transmission image and the reflection image. The preprocessed transmission image and the preprocessed reflection image are then input into the image detection model. The image detection model processes the transmission image and the reflection image to obtain the prediction result.

[0168] Among them, the image detection models are deep learning networks such as CNN (Convolutional Neural Networks), U-Net (a neural network for image segmentation), and GAN (Generative Adversarial Networks).

[0169] Before using the image detection model, it needs to be trained by acquiring a first sample image, a second sample image, and a third sample image. The image detection model is then trained based on these three images. The first sample image is obtained based on a third light signal, and the second sample image is obtained based on a fourth light signal. The third light signal is the light signal obtained after the light emitted by the first light source is transmitted through the sample object, and the fourth light signal is the light signal obtained after the light emitted by the second light source is reflected by the sample object. The third sample image is an image of the sample object marked with abnormal regions. For example, the third sample image could be a whole-slide image (WSI) of the sample object or other labeled images.

[0170] In one possible implementation, image preprocessing is performed on the first sample image, the second sample image, and the third sample image. Based on the preprocessed first sample image, the second sample image, and the third sample image, an image detection model is trained. Image preprocessing includes image registration, image denoising, image enhancement, and image background correction.

[0171] For example, see Figure 9The schematic diagram shows that the sample reflection image 901, sample transmission image 902, and sample WSI image 903 are preprocessed. The preprocessed sample transmission image, sample reflection image, and sample WSI image are then input into the image detection model to be trained. The image detection model processes the sample transmission image and sample reflection image to obtain the prediction result.

[0172] In one possible implementation, a first sample image, a second sample image, and a third sample image are input into an image detection model to be trained. The image detection model outputs a prediction result. The difference between the prediction result and the anomaly region marked in the third sample image is compared, and the parameters of the image detection model are adjusted to reduce the difference, so that the image detection model learns the ability to detect anomaly regions based on the transmission and reflection images.

[0173] In one possible implementation, after calling the image detection model to detect the transmission and reflection images, the image detection model can continue to be trained. Optionally, the detected transmission and reflection images can be used as training sample images, and the above training process can be repeated to continue training the image detection model.

[0174] In another possible implementation, machine learning algorithms such as Principal Component Analysis (PCA) can be used to detect transmission and reflection images.

[0175] In this embodiment of the application, an image detection model or other machine learning algorithm is used to perform region segmentation on the transmission or reflection image of the target object in order to detect abnormal regions in the transmission or reflection image.

[0176] 503. Display abnormal areas in the detected image of the target object.

[0177] The detected image refers to either a transmission image or a reflection image. That is, marking abnormal areas within the transmission or reflection image.

[0178] In one possible implementation, abnormal regions are marked with a preset color in the detection image, that is, the abnormal regions are filled with a preset color; or, abnormal regions are marked with contour lines in the detection image, that is, the abnormal regions are outlined with contour lines.

[0179] In one possible implementation, the image detection device identifies the target object as an abnormal object when the proportion of the abnormal region is greater than a preset proportion; and identifies the target object as a normal object when the proportion of the abnormal region is not greater than the preset proportion. The preset proportion can be any proportion, for example, 50% or 60%.

[0180] The method provided in this application, when detecting transmission and reflection images, addresses the fact that the information about the target object contained in the transmission and reflection images is not entirely identical. By utilizing more information, a more accurate detection result can be obtained, thus improving the detection accuracy. Furthermore, compared to related technologies where observation is obtained by the human eye, the detection results obtained by the image detection device are more objective, further enhancing the detection accuracy.

[0181] Furthermore, in related technologies, radiological imaging acquisition equipment is used to acquire radiological images of the target object, and technicians observe the radiological images to obtain observation results. Compared with related technologies, the detection results obtained in this application are more objective, and the problem of inconsistent observation results obtained by different technicians is avoided.

[0182] The image detection method described above can be applied to a variety of scenarios.

[0183] For example, it is used in pathological sampling.

[0184] After surgery, a portion of the removed tissue is selected and prepared into sections. By observing these sections and combining them with other relevant information, the success of the surgery is determined. In preparing the sections, a tissue block containing the lesion area is first selected from multiple tissue blocks. Using the image detection method described in the above embodiment, it is determined whether the tissue block contains abnormal areas. If the tissue block contains abnormal areas, it is prepared into a section. During section preparation, the tissue block is fixed using methods such as formalin immersion, and then undergoes a series of operations including dehydration, paraffin embedding, section mounting, staining, and mounting to produce a pathological section that can be observed under a microscope.

[0185] The image detection method described above can accurately determine whether a tissue block contains abnormal regions and accurately select the tissue block to be used for slide preparation from multiple tissue blocks. This avoids the omission of tissue blocks due to inaccurate judgment of whether a tissue block contains abnormal regions, or avoids increasing the cost and reducing efficiency of slide preparation due to selecting too many tissue blocks.

[0186] For example, it can be used for tumor edge detection during surgery.

[0187] During surgery, accurate tumor removal can prevent disease recurrence and avoid secondary surgery. To accurately remove the tumor, it is necessary to accurately determine the edge location of the tumor. Using the image detection method in the above embodiment, abnormal areas can be detected. Then, based on the detected abnormal areas and other relevant information about the tumor, it can be determined whether the removed part includes the edge location.

[0188] Figure 10This is a schematic diagram of the structure of an image detection device provided in an embodiment of this application. See also... Figure 10 The device includes:

[0189] The image acquisition module 1001 is used to acquire the transmission image and the reflection image of the target object. The transmission image is acquired based on the first light signal, and the reflection image is acquired based on the second light signal. The first light signal is the light signal obtained after the light signal emitted by the first light source is transmitted through the target object, and the second light signal is the light signal obtained after the light signal emitted by the second light source is reflected through the target object.

[0190] Detection module 1002 is used to detect transmission and reflection images and determine abnormal areas in the target object;

[0191] The abnormal area display module 1003 is used to display abnormal areas in the detection image of the target object, where the detection image refers to a transmission image or a reflection image.

[0192] The apparatus provided in this application detects transmitted and reflected images, where the information about the target object contained in the transmitted and reflected images is not entirely the same. Based on more information, it can obtain more accurate detection results, thus improving detection accuracy. Furthermore, compared to observation results obtained by the human eye in related technologies, the detection results obtained by the image detection device are more objective, further improving detection accuracy.

[0193] Optionally, see Figure 11 The detection module 1002 includes:

[0194] The first detection unit 1012 is used to detect the transmission image and obtain the transmission features corresponding to the transmission image;

[0195] The second detection unit 1022 is used to detect the reflection image and obtain the reflection features corresponding to the reflection image;

[0196] The abnormal region acquisition unit 1032 is used to detect transmission and reflection features to obtain abnormal regions.

[0197] Optionally, see Figure 11 The device also includes:

[0198] The preprocessing module 1004 is used to preprocess the transmission image and the reflection image respectively to obtain the preprocessed transmission image and the preprocessed reflection image.

[0199] Optionally, the abnormal area display module 1003 is used for:

[0200] In the detected image, abnormal areas are marked with a preset color; or...

[0201] Anomaly regions are marked with contour lines in the detected image.

[0202] Optionally, the detection module 1002 is used to call an image detection model to detect the transmission and reflection images and determine abnormal areas in the target object.

[0203] Optionally, the image detection model is trained through the following steps:

[0204] Acquire a first sample image, a second sample image, and a third sample image. The first sample image is acquired based on a third optical signal, and the second sample image is acquired based on a fourth optical signal. The third optical signal is the optical signal obtained after the optical signal emitted by the first light source is transmitted through the sample object, and the fourth optical signal is the optical signal obtained after the optical signal emitted by the second light source is reflected by the sample object. The third sample image is an image of the sample object marked with sample abnormal areas.

[0205] The image detection model is trained based on the first sample image, the second sample image, and the third sample image.

[0206] Optionally, see Figure 11 The device also includes:

[0207] The abnormal object determination module 1005 is used to determine the target object as an abnormal object in response to the proportion of the abnormal area being greater than a preset proportion.

[0208] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0209] It should be noted that the image detection device provided in the above embodiments is only illustrated by the division of the above functional modules when detecting images. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the image detection device can be divided into different functional modules to complete all or part of the functions described above. In addition, the image detection device and the image detection method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0210] Figure 12A structural block diagram of a terminal 1200 provided in an exemplary embodiment of this application is shown. The terminal 1200 may be a portable mobile terminal, such as a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 1200 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0211] Typically, terminal 1200 includes a processor 1201 and a memory 1202.

[0212] Processor 1201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1201 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1201 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1201 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0213] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1202 are used to store at least one program code, which is executed by the processor 1201 to implement the image detection method provided in the method embodiments of this application.

[0214] In some embodiments, the terminal 1200 may also optionally include a peripheral device interface 1203 and at least one peripheral device. The processor 1201, memory 1202, and peripheral device interface 1203 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1203 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: radio frequency circuitry 1204, display screen 1205, camera assembly 1206, audio circuitry 1207, and power supply 1209.

[0215] Peripheral device interface 1203 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1201 and memory 1202. In some embodiments, processor 1201, memory 1202 and peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1201, memory 1202 and peripheral device interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0216] The radio frequency (RF) circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1204 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1204 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1204 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1204 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0217] Display screen 1205 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1205 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1201 for processing. In this case, display screen 1205 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1205, disposed on the front panel of terminal 1200; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 1200 or in a folded design; in still other embodiments, display screen 1205 may be a flexible display screen, disposed on a curved or folded surface of terminal 1200. Furthermore, display screen 1205 may also be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1205 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0218] The camera assembly 1206 is used to acquire images or videos. Optionally, the camera assembly 1206 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0219] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1201 for processing, or input to the radio frequency circuit 1204 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1200. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1207 may also include a headphone jack.

[0220] Power supply 1209 is used to power the various components in terminal 1200. Power supply 1209 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1209 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, and a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0221] In some embodiments, the terminal 1200 further includes one or more sensors 1210. The one or more sensors 1210 include, but are not limited to: an acceleration sensor 1211, a gyroscope sensor 1212, a pressure sensor 1213, an optical sensor 1215, and a proximity sensor 1216.

[0222] Accelerometer 1211 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established with terminal 1200. For example, accelerometer 1211 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1201 can control display screen 1205 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1211. Accelerometer 1211 can also be used for games or for acquiring user motion data.

[0223] The gyroscope sensor 1212 can detect the orientation and rotation angle of the terminal 1200. The gyroscope sensor 1212 can work in conjunction with the accelerometer sensor 1211 to collect the user's 3D movements on the terminal 1200. Based on the data collected by the gyroscope sensor 1212, the processor 1201 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0224] The pressure sensor 1213 can be disposed on the side bezel of the terminal 1200 and / or on the lower layer of the display screen 1205. When the pressure sensor 1213 is disposed on the side bezel of the terminal 1200, it can detect the user's grip signal on the terminal 1200, and the processor 1201 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1213. When the pressure sensor 1213 is disposed on the lower layer of the display screen 1205, the processor 1201 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1205. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0225] The optical sensor 1215 is used to collect ambient light intensity. In one embodiment, the processor 1201 can control the display brightness of the display screen 1205 based on the ambient light intensity collected by the optical sensor 1215. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1205 is increased; when the ambient light intensity is low, the display brightness of the display screen 1205 is decreased. In another embodiment, the processor 1201 can also dynamically adjust the shooting parameters of the camera assembly 1206 based on the ambient light intensity collected by the optical sensor 1215.

[0226] The proximity sensor 1216, also known as a distance sensor, is typically mounted on the front panel of the terminal 1200. The proximity sensor 1216 is used to detect the distance between the user and the front of the terminal 1200. In one embodiment, when the proximity sensor 1216 detects that the distance between the user and the front of the terminal 1200 is gradually decreasing, the processor 1201 controls the display screen 1205 to switch from a screen-on state to a screen-off state; when the proximity sensor 1216 detects that the distance between the user and the front of the terminal 1200 is gradually increasing, the processor 1201 controls the display screen 1205 to switch from a screen-off state to a screen-on state.

[0227] Those skilled in the art will understand that Figure 12 The structure shown does not constitute a limitation on terminal 1200 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0228] Figure 13This is a schematic diagram of a server structure provided in an embodiment of this application. The server 1300 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1301 and one or more memories 1302. The memory 1302 stores at least one line of program code, which is loaded and executed by the processor 1301 to implement the methods provided in the various method embodiments described above. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated upon here.

[0229] Server 1300 can be used to perform the steps executed by the server in the above image detection method.

[0230] This application also provides a computer device, which includes a processor and a memory. The memory stores at least one piece of program code, which is loaded and executed by the processor to implement the operations performed in the image detection method of the above embodiments.

[0231] This application also provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the operations performed in the image detection method of the above embodiments.

[0232] This application also provides a computer program product including computer program code stored in a computer-readable storage medium. A processor of a computer device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the computer device to perform the operations performed in the image detection method of the above embodiments.

[0233] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0234] The above are merely optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present application should be included within the protection scope of the present application.

Claims

1. An image capturing device, characterized by, The image acquisition device comprises a first light source, a second light source, an image acquisition assembly, a placement plate, a base, a first support, a second support and a plurality of third supports, the first light source comprises a plurality of first sub-light sources, the second light source comprises a plurality of second sub-light sources, the material of the placement plate is light-transmitting material, the placement plate comprises a light-transmitting area and a non-light-transmitting area, and the light-transmitting area is used for placing an object to be acquired image; The placement plate is arranged on the first support, the image acquisition assembly is arranged on the second support, the first support is connected with the second support, the first support is provided with a sliding rail, the second support is arranged in the sliding rail, and the second support moves along the sliding rail under the action of an external force to drive the image acquisition assembly to move relative to the placement plate; The first light source is located below the placement plate, and the second light source is located obliquely above the placement plate; The image acquisition assembly is located directly above the placement plate, and the image acquisition assembly is opposite to the first light source; The base is connected with the first support, and the plurality of first sub-light sources of the first light source are fixedly arranged on the base; The plurality of third supports are arranged on different sides of the first support, and the plurality of third supports are arranged at different heights, each third support comprises a first part and a second part, the first part and the second part are connected through a connecting shaft, the first part is fixedly connected with the first support, each second sub-light source in the second light source is arranged on the second part of one third support, at least one second sub-light source is arranged on the second part of each third support, and the second part rotates around the connecting shaft under the action of an external force to drive at least one second sub-light source on the second part to rotate around the connecting shaft, so that the angle between at least one second sub-light source on the second part and the placement plate changes; The image acquisition assembly is used for acquiring a transmission image of a target object based on a first light signal under the condition that the first light source is turned on and the second light source is turned off, the target object is placed on the light-transmitting area above the placement plate, and the target object has transparency, and the first light signal is a light signal obtained after a light signal emitted by the first light source is transmitted through the target object; The image acquisition assembly is also used for acquiring a reflection image of the target object based on a second light signal under the condition that the second light source is turned on and the first light source is turned off, and the second light signal is a light signal obtained after a light signal emitted by the second light source is reflected through the target object.

2. The image acquisition device of claim 1, wherein, The image acquisition device further comprises a light-shielding box, and the first light source, the second light source, the image acquisition assembly and the placement plate are located inside the light-shielding box.

3. An image acquisition method characterized in that, The method is applied to an image acquisition device; the image acquisition device comprises a first light source, a second light source, an image acquisition assembly, a placement plate, a base, a first support, a second support and a plurality of third supports, the first light source comprises a plurality of first sub-light sources, the second light source comprises a plurality of second sub-light sources, the material of the placement plate is light-transmitting material, the placement plate comprises a light-transmitting area and a non-light-transmitting area, the light-transmitting area is used for placing an object to be acquired image; the placement plate is arranged on the first support, the image acquisition assembly is arranged on the second support, the first support is connected with the second support, the first support is provided with a sliding rail, the second support is arranged in the sliding rail, the second support moves along the sliding rail under the action of external force to drive the image acquisition assembly to move relative to the placement plate; the first light source is located below the placement plate; the second light source is located obliquely above the placement plate; the image acquisition assembly is located directly above the placement plate, and the image acquisition assembly is opposite to the first light source; the base is connected with the first support, and a plurality of first sub-light sources of the first light source are fixedly arranged on the base; the plurality of third supports are arranged on different sides of the first support, and the plurality of third supports are arranged at different heights, each third support comprises a first part and a second part, the first part and the second part are connected through a connecting shaft, the first part is fixedly connected with the first support, each second sub-light source of the second light source is arranged on the second part of one third support, at least one second sub-light source is arranged on the second part of each third support, the second part rotates around the connecting shaft under the action of external force to drive at least one second sub-light source on the second part to rotate around the connecting shaft, so that the angle between at least one second sub-light source on the second part and the placement plate changes; the method comprises: The image acquisition assembly acquires a transmission image of a target object based on a first light signal under the condition that the first light source is turned on and the second light source is turned off, the target object is placed on the light-transmitting area above the placement plate, and the target object has transparency, the first light signal is a light signal obtained after a light signal emitted by the first light source is transmitted through the target object; The image acquisition assembly acquires a reflection image of the target object based on a second light signal under the condition that the first light source is turned off and the second light source is turned on, the second light signal is a light signal obtained after a light signal emitted by the second light source is reflected by the target object.

4. An image detection system, characterized by The image detection system comprises an image acquisition device and an image detection device; the image acquisition device comprises a first light source, a second light source, an image acquisition assembly, a placement plate, a base, a first support, a second support and a plurality of third supports, the first light source comprises a plurality of first sub-light sources, the second light source comprises a plurality of second sub-light sources, the placement plate is made of light-transmitting material, the placement plate comprises a light-transmitting area and a non-light-transmitting area, and the light-transmitting area is used for placing an object to be acquired; the placement plate is arranged on the first support, the image acquisition assembly is arranged on the second support, the first support is connected with the second support, the first support is provided with a sliding track, the second support is arranged in the sliding track, and the second support moves along the sliding track under the action of an external force to drive the image acquisition assembly to move relative to the placement plate; the first light source is located below the placement plate; the second light source is located obliquely above the placement plate; the image acquisition assembly is located directly above the placement plate, and the image acquisition assembly is opposite to the first light source; the base is connected with the first support, and the plurality of first sub-light sources of the first light source are fixedly arranged on the base; the plurality of third supports are arranged on different sides of the first support, and the plurality of third supports are arranged at different heights, each third support comprises a first part and a second part, the first part and the second part are connected through a connecting shaft, the first part is fixedly connected with the first support, each second sub-light source of the second light source is arranged on the second part of one third support, at least one second sub-light source is arranged on the second part of each third support, and the second part rotates around the connecting shaft under the action of an external force to drive at least one second sub-light source on the second part to rotate around the connecting shaft, so that the angle between at least one second sub-light source on the second part and the placement plate changes; The image acquisition assembly is used for acquiring a transmission image of a target object based on a first light signal under the condition that the first light source is turned on and the second light source is turned off, the target object is placed on the light-transmitting area above the placement plate, and the target object has transparency, and the first light signal is a light signal obtained after a light signal emitted by the first light source is transmitted through the target object; The image acquisition assembly is also used for acquiring a reflection image of the target object based on a second light signal under the condition that the second light source is turned on and the first light source is turned off, the second light signal is a light signal obtained after a light signal emitted by the second light source is reflected through the target object; The image acquisition assembly is also used for sending the transmission image and the reflection image to the image detection device; The image detection device is used for detecting the transmission image and the reflection image to determine an abnormal area in the target object. The image detection device is further configured to display the abnormal area in a detection image, the detection image being the transmission image or the reflection image.

5. An image detection method characterized by, The method comprises: acquiring a transmission image and a reflection image of a target object, the transmission image being acquired by an image acquisition component in an image acquisition device based on a first light signal, the reflection image being acquired by the image acquisition component based on a second light signal, the first light signal being a light signal emitted by a first light source in the image acquisition device after being transmitted through the target object, the second light signal being a light signal emitted by a second light source in the image acquisition device after being reflected by the target object; detecting the transmission image and the reflection image to determine an abnormal area in the target object; displaying the abnormal area in a detection image of the target object, the detection image being the transmission image or the reflection image; The image acquisition device comprises the first light source, the second light source, the image acquisition component, a placement plate, a base, a first support, a second support, and a plurality of third supports. The first light source comprises a plurality of first sub-sources, and the second light source comprises a plurality of second sub-sources. The placement plate is made of a light-transmitting material and comprises a light-transmitting area and a non-light-transmitting area. The light-transmitting area above the placement plate is used for placing an object whose image is to be acquired. The placement plate is arranged on the first support, the image acquisition component is arranged on the second support, the first support is connected to the second support, the first support is provided with a sliding rail, the second support is arranged in the sliding rail, and the second support moves along the sliding rail under the action of an external force to drive the image acquisition component to move relative to the placement plate. The first light source is located below the placement plate, the second light source is located obliquely above the placement plate, the image acquisition component is located directly above the placement plate, and the image acquisition component is opposite to the first light source. The base is connected to the first support, and the plurality of first sub-sources of the first light source are fixedly arranged on the base. The plurality of third supports are arranged on different sides of the first support and at different heights. Each third support comprises a first part and a second part, the first part and the second part are connected by a connecting shaft, the first part is fixedly connected to the first support, each second sub-source of the second light source is arranged on the second part of one third support, at least one second sub-source is arranged on the second part of each third support, and the second part rotates around the connecting shaft under the action of an external force to drive at least one second sub-source on the second part to rotate around the connecting shaft, so that the angle between at least one second sub-source on the second part and the placement plate changes.

6. The method of claim 5, wherein, The detecting the transmission image and the reflection image to determine the abnormal area in the target object comprises: detecting the transmission image to obtain a transmission feature corresponding to the transmission image; detecting the reflection image to obtain a reflection feature corresponding to the reflection image; detecting the transmission feature and the reflection feature to obtain the abnormal area.

7. The method of claim 5, wherein, The detecting the transmission image and the reflection image to determine the abnormal area in the target object comprises: calling an image detection model to detect the transmission image and the reflection image to determine the abnormal area in the target object.

8. An image detection apparatus characterized by comprising: The device comprises: an image acquisition module configured to acquire a transmission image and a reflection image of a target object, the transmission image being acquired by an image acquisition component in an image acquisition device based on a first light signal, the reflection image being acquired by the image acquisition component based on a second light signal, the first light signal being a light signal emitted by a first light source in the image acquisition device after being transmitted through the target object, and the second light signal being a light signal emitted by a second light source in the image acquisition device after being reflected by the target object; a detection module configured to detect the transmission image and the reflection image to determine an abnormal area in the target object; an abnormal area display module configured to display the abnormal area in a detection image of the target object, the detection image being the transmission image or the reflection image. The image acquisition device includes the first light source, the second light source, the image acquisition assembly, the object placing plate, the base, the first support, the second support and the plurality of third supports. The first light source includes a plurality of first sub-light sources. The second light source includes a plurality of second sub-light sources. The object placing plate is made of light-transmitting material. The object placing plate includes a light-transmitting area and a non-light-transmitting area. The light-transmitting area above the object placing plate is used for placing an object whose image is to be acquired. The object placing plate is arranged on the first support, and the image acquisition assembly is arranged on the second support. The first support is connected with the second support. The first support is provided with a sliding track, and the second support is arranged in the sliding track. The second support moves along the sliding track under the action of an external force to drive the image acquisition assembly to move relative to the object placing plate. The first light source is located below the object placing plate. The second light source is located obliquely above the object placing plate. The image acquisition assembly is located directly above the object placing plate and opposite the first light source. The base is connected with the first support, and the plurality of first sub-light sources of the first light source are fixedly arranged on the base. The plurality of third supports are arranged on different sides of the first support and at different heights. Each third support includes a first part and a second part. The first part and the second part are connected by a connecting shaft. The first part is fixedly connected with the first support. Each second sub-light source of the second light source is arranged on the second part of one third support. At least one second sub-light source is arranged on the second part of each third support. The second part rotates around the connecting shaft under the action of an external force to drive at least one second sub-light source on the second part to rotate around the connecting shaft, so that the angle between at least one second sub-light source on the second part and the object placing plate changes.

9. A computer device, comprising: The computer device includes a processor and a memory. The memory stores at least one program code. The at least one program code is loaded and executed by the processor to implement the operations performed in the image detection method according to any one of claims 5 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one program code. The at least one program code is loaded and executed by the processor to implement the operations performed in the image detection method according to any one of claims 5 to 7.

11. A computer program product, characterised in that, The computer program product includes computer program code. The processor of the computer device loads and executes the computer program code, so that the computer device implements the operations performed in the image detection method according to any one of claims 5 to 7.

Images