WO2020108436A1 - Tongue surface image segmentation device and method, and computer storage medium - Google Patents
Tongue surface image segmentation device and method, and computer storage medium Download PDFInfo
- Publication number
- WO2020108436A1 WO2020108436A1 PCT/CN2019/120644 CN2019120644W WO2020108436A1 WO 2020108436 A1 WO2020108436 A1 WO 2020108436A1 CN 2019120644 W CN2019120644 W CN 2019120644W WO 2020108436 A1 WO2020108436 A1 WO 2020108436A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- tongue
- ventral surface
- image
- ventral
- segmentation
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Definitions
- the invention relates to the technical field of tongue surface treatment of traditional Chinese medicine, and in particular to a tongue surface image segmentation device, method and computer storage medium.
- the sublingual tongue and vein diagnosis method has the same value as the auxiliary diagnosis for various diseases.
- the main syndrome is stasis syndrome, especially blood stasis syndrome; the main syndrome is malignant tumor, cardiopulmonary disease, liver disease, blood disease is particularly diagnostic value. Although it is a non-specific diagnosis, it can better reflect the overall situation of the patient on the cause of the disease, especially whether the qi and blood are balanced, whether the meridians are unobstructed, and whether there is internal resistance of phlegm and stasis. According to a large number of studies in traditional Chinese medicine, it mainly reflects changes in the state of the systemic circulation and microcirculation and blood. If doctors have certain experience, through detailed inspections to exclude the effects of age, individual differences, and climate interference, the results can make up for the shortcomings of traditional tongue diagnosis, and provide more and more important information for medical clinics in syndrome differentiation.
- the main object of the present invention is to provide a tongue surface image segmentation device, method and computer storage medium used in the face diagnosis of traditional Chinese medicine, aiming to solve the technical problem of the existing technique that the tongue and ventral surface segmentation from the tongue surface image is not high .
- the present invention provides a tongue image segmentation device, which includes a processor suitable for implementing various computer program instructions and a memory suitable for storing a plurality of computer program instructions.
- the computer program instructions are loaded by the processor and Perform the following steps: input different tongue sample images through the input unit to construct multiple positive and negative samples; use the opencv_createsamples program in the opencv open source library to process multiple positive and negative samples to generate a training data set; use the opencv_traincascade in the opencv open source library
- the program trains the training data set to generate the tongue and ventral surface detector; the tongue and ventral surface detector is used to detect the tongue and ventral surface including the lips from the tongue and facial image to be detected; the position information of the tongue and ventral surface is determined based on the tongue and facial image to be detected, and The position information of the tongue and ventral surface intercepts the tongue and ventral surface including the lips; threshold segmentation is performed on the intercepted tongue and ventral surface to obtain the shadow area and tooth area of the tongue and ventral
- the plurality of positive and negative samples include a plurality of positive samples and a plurality of negative samples, one positive sample includes image data of the ventral surface area of a tongue sample image, and one negative sample includes a non-tongue of the tongue sample image Image data of the ventral area.
- the threshold segmentation process of the intercepted tongue and ventral surface to obtain the shadow region and the tooth region of the tongue and ventral surface includes: performing threshold segmentation processing on the intercepted tongue and ventral surface; performing a morphological transformation on the result of the segmentation process to remove the tongue and ventral surface
- the speckled impurities in the image get the shadow area and tooth area on the ventral surface of the tongue.
- the step of creating a tongue and ventral segmentation template using the shadow area and the tooth area of the tongue and ventral surface includes: extracting the contour line of the tongue and ventral shadow area using a canny edge detection algorithm, extracting all n coordinate points of the contour line, and extracting All n coordinate points of the pair are paired to form n ⁇ (n-1)/2 edges; for each edge, check whether the remaining (n-2) points are on the same side of the edge; if all points are On one side of the edge, add the edge to the convex hull set until all edges have been traversed, and use the convex hull set as the outline of the shadow area of the ventral surface of the tongue; create a single size of the original tongue image Channel template image, and map the contour line of the shadow area of the tongue and ventral surface to the corresponding position of the single channel template image; set all pixel values of the non-white area inside the contour line to 1 and set all pixel values of the white area inside the contour line to 3 , Set all the
- the invention also provides a tongue image segmentation method.
- the method includes the following steps: inputting different tongue sample images through an input unit to construct multiple positive and negative samples; and using the opencv_createsamples program in the opencv open source library for multiple Positive and negative samples are processed to generate a training data set; the opencv_traincascade program in the opencv open source library is used to train the training data set to generate the tongue and ventral surface detector; the tongue and ventral surface detector is used to detect the tongue containing the lips from the tongue surface image to be detected Ventral surface; determine the position information of the tongue and ventral surface based on the tongue image to be detected, and intercept the tongue and ventral surface including the lips according to the position information of the tongue and ventral surface; perform threshold segmentation on the intercepted tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface; use The tongue and ventral surface shadow area and the tooth area create a tongue and ventral segmentation template; input the tongue and ventral segmentation template to be detected
- the plurality of positive and negative samples include a plurality of positive samples and a plurality of negative samples, one positive sample includes image data of the ventral surface area of a tongue sample image, and one negative sample includes a non-tongue of the tongue sample image Image data of the ventral area.
- the threshold segmentation process of the intercepted tongue and ventral surface to obtain the shadow region and the tooth region of the tongue and ventral surface includes: performing threshold segmentation processing on the intercepted tongue and ventral surface; performing a morphological transformation on the result of the segmentation process to remove the tongue and ventral surface
- the speckled impurities in the image get the shadow area and tooth area on the ventral surface of the tongue.
- the step of creating a tongue and ventral segmentation template using the shadow area and the tooth area of the tongue and ventral surface includes: extracting the contour line of the tongue and ventral shadow area using a canny edge detection algorithm, extracting all n coordinate points of the contour line, and extracting All n coordinate points of the pair are paired to form n ⁇ (n-1)/2 edges; for each edge, check whether the remaining (n-2) points are on the same side of the edge; if all points are On one side of the edge, add the edge to the convex hull set until all edges have been traversed, and use the convex hull set as the outline of the shadow area of the ventral surface of the tongue; create a single size of the original tongue image Channel template image, and map the contour line of the shadow area of the tongue and ventral surface to the corresponding position of the single channel template image; set all pixel values of the non-white area inside the contour line to 1 and set all pixel values of the white area inside the contour line to 3 , Set all the
- the present invention also provides a computer-readable storage medium storing a plurality of computer program instructions, the computer program instructions being loaded by a processor of a computer device and executing the tongue-face image segmentation method Various method steps.
- the tongue surface image segmentation device, method and computer storage medium of the present invention through a large number of different tongue surface sample image training to obtain a tongue and ventral surface detector to effectively detect the tongue and ventral surface including lips, improve
- the accuracy of the segmentation of the ventral surface of the tongue is used by the Chinese doctor to provide a clinical reference for the tongue diagnosis of the Chinese medicine, thereby assisting the Chinese doctor to judge the accuracy of the tongue diagnosis of the Chinese medicine.
- FIG. 1 is a schematic diagram of functional modules of a preferred embodiment of a tongue image segmentation device of the present invention
- FIG. 2 is a method flowchart of a preferred embodiment of the tongue image segmentation method of the present invention
- FIG. 3 is a schematic diagram of segmenting the tongue and ventral image from the original tongue and facial image.
- FIG. 1 is a schematic diagram of functional modules of a preferred embodiment of a tongue image segmentation device of the present invention.
- the tongue image segmentation device 1 may be a personal computer, a workstation computer, a traditional Chinese medicine facial imager, a traditional Chinese medicine four-diagnostic instrument, etc. that have a tongue surface image segmentation system 10 installed, which have data processing functions and image processing functions.
- the tongue image segmentation device 1 includes, but is not limited to, a tongue surface segmentation system 10, an input unit 11, a memory 12 suitable for storing multiple computer program instructions, and a variety of computer program instructions to execute Processor 13 and output unit 14.
- the input unit 11 may be an image input device such as a high-definition camera, which is used to capture a tongue image and input it into the tongue image segmentation device 1; the input unit 11 may also be an image reading device, which is used to The tongue image is read from the database in which the tongue image is stored and input to the tongue image segmentation device 1.
- the memory 12 may be a read-only memory ROM, a random access memory RAM, an electrically erasable memory EEPROM, a flash memory FLASH, a magnetic disk, or an optical disk.
- the processor 13 is a central processing unit (CPU), a microcontroller (MCU), a data processing chip, or an information processing unit with a data processing function.
- the output unit 14 may be an output device such as a display or a printer, which can output the segmented tongue and ventral image to the display or the printer for printing, so as to provide a clinical reference for the Chinese medicine doctor's tongue diagnosis, so as to assist the Chinese medicine doctor The accuracy of tongue diagnosis.
- an output device such as a display or a printer, which can output the segmented tongue and ventral image to the display or the printer for printing, so as to provide a clinical reference for the Chinese medicine doctor's tongue diagnosis, so as to assist the Chinese medicine doctor The accuracy of tongue diagnosis.
- the tongue image segmentation system 10 is composed of program modules composed of multiple computer program instructions, including but not limited to, the tongue and ventral surface training module 101, the tongue and ventral surface detection module 102, the tongue and ventral surface segmentation module 103, and The tongue and ventral output module 104.
- the module referred to in the present invention refers to a series of computer program instruction segments that can be executed by the processor 13 of the tongue image segmentation device 1 and can complete a fixed function, which are stored in the memory 12, and the specific description of each The specific function of a module.
- FIG. 2 it is a flowchart of a preferred embodiment of the tongue image segmentation method of the present invention.
- various method steps of the tongue image segmentation method are implemented by a computer software program, which is stored in the form of computer program instructions in a computer-readable storage medium (such as the memory 12).
- the readable storage medium may include: a read-only memory, a random access memory, a magnetic disk, or an optical disk.
- the computer program instructions can be loaded by a processor (for example, the processor 13) and execute the following steps S21 to S29.
- Step S21 input different tongue sample images to construct multiple positive and negative samples; in this embodiment, the input unit 11 takes a large number of different tongue sample images through a high-definition camera device or reads a large number of different samples from an external database
- the tongue surface sample image is input into the tongue surface image segmentation system 10.
- the tongue and ventral surface training module 101 constructs multiple positive and negative samples according to different input tongue image samples, the multiple positive and negative samples include multiple positive samples and multiple negative samples, for example, including 200 positive samples and 300 negative samples
- a positive sample includes image data of the lingual ventral surface area in a lingual sample image
- a negative sample includes image data of a non-lingual ventral surface area in a lingual sample image.
- the tongue surface sample image input by the input unit 11 is trained to the tongue and ventral surface training module 101 to obtain a tongue and ventral surface detector.
- the invention uses a large number of different tongue surface sample images to train a tongue and ventral surface detector for recognizing the tongue surface image, as long as the doctor inputs the tongue surface image to be detected to the tongue and ventral surface detector to detect the tongue and ventral surface image including the lips .
- Step S22 the opencv_createsamples program in the opencv open source library is used to process multiple positive and negative samples to generate a training data set; in this embodiment, the tongue and ventral training module 101 uses the opencv_createsamples program in the opencv open source library to process multiple positive and negative samples Process to generate a training data set.
- the opencv_createsamples program is a general program for sample creation in the opencv open source library. Those skilled in the art can process multiple positive and negative samples through the existing opencv_createsamples program to generate a training data set.
- Step S23 the opencv_traincascade program in the opencv open source library is used to train the training data set to generate the tongue and ventral surface detector; in this embodiment, the tongue and ventral surface training module 101 uses the opencv_traincascade program in the opencv open source library to train the training data set to generate the tongue Ventral detector.
- the opencv_traincascade program is a general program for classifier training in the opencv open source library. Those skilled in the art can train the training data set to generate a tongue and ventral surface detector through the existing opencv_traincascade program.
- the tongue and ventral surface detector is used to detect the tongue and ventral surface including the lips from the tongue and facial image to be detected; specifically, the tongue and ventral surface detection module 102 first receives the needs from the input unit 11 when performing tongue and ventral surface detection and recognition
- the detected tongue image for example, shown in (a) of FIG. 3 is the tongue surface image to be detected, and then the trained tongue and ventral surface detector is used to detect the tongue and ventral surface including the lips from the tongue surface image to be detected, for example 3, (b) shows the ventral surface of the tongue including the lips.
- Step S25 Determine the position information of the tongue and ventral surface based on the tongue and facial image to be detected, and intercept the tongue and ventral surface including the lips according to the position information of the tongue and ventral surface; specifically, the tongue and ventral surface detection module 102 is based on the tongue and ventral surface to be detected Determine the position of the tongue and ventral surface rect(x, y, l, w) from the position in the tongue image, and then intercept the tongue and ventral surface containing the lips according to the position information of the tongue and ventral surface, where x and y represent the box in Figure 3(a) The coordinates of the vertex in the upper left corner of, l, w represent the length and width of the box.
- step S26 threshold segmentation is performed on the intercepted tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface; in this embodiment, the tongue and ventral surface segmentation module 103 performs threshold segmentation processing on the intercepted tongue and ventral surface (including lips), and Morphological transformation is performed on the results of the segmentation process to remove some small speckle impurities in the image of the tongue and ventral surface, respectively to obtain the shadow area and the tooth area of the tongue and ventral surface (dark area and tooth area located in the lips), as shown in Figure 3(c)
- the white area in the represents the shadow area on the ventral surface of the tongue
- the white area in 3(d) represents the tooth area on the ventral surface of the tongue.
- Step S27 the tongue and ventral segmentation template is created by using the shadow region and the tooth region of the tongue and ventral surface; in this embodiment, the tongue and ventral segmentation module 103 performs convex hull calculation according to the tongue and ventral shadow region to generate the contour of the tongue and ventral shadow region, and the generated result is as follows: The white outline in Figure 3(e).
- the tongue and ventral segmentation module 103 uses the canny edge detection algorithm to extract the contour line of the shadow region of the tongue and ventral surface, and then extracts all the coordinate points of the contour line (assuming that there are n points in total), and pairs all the extracted n coordinate points in pairs Make up n ⁇ (n-1)/2 edges; for each edge, check whether the remaining (n-2) points are on the same side of the edge; if all points are on the side of the edge, Then add this edge to the convex hull set as the outline of the shadow area of the tongue and ventral surface until all the constituent edges have been traversed; create a single-channel template image of the original tongue image size, and add the outline of the shadow area of the tongue and ventral surface Map to the corresponding position of the single-channel template image, set all pixel values of the non-white area inside the outline to 1, set all pixel values of the white area inside the outline to 3, and set all pixel values of the area outside the outline to all Set to 0, the pixel value of the
- 0 represents the determined background pixel value (non-tongue surface)
- 1 represents the determined foreground pixel value (tongue surface)
- 2 represents the uncertain background pixel value (may be non-tongue surface)
- 3 represents the uncertain foreground pixel Value (probably tongue and ventral surface).
- Step S28 Input the tongue image and tongue and ventral segmentation template to be detected into the openCV open source library's grabCut function to segment the tongue and ventral image; in this embodiment, the tongue and ventral segmentation module 103 converts the tongue and ventral image and tongue to be detected
- the ventral segmentation template is input into the grabCut function of the opencv open source library to segment the tongue and ventral image.
- the grabCut function of the opencv open source library is an existing tongue and ventral segmentation function, and the grabCut function can perform image segmentation.
- a person skilled in the art inputs a tongue surface image and a tongue and ventral segmentation template into the grabCut function, and uses the grabCut function You can segment the tongue and ventral image.
- the tongue image (a) and the tongue and ventral segmentation template (e) to be detected are input into the grabCut function to segment the tongue and ventral image (f).
- Step S29 the tongue and ventral surface image is output to the display or the printer for printing via the output unit; specifically, the tongue and ventral surface output module 104 outputs the tongue and ventral surface image to the display or the printer for printing via the output unit 14 for the doctor Provide clinical reference for tongue diagnosis of traditional Chinese medicine, so as to assist Chinese doctors to judge the accuracy of results of tongue diagnosis of traditional Chinese medicine.
- the invention also provides a computer-readable storage medium storing a plurality of computer program instructions, which are loaded by a processor of a computer device and execute the steps of the tongue image segmentation method of the invention .
- a computer-readable storage medium storing a plurality of computer program instructions, which are loaded by a processor of a computer device and execute the steps of the tongue image segmentation method of the invention .
- the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, Disk or CD, etc.
- the tongue image segmentation device, method and computer storage medium of the present invention obtain tongue and ventral surface detector through a large number of different tongue sample image training to effectively detect the tongue and ventral surface including lips, and improve the accuracy of tongue and ventral surface segmentation, It is for the Chinese doctor to provide clinical reference to the tongue diagnosis of Chinese medicine, so as to assist the doctor to judge the accuracy of the result of the tongue diagnosis of Chinese medicine.
- the tongue image segmentation device, method and computer storage medium of the present invention through a large number of different tongue surface sample image training to obtain a tongue and ventral surface detector to effectively detect the tongue and ventral surface including lips
- the accuracy of the segmentation of the ventral surface of the tongue is used by the Chinese doctor to provide a clinical reference for the tongue diagnosis of the Chinese medicine, thereby assisting the Chinese doctor to judge the accuracy of the tongue diagnosis of the Chinese medicine.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a tongue surface image segmentation device and method, and a computer storage medium. The method comprises the steps of: inputting, by an inputting unit, different tongue surface sample images to create multiple positive and negative samples; processing the multiple positive and negative samples to generate one training data set; training the data set to generate a ventral surface of tongue detector; detecting a ventral surface of tongue comprising a lip from a ventral surface of tongue image by using the ventral surface of tongue detector; determining position information of the ventral surface of tongue on the basis of a ventral surface of tongue image to be detected, and intercepting the ventral surface of tongue comprising the lip according to the position information of the ventral surface of tongue; performing threshold segmentation on the intercepted ventral surface of tongue to obtain a shadow region of the ventral surface of tongue and a tooth area; creating a ventral surface of tongue segmentation template by using the shadow region of the ventral surface of tongue and the tooth area; segmenting the ventral surface of tongue image from the ventral surface of tongue image according to the ventral surface of tongue segmentation template; and outputting, by an outputting unit, the ventral surface of tongue image to a display for displaying or a printer for printing. The ventral surface of tongue image method in the present invention improves the accuracy of ventral surface of tongue segmentation.
Description
本发明涉及中医舌面处理的技术领域，尤其涉及一种舌面图像分割装置、方法及计算机存储介质。The invention relates to the technical field of tongue surface treatment of traditional Chinese medicine, and in particular to a tongue surface image segmentation device, method and computer storage medium.
舌下络脉诊法与舌诊一样对各种病证有一定的辅助诊断价值。在证主为瘀证，尤其是血瘀证；在病主为恶性肿瘤、心肺疾病、肝病、血液病尤具诊断价值。它虽非特异性诊断，但能较好地反映患者对致病动因的整体态势，特别是对气血是否盈亏调和，经络是否通畅，有无痰瘀内阻具较大意义。根据中医学中的大量研究，它主要反映的是体循环与微循环的状态及血液有关方面的变化。如果医者具有一定经验，通过详细望诊，排除年龄、个体差异、气候干扰等影响，其结果可以弥补传统舌诊的不足，为医学临床在辨证中提供更多更重要的信息。The sublingual tongue and vein diagnosis method has the same value as the auxiliary diagnosis for various diseases. The main syndrome is stasis syndrome, especially blood stasis syndrome; the main syndrome is malignant tumor, cardiopulmonary disease, liver disease, blood disease is particularly diagnostic value. Although it is a non-specific diagnosis, it can better reflect the overall situation of the patient on the cause of the disease, especially whether the qi and blood are balanced, whether the meridians are unobstructed, and whether there is internal resistance of phlegm and stasis. According to a large number of studies in traditional Chinese medicine, it mainly reflects changes in the state of the systemic circulation and microcirculation and blood. If doctors have certain experience, through detailed inspections to exclude the effects of age, individual differences, and climate interference, the results can make up for the shortcomings of traditional tongue diagnosis, and provide more and more important information for medical clinics in syndrome differentiation.
然而，由传统中医舌诊方法所得到的诊断结果往往受医生的经验积累以及病人当时所处的环境等因素所影响，主观依赖性较强，缺乏客观化、定量化的依据。舌下络脉诊法的深入发展，仍有赖于基础研究的认真探索和临床观察的客观化，因此要特别重视运用高科技手段创造新的仪器和方法，形成统一、规范的客观指标和观察方法，找出规律，说明机制，实用于临床。However, the diagnosis results obtained by the traditional tongue diagnosis method of traditional Chinese medicine are often affected by factors such as the accumulation of doctors' experience and the environment in which the patients were at the time. They are subjectively dependent and lack objective and quantitative basis. The in-depth development of the sublingual collateral diagnosis method still depends on the serious exploration of basic research and the objectivity of clinical observation. Therefore, special attention should be paid to the use of high-tech means to create new instruments and methods to form unified and standardized objective indicators and observation methods , Find out the rules, explain the mechanism, and apply it to the clinic.
面向计算机化中医舌下络脉诊法研究工作的开展将进一步推动现代信息科学与祖国传统医学的交融发展，对于中医辨证规范化及中医临床、教学、科研手段的现代化，解决制约发挥中医特色优势的重大基础问题，实现中医现代化，具有重要的理论价值和实际意义，是中医舌诊现代化的重要环节。目前，图像处理和模式识别等计算机方法为中医诊断技术提供参考依据，然而，目前现有技术没有出现利用大量不同的舌面图像进行训练得到一个在舌腹面检测器，在舌腹面分割方面准确度不高，从而导致从舌面图像中分割出来的舌腹面图像不够准确，从而影响医生对中医舌诊判断结果的准确性。The development of the research work of computerized sublingual collateral diagnosis of Chinese medicine will further promote the integration of modern information science and traditional medicine in the motherland. It will solve the restrictions on the standardization of traditional Chinese medicine syndrome differentiation and the modernization of traditional Chinese medicine clinical, teaching and scientific research methods. Major basic problems and the realization of modernization of traditional Chinese medicine have important theoretical value and practical significance, and are an important part of the modernization of tongue diagnosis of traditional Chinese medicine. At present, computer methods such as image processing and pattern recognition provide a reference basis for Chinese medicine diagnosis technology. However, at present, there is no existing technology that uses a large number of different tongue surface images for training to obtain a tongue and ventral surface detector, and accuracy in tongue and ventral surface segmentation It is not high, which results in the tongue and ventral image segmented from the tongue and facial image is not accurate enough, which affects the accuracy of the doctor’s judgment on the tongue diagnosis of traditional Chinese medicine.
本发明的主要目的在于提供一种应用于中医面诊中的舌面图像分割装置、方法及计算机存储介质，旨在解决现有技术存在从舌面图像分割的舌腹面准确度不高的技术问题。The main object of the present invention is to provide a tongue surface image segmentation device, method and computer storage medium used in the face diagnosis of traditional Chinese medicine, aiming to solve the technical problem of the existing technique that the tongue and ventral surface segmentation from the tongue surface image is not high .
为实现上述目的，本发明提供一种舌面图像分割装置，包括适于实现各种计算机程序指令的处理器以及适于存储多条计算机程序指令的存储器，所述计算机程序指令由处理器加载并执行如下步骤：通过输入单元输入不同的舌面样本图像构建多个正负样本；利用opencv开源库中的opencv_createsamples程序对多个正负样本进行处理生成一个训练数据集；利用opencv开源库中的opencv_traincascade程序对训练数据集进行训练生成舌腹面检测器；利用舌腹面检测器从待检测的舌面图像中检测出包含嘴唇的舌腹面；基于待检测的舌面图像确定舌腹面的位置信息，并根据舌腹面的位置信息截取包含嘴唇的舌腹面；对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域；利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板；将待检测的舌面图像和舌腹面分割模板输入到opencv开源库中的grabCut函数中分割出舌腹面图像；通过输出单元将舌腹面图像输出至显示器上显示或打印机上打印。To achieve the above object, the present invention provides a tongue image segmentation device, which includes a processor suitable for implementing various computer program instructions and a memory suitable for storing a plurality of computer program instructions. The computer program instructions are loaded by the processor and Perform the following steps: input different tongue sample images through the input unit to construct multiple positive and negative samples; use the opencv_createsamples program in the opencv open source library to process multiple positive and negative samples to generate a training data set; use the opencv_traincascade in the opencv open source library The program trains the training data set to generate the tongue and ventral surface detector; the tongue and ventral surface detector is used to detect the tongue and ventral surface including the lips from the tongue and facial image to be detected; the position information of the tongue and ventral surface is determined based on the tongue and facial image to be detected, and The position information of the tongue and ventral surface intercepts the tongue and ventral surface including the lips; threshold segmentation is performed on the intercepted tongue and ventral surface to obtain the shadow area and tooth area of the tongue and ventral surface; the tongue and ventral surface segmentation template is created by using the shadow area and the tooth area of the tongue and ventral surface; The tongue image and the tongue and ventral segmentation template are input to the grabCut function in the opencv open source library to segment the tongue and ventral image; the tongue and ventral image is output to the display or printed on the printer through the output unit.
优选的，所述多个正负样本包括多个正样本和多个负样本，一个正样本包括一个舌面样本图像中舌腹面区域的图像数据，一个负样本包括一个舌面样本图像中非舌腹面区域的图像数据。Preferably, the plurality of positive and negative samples include a plurality of positive samples and a plurality of negative samples, one positive sample includes image data of the ventral surface area of a tongue sample image, and one negative sample includes a non-tongue of the tongue sample image Image data of the ventral area.
优选的，所述对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域的步骤包括：对截取的舌腹面进行阈值分割处理；对分割处理的结果进行形态学变换以去除舌腹面图像中的斑点杂质，得到舌腹面的暗影区域和牙齿区域。Preferably, the threshold segmentation process of the intercepted tongue and ventral surface to obtain the shadow region and the tooth region of the tongue and ventral surface includes: performing threshold segmentation processing on the intercepted tongue and ventral surface; performing a morphological transformation on the result of the segmentation process to remove the tongue and ventral surface The speckled impurities in the image get the shadow area and tooth area on the ventral surface of the tongue.
优选的，所述利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板的步骤包括：利用canny边缘检测算法提取舌腹面暗影区域的轮廓线，提取轮廓线的所有n个坐标点，并将提取的所有n个坐标点两两配对组成n×(n-1)/2条边；对于每条边，检查剩余的(n-2)个点是否在该条边的同一侧；如果所有点都在该条边的一侧，则将该条边加入凸包集合中直到所有边都被遍历过为止，并将该凸包集合作为舌腹面暗影区域的轮廓线；创建原始舌面图像大小的单通道模板图像，并将舌腹面暗影区域的轮廓线映射到单通道模板图像的相应位置；将轮廓线内部非白色区域所有像素值全部置为1，将轮廓线内部白色区域所有像素值置为3，将轮廓线外部区域所有像素值全部置0，依照舌腹面牙齿区域将单通道模板图像相应位置的像素值置为0，得到舌腹面分割模板。Preferably, the step of creating a tongue and ventral segmentation template using the shadow area and the tooth area of the tongue and ventral surface includes: extracting the contour line of the tongue and ventral shadow area using a canny edge detection algorithm, extracting all n coordinate points of the contour line, and extracting All n coordinate points of the pair are paired to form n×(n-1)/2 edges; for each edge, check whether the remaining (n-2) points are on the same side of the edge; if all points are On one side of the edge, add the edge to the convex hull set until all edges have been traversed, and use the convex hull set as the outline of the shadow area of the ventral surface of the tongue; create a single size of the original tongue image Channel template image, and map the contour line of the shadow area of the tongue and ventral surface to the corresponding position of the single channel template image; set all pixel values of the non-white area inside the contour line to 1 and set all pixel values of the white area inside the contour line to 3 , Set all the pixel values in the area outside the contour line to 0, and set the pixel value of the corresponding position of the single-channel template image to 0 according to the tooth area of the tongue and ventral surface to obtain the tongue and ventral segmentation template.
另一方面，本发明还提供一种舌面图像分割方法，该方法包括如下步骤：通过输入单元输入不同的舌面样本图像构建多个正负样本；利用opencv开源库中的opencv_createsamples程序对多个正负样本进行处理生成一个训练数据集；利用opencv开源库中的opencv_traincascade程序对训练数据集进行训练生成舌腹面检测器；利用舌腹面检测器从待检测的舌面图像中检测出包含嘴唇的舌腹面；基于待检测的舌面图像确定舌腹面的位置信息，并根据舌腹面的位置信息截取包含嘴唇的舌腹面；对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域；利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板；将待检测的舌面图像和舌腹面分割模板输入到opencv开源库中的grabCut函数中分割出舌腹面图像；通过输出单元将舌腹面图像输出至显示器上显示或打印机上打印。On the other hand, the invention also provides a tongue image segmentation method. The method includes the following steps: inputting different tongue sample images through an input unit to construct multiple positive and negative samples; and using the opencv_createsamples program in the opencv open source library for multiple Positive and negative samples are processed to generate a training data set; the opencv_traincascade program in the opencv open source library is used to train the training data set to generate the tongue and ventral surface detector; the tongue and ventral surface detector is used to detect the tongue containing the lips from the tongue surface image to be detected Ventral surface; determine the position information of the tongue and ventral surface based on the tongue image to be detected, and intercept the tongue and ventral surface including the lips according to the position information of the tongue and ventral surface; perform threshold segmentation on the intercepted tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface; use The tongue and ventral surface shadow area and the tooth area create a tongue and ventral segmentation template; input the tongue and ventral segmentation template to be detected into the grabCut function in the opencv open source library to segment the tongue and ventral surface image; output the tongue and ventral surface image through the output unit Go to the display or print on the printer.
优选的，所述多个正负样本包括多个正样本和多个负样本，一个正样本包括一个舌面样本图像中舌腹面区域的图像数据，一个负样本包括一个舌面样本图像中非舌腹面区域的图像数据。Preferably, the plurality of positive and negative samples include a plurality of positive samples and a plurality of negative samples, one positive sample includes image data of the ventral surface area of a tongue sample image, and one negative sample includes a non-tongue of the tongue sample image Image data of the ventral area.
优选的，所述对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域的步骤包括：对截取的舌腹面进行阈值分割处理；对分割处理的结果进行形态学变换以去除舌腹面图像中的斑点杂质，得到舌腹面的暗影区域和牙齿区域。Preferably, the threshold segmentation process of the intercepted tongue and ventral surface to obtain the shadow region and the tooth region of the tongue and ventral surface includes: performing threshold segmentation processing on the intercepted tongue and ventral surface; performing a morphological transformation on the result of the segmentation process to remove the tongue and ventral surface The speckled impurities in the image get the shadow area and tooth area on the ventral surface of the tongue.
优选的，所述利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板的步骤包括：利用canny边缘检测算法提取舌腹面暗影区域的轮廓线，提取轮廓线的所有n个坐标点，并将提取的所有n个坐标点两两配对组成n×(n-1)/2条边；对于每条边，检查剩余的(n-2)个点是否在该条边的同一侧；如果所有点都在该条边的一侧，则将该条边加入凸包集合中直到所有边都被遍历过为止，并将该凸包集合作为舌腹面暗影区域的轮廓线；创建原始舌面图像大小的单通道模板图像，并将舌腹面暗影区域的轮廓线映射到单通道模板图像的相应位置；将轮廓线内部非白色区域所有像素值全部置为1，将轮廓线内部白色区域所有像素值置为3，将轮廓线外部区域所有像素值全部置0，依照舌腹面牙齿区域将单通道模板图像相应位置的像素值置为0，得到舌腹面分割模板。Preferably, the step of creating a tongue and ventral segmentation template using the shadow area and the tooth area of the tongue and ventral surface includes: extracting the contour line of the tongue and ventral shadow area using a canny edge detection algorithm, extracting all n coordinate points of the contour line, and extracting All n coordinate points of the pair are paired to form n×(n-1)/2 edges; for each edge, check whether the remaining (n-2) points are on the same side of the edge; if all points are On one side of the edge, add the edge to the convex hull set until all edges have been traversed, and use the convex hull set as the outline of the shadow area of the ventral surface of the tongue; create a single size of the original tongue image Channel template image, and map the contour line of the shadow area of the tongue and ventral surface to the corresponding position of the single channel template image; set all pixel values of the non-white area inside the contour line to 1 and set all pixel values of the white area inside the contour line to 3 , Set all the pixel values in the area outside the contour line to 0, and set the pixel value of the corresponding position of the single-channel template image to 0 according to the tooth area of the tongue and ventral surface to obtain the tongue and ventral segmentation template.
另一方面，本发明还一种计算机可读存储介质，该计算机可读存储介质存储多条计算机程序指令，所述计算机程序指令由计算机装置的处理器加载并执行所述舌面图像分割方法的各项方法步骤。On the other hand, the present invention also provides a computer-readable storage medium storing a plurality of computer program instructions, the computer program instructions being loaded by a processor of a computer device and executing the tongue-face image segmentation method Various method steps.
相较于现有技术，本发明所述舌面图像分割装置、方法及计算机存储介质，通过大量的不同舌面样本图像训练得到舌腹面检测器来有效地检测出包含嘴唇的舌腹面，提高了舌腹面分割的准确性，以供中医生对中医舌诊提供临床参考，从而辅助中医生对中医舌诊判断结果的准确性。Compared with the prior art, the tongue surface image segmentation device, method and computer storage medium of the present invention, through a large number of different tongue surface sample image training to obtain a tongue and ventral surface detector to effectively detect the tongue and ventral surface including lips, improve The accuracy of the segmentation of the ventral surface of the tongue is used by the Chinese doctor to provide a clinical reference for the tongue diagnosis of the Chinese medicine, thereby assisting the Chinese doctor to judge the accuracy of the tongue diagnosis of the Chinese medicine.
图1是本发明舌面图像分割装置的优选实施例的功能模块示意图；1 is a schematic diagram of functional modules of a preferred embodiment of a tongue image segmentation device of the present invention;
图2是本发明舌面图像分割方法优选实施例的方法流程图；FIG. 2 is a method flowchart of a preferred embodiment of the tongue image segmentation method of the present invention;
图3为从原始的舌面图像中分割出舌腹面图像的示意图。FIG. 3 is a schematic diagram of segmenting the tongue and ventral image from the original tongue and facial image.
本发明目的实现、功能特点及优点将结合以下实施例，一并参照附图做进一步说明。The objectives, functional characteristics and advantages of the present invention will be further described in conjunction with the following embodiments with reference to the accompanying drawings.
为更进一步阐述本发明为达成预定发明目的所采取的技术手段及功效，以下结合附图及较佳实施例，对本发明的具体实施方式、结构、特征及其功效，详细说明如下。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。In order to further illustrate the technical means and effects adopted by the present invention to achieve the intended purpose of the invention, the specific implementation, structure, features and effects of the present invention are described in detail below in conjunction with the drawings and preferred embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not intended to limit the present invention.
参照图1所示，图1是本发明舌面图像分割装置的优选实施例的功能模块示意图。在本实施例中，所述舌面图像分割装置1可以为安装有舌面图像分割***10的个人计算机、工作站计算机、中医面像仪、中医四诊仪等具有数据处理功能和图像处理功能的计算机装置。在本实施例中，所述舌面图像分割装置1包括，但不仅限于，舌面图像分割***10、输入单元11、适于存储多条计算机程序指令的存储器12、执行各种计算机程序指令的处理器13以及输出单元14。所述输入单元11可以为一种高清摄像头等影像输入设备，用于拍摄舌面图像并输入至舌面图像分割装置1中；所述输入单元11也可以为一种图像读取设备，用于从存储有舌面图像的数据库中读取舌面图像并输入至舌面图像分割装置1中。所述存储器12可以为一种只读存储器ROM，随机存储器RAM、电可擦写存储器EEPROM、快闪存储器FLASH、磁盘或光盘等。所述处理器13为一种中央处理器（CPU）、微控制器（MCU）、数据处理芯片、或者具有数据处理功能的信息处理单元。所述输出单元14可以为显示器或者打印机等输出设备，能够将分割出的舌腹面图像输出至显示器上显示或打印机上打印，以供中医生对中医舌诊提供临床参考，从而辅助中医生对中医舌诊判断结果的准确性。Referring to FIG. 1, FIG. 1 is a schematic diagram of functional modules of a preferred embodiment of a tongue image segmentation device of the present invention. In this embodiment, the tongue image segmentation device 1 may be a personal computer, a workstation computer, a traditional Chinese medicine facial imager, a traditional Chinese medicine four-diagnostic instrument, etc. that have a tongue surface image segmentation system 10 installed, which have data processing functions and image processing functions. Computer device. In this embodiment, the tongue image segmentation device 1 includes, but is not limited to, a tongue surface segmentation system 10, an input unit 11, a memory 12 suitable for storing multiple computer program instructions, and a variety of computer program instructions to execute Processor 13 and output unit 14. The input unit 11 may be an image input device such as a high-definition camera, which is used to capture a tongue image and input it into the tongue image segmentation device 1; the input unit 11 may also be an image reading device, which is used to The tongue image is read from the database in which the tongue image is stored and input to the tongue image segmentation device 1. The memory 12 may be a read-only memory ROM, a random access memory RAM, an electrically erasable memory EEPROM, a flash memory FLASH, a magnetic disk, or an optical disk. The processor 13 is a central processing unit (CPU), a microcontroller (MCU), a data processing chip, or an information processing unit with a data processing function. The output unit 14 may be an output device such as a display or a printer, which can output the segmented tongue and ventral image to the display or the printer for printing, so as to provide a clinical reference for the Chinese medicine doctor's tongue diagnosis, so as to assist the Chinese medicine doctor The accuracy of tongue diagnosis.
在本实施例中，所述舌面图像分割***10由多条计算机程序指令组成的程序模块组成，包括但不局限于，舌腹面训练模块101、舌腹面检测模块102、舌腹面分割模块103以及舌腹面输出模块104。本发明所称的模块是指一种能够被舌面图像分割装置1的处理器13执行并且能够完成固定功能的一系列计算机程序指令段，其存储在存储器12中，以下结合图2具体说明每一个模块的具体功能。In this embodiment, the tongue image segmentation system 10 is composed of program modules composed of multiple computer program instructions, including but not limited to, the tongue and ventral surface training module 101, the tongue and ventral surface detection module 102, the tongue and ventral surface segmentation module 103, and The tongue and ventral output module 104. The module referred to in the present invention refers to a series of computer program instruction segments that can be executed by the processor 13 of the tongue image segmentation device 1 and can complete a fixed function, which are stored in the memory 12, and the specific description of each The specific function of a module.
参考图2所示，是本发明舌面图像分割方法优选实施例的流程图。在本实施例中，所述舌面图像分割方法的各种方法步骤通过计算机软件程序来实现，该计算机软件程序以计算机程序指令的形式存储于计算机可读存储介质（例如存储器12）中，计算机可读存储介质可以包括：只读存储器、随机存储器、磁盘或光盘等，所述计算机程序指令能够被处理器（例如处理器13）加载并执行如下步骤S21至步骤S29。Referring to FIG. 2, it is a flowchart of a preferred embodiment of the tongue image segmentation method of the present invention. In this embodiment, various method steps of the tongue image segmentation method are implemented by a computer software program, which is stored in the form of computer program instructions in a computer-readable storage medium (such as the memory 12). The readable storage medium may include: a read-only memory, a random access memory, a magnetic disk, or an optical disk. The computer program instructions can be loaded by a processor (for example, the processor 13) and execute the following steps S21 to S29.
步骤S21，输入不同的舌面样本图像构建多个正负样本；在本实施例中，所述输入单元11通过高清摄像设备摄取大量不同的舌面样本图像或者从外部数据库中读取大量不同的舌面样本图像，并输入到舌面图像分割***10中。所述舌腹面训练模块101根据输入不同的舌面样本图像构建多个正负样本，所述多个正负样本包括多个正样本和多个负样本，例如包括正样本200个，负样本300个，一个正样本包括一个舌面样本图像中舌腹面区域的图像数据，一个负样本包括一个舌面样本图像中非舌腹面区域的图像数据。所述输入单元11输入的舌面样本图像至舌腹面训练模块101进行训练以得到舌腹面检测器。本发明采用大量不同的舌面样本图像来训练一个用于识别舌面图像的舌腹面检测器，只要当中医生输入待检测的舌面图像至舌腹面检测器即可检测出包嘴唇的舌腹面图像。Step S21, input different tongue sample images to construct multiple positive and negative samples; in this embodiment, the input unit 11 takes a large number of different tongue sample images through a high-definition camera device or reads a large number of different samples from an external database The tongue surface sample image is input into the tongue surface image segmentation system 10. The tongue and ventral surface training module 101 constructs multiple positive and negative samples according to different input tongue image samples, the multiple positive and negative samples include multiple positive samples and multiple negative samples, for example, including 200 positive samples and 300 negative samples One, a positive sample includes image data of the lingual ventral surface area in a lingual sample image, and a negative sample includes image data of a non-lingual ventral surface area in a lingual sample image. The tongue surface sample image input by the input unit 11 is trained to the tongue and ventral surface training module 101 to obtain a tongue and ventral surface detector. The invention uses a large number of different tongue surface sample images to train a tongue and ventral surface detector for recognizing the tongue surface image, as long as the doctor inputs the tongue surface image to be detected to the tongue and ventral surface detector to detect the tongue and ventral surface image including the lips .
步骤S22，利用opencv开源库中的opencv_createsamples程序对多个正负样本进行处理生成一个训练数据集；在本实施例中，舌腹面训练模块101利用opencv开源库中的opencv_createsamples程序对多个正负样本进行处理生成一个训练数据集。所述opencv_createsamples程序是opencv开源库中一种样本创建的通用程序，本领域技术人员通过现有的opencv_createsamples程序即可对多个正负样本进行处理生成一个训练数据集。Step S22, the opencv_createsamples program in the opencv open source library is used to process multiple positive and negative samples to generate a training data set; in this embodiment, the tongue and ventral training module 101 uses the opencv_createsamples program in the opencv open source library to process multiple positive and negative samples Process to generate a training data set. The opencv_createsamples program is a general program for sample creation in the opencv open source library. Those skilled in the art can process multiple positive and negative samples through the existing opencv_createsamples program to generate a training data set.
步骤S23，利用opencv开源库中的opencv_traincascade程序对训练数据集进行训练生成舌腹面检测器；在本实施例中，舌腹面训练模块101利用opencv开源库中的opencv_traincascade程序对训练数据集进行训练生成舌腹面检测器。所述opencv_traincascade程序是opencv开源库中一种分类器训练的通用程序，本领域技术人员通过现有的opencv_traincascade程序即可对所述训练数据集进行训练生成舌腹面检测器。Step S23, the opencv_traincascade program in the opencv open source library is used to train the training data set to generate the tongue and ventral surface detector; in this embodiment, the tongue and ventral surface training module 101 uses the opencv_traincascade program in the opencv open source library to train the training data set to generate the tongue Ventral detector. The opencv_traincascade program is a general program for classifier training in the opencv open source library. Those skilled in the art can train the training data set to generate a tongue and ventral surface detector through the existing opencv_traincascade program.
步骤S24，利用舌腹面检测器从待检测的舌面图像中检测出包含嘴唇的舌腹面；具体地，舌腹面检测模块102在进行舌腹面检测与识别时，首先从所述输入单元11接收需要检测的舌面图像，例如图3中（a）所示为待检测的舌面图像，再利用训练好的舌腹面检测器从待检测的舌面图像中检测出包含嘴唇的舌腹面，例如图3中（b）所示包含嘴唇的舌腹面。Step S24, the tongue and ventral surface detector is used to detect the tongue and ventral surface including the lips from the tongue and facial image to be detected; specifically, the tongue and ventral surface detection module 102 first receives the needs from the input unit 11 when performing tongue and ventral surface detection and recognition The detected tongue image, for example, shown in (a) of FIG. 3 is the tongue surface image to be detected, and then the trained tongue and ventral surface detector is used to detect the tongue and ventral surface including the lips from the tongue surface image to be detected, for example 3, (b) shows the ventral surface of the tongue including the lips.
步骤S25，基于待检测的待检测的舌面图像确定舌腹面的位置信息，并根据舌腹面的位置信息截取包含嘴唇的舌腹面；具体地，所述舌腹面检测模块102基于待检测的舌腹面在舌面图像中的位置确定舌腹面的位置信息rect(x，y，l，w)，再根据舌腹面的位置信息截取包含嘴唇的舌腹面，其中x、y表示图3（a）中方框的左上角顶点坐标，l、w表示方框的长和宽。Step S25: Determine the position information of the tongue and ventral surface based on the tongue and facial image to be detected, and intercept the tongue and ventral surface including the lips according to the position information of the tongue and ventral surface; specifically, the tongue and ventral surface detection module 102 is based on the tongue and ventral surface to be detected Determine the position of the tongue and ventral surface rect(x, y, l, w) from the position in the tongue image, and then intercept the tongue and ventral surface containing the lips according to the position information of the tongue and ventral surface, where x and y represent the box in Figure 3(a) The coordinates of the vertex in the upper left corner of, l, w represent the length and width of the box.
步骤S26，对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域；在本实施例中，所述舌腹面分割模块103对截取的舌腹面（包含嘴唇）进行阈值分割处理，并对分割处理的结果进行形态学变换以去除舌腹面图像中的一些小斑点杂质，分别得到舌腹面的暗影区域和牙齿区域（位于嘴唇内的暗影区域和牙齿区域），如图3（c）中的白色区域表示舌腹面暗影区域，3（d）中的白色区域表示舌腹面的牙齿区域。In step S26, threshold segmentation is performed on the intercepted tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface; in this embodiment, the tongue and ventral surface segmentation module 103 performs threshold segmentation processing on the intercepted tongue and ventral surface (including lips), and Morphological transformation is performed on the results of the segmentation process to remove some small speckle impurities in the image of the tongue and ventral surface, respectively to obtain the shadow area and the tooth area of the tongue and ventral surface (dark area and tooth area located in the lips), as shown in Figure 3(c) The white area in the represents the shadow area on the ventral surface of the tongue, and the white area in 3(d) represents the tooth area on the ventral surface of the tongue.
步骤S27，利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板；在本实施例中，舌腹面分割模块103根据舌腹面暗影区域进行凸包计算生成舌腹面暗影区域的轮廓线，生成结果如图3（e）中的白色轮廓线。具体步骤为：舌腹面分割模块103利用canny边缘检测算法提取舌腹面暗影区域的轮廓线，然后提取轮廓线的所有坐标点（假设共有n个点），将提取的所有n个坐标点两两配对组成n×(n-1)/2条边；对于每条边，再检查剩余的(n-2)个点是否在该条边的同一侧；如果所有点都在该条边的一侧，则将该条边加入凸包集合，作为舌腹面暗影区域的轮廓线，直到所有组成的边都被遍历过为止；创建原始舌面图像大小的单通道模板图像，将舌腹面暗影区域的轮廓线映射到单通道模板图像的相应位置，将轮廓线内部非白色区域的所有像素值全部置为1，将轮廓线内部白色区域的所有像素值置为3，将轮廓线外部区域的所有像素值全部置0，依照舌腹面牙齿区域将单通道模板图像的相应位置的像素值置为0，从而得到舌腹面分割模板。其中，0代表确定的背景像素值（非舌腹面），1代表确定的前景像素值（舌腹面），2代表不确定的背景像素值（可能为非舌腹面），3代表不确定的前景像素值（可能为舌腹面）。Step S27, the tongue and ventral segmentation template is created by using the shadow region and the tooth region of the tongue and ventral surface; in this embodiment, the tongue and ventral segmentation module 103 performs convex hull calculation according to the tongue and ventral shadow region to generate the contour of the tongue and ventral shadow region, and the generated result is as follows: The white outline in Figure 3(e). The specific steps are: the tongue and ventral segmentation module 103 uses the canny edge detection algorithm to extract the contour line of the shadow region of the tongue and ventral surface, and then extracts all the coordinate points of the contour line (assuming that there are n points in total), and pairs all the extracted n coordinate points in pairs Make up n×(n-1)/2 edges; for each edge, check whether the remaining (n-2) points are on the same side of the edge; if all points are on the side of the edge, Then add this edge to the convex hull set as the outline of the shadow area of the tongue and ventral surface until all the constituent edges have been traversed; create a single-channel template image of the original tongue image size, and add the outline of the shadow area of the tongue and ventral surface Map to the corresponding position of the single-channel template image, set all pixel values of the non-white area inside the outline to 1, set all pixel values of the white area inside the outline to 3, and set all pixel values of the area outside the outline to all Set to 0, the pixel value of the corresponding position of the single-channel template image is set to 0 according to the tooth area of the tongue and ventral surface, thereby obtaining the tongue and ventral segmentation template. Among them, 0 represents the determined background pixel value (non-tongue surface), 1 represents the determined foreground pixel value (tongue surface), 2 represents the uncertain background pixel value (may be non-tongue surface), and 3 represents the uncertain foreground pixel Value (probably tongue and ventral surface).
步骤S28，将待检测的舌面图像和舌腹面分割模板输入到opencv开源库的grabCut函数中分割出舌腹面图像；在本实施例中，舌腹面分割模块103将待检测的舌面图像和舌腹面分割模板输入到opencv开源库的grabCut函数中分割出舌腹面图像。所述opencv开源库的grabCut函数为一种现有的舌腹面分割函数，该grabCut函数能够进行图像分割，本领域技术人员将舌面图像和舌腹面分割模板输入到grabCut函数中，利用该grabCut函数即可分割出舌腹面图像。如图3所示，例如将待检测的舌面图像（a）和舌腹面分割模板（e）输入grabCut函数中分割出舌腹面图像（f）。Step S28: Input the tongue image and tongue and ventral segmentation template to be detected into the openCV open source library's grabCut function to segment the tongue and ventral image; in this embodiment, the tongue and ventral segmentation module 103 converts the tongue and ventral image and tongue to be detected The ventral segmentation template is input into the grabCut function of the opencv open source library to segment the tongue and ventral image. The grabCut function of the opencv open source library is an existing tongue and ventral segmentation function, and the grabCut function can perform image segmentation. A person skilled in the art inputs a tongue surface image and a tongue and ventral segmentation template into the grabCut function, and uses the grabCut function You can segment the tongue and ventral image. As shown in FIG. 3, for example, the tongue image (a) and the tongue and ventral segmentation template (e) to be detected are input into the grabCut function to segment the tongue and ventral image (f).
步骤S29，通过输出单元将舌腹面图像输出至显示器上显示或打印机上打印；具体地，舌腹面输出模块104通过输出单元14将舌腹面图像输出至显示器上显示或打印机上打印，以供中医生对中医舌诊提供临床参考，从而辅助中医生对中医舌诊判断结果的准确性。Step S29, the tongue and ventral surface image is output to the display or the printer for printing via the output unit; specifically, the tongue and ventral surface output module 104 outputs the tongue and ventral surface image to the display or the printer for printing via the output unit 14 for the doctor Provide clinical reference for tongue diagnosis of traditional Chinese medicine, so as to assist Chinese doctors to judge the accuracy of results of tongue diagnosis of traditional Chinese medicine.
本发明还一种计算机可读存储介质，该计算机可读存储介质存储多条计算机程序指令，所述计算机程序指令由计算机装置的处理器加载并执行本发明所述舌面图像分割方法的各个步骤。本领域技术人员可以理解，上述实施方式中各种方法的全部或部分步骤可以通过相关程序指令完成，该程序可以存储于计算机可读存储介质中，存储介质可以包括：只读存储器、随机存储器、磁盘或光盘等。The invention also provides a computer-readable storage medium storing a plurality of computer program instructions, which are loaded by a processor of a computer device and execute the steps of the tongue image segmentation method of the invention . Those skilled in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by related program instructions, and the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, random access memory, Disk or CD, etc.
本发明所述舌面图像分割装置、方法及计算机存储介质，通过大量的不同舌面样本图像训练得到舌腹面检测器来有效地检测出包含嘴唇的舌腹面，提高了舌腹面分割的准确性，以供中医生对中医舌诊提供临床参考，从而辅助中医生对中医舌诊判断结果的准确性。The tongue image segmentation device, method and computer storage medium of the present invention obtain tongue and ventral surface detector through a large number of different tongue sample image training to effectively detect the tongue and ventral surface including lips, and improve the accuracy of tongue and ventral surface segmentation, It is for the Chinese doctor to provide clinical reference to the tongue diagnosis of Chinese medicine, so as to assist the doctor to judge the accuracy of the result of the tongue diagnosis of Chinese medicine.
以上仅为本发明的优选实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。The above are only preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by the description and drawings of the present invention, or directly or indirectly used in other related technical fields The same reason is included in the patent protection scope of the present invention.
相较于现有技术，本发明所述舌面图像分割装置、方法及计算机存储介质，通过大量的不同舌面样本图像训练得到舌腹面检测器来有效地检测出包含嘴唇的舌腹面，提高了舌腹面分割的准确性，以供中医生对中医舌诊提供临床参考，从而辅助中医生对中医舌诊判断结果的准确性。Compared with the prior art, the tongue image segmentation device, method and computer storage medium of the present invention, through a large number of different tongue surface sample image training to obtain a tongue and ventral surface detector to effectively detect the tongue and ventral surface including lips The accuracy of the segmentation of the ventral surface of the tongue is used by the Chinese doctor to provide a clinical reference for the tongue diagnosis of the Chinese medicine, thereby assisting the Chinese doctor to judge the accuracy of the tongue diagnosis of the Chinese medicine.
Claims (9)
- 一种舌面图像分割装置，包括适于实现各种计算机程序指令的处理器以及适于存储多条计算机程序指令的存储器，其特征在于，所述计算机程序指令由处理器加载并执行如下步骤：A tongue image segmentation device includes a processor suitable for implementing various computer program instructions and a memory suitable for storing multiple computer program instructions. The computer program instructions are loaded by the processor and perform the following steps:通过输入单元输入不同的舌面样本图像构建多个正负样本；Input multiple different tongue surface sample images through the input unit to construct multiple positive and negative samples;利用opencv开源库中的opencv_createsamples程序对多个正负样本进行处理生成一个训练数据集；Use the opencv_createsamples program in the opencv open source library to process multiple positive and negative samples to generate a training data set;利用opencv开源库中的opencv_traincascade程序对训练数据集进行训练生成舌腹面检测器；Use the opencv_traincascade program in the opencv open source library to train the training data set to generate the tongue and ventral surface detector;利用舌腹面检测器从待检测的舌面图像中检测出包含嘴唇的舌腹面；The tongue and ventral surface detector is used to detect the tongue and ventral surface including lips from the tongue and facial image to be detected;基于待检测的舌面图像确定舌腹面的位置信息，并根据舌腹面的位置信息截取包含嘴唇的舌腹面；Determine the position information of the tongue and ventral surface based on the tongue image to be detected, and intercept the tongue and ventral surface including the lips according to the position information of the tongue and ventral surface;对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域；Thresholding the tongue and ventral surface by threshold segmentation to obtain the shadow area and tooth area of the tongue and ventral surface;利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板；Use the shadow area and tooth area of the tongue and ventral surface to create a tongue and ventral segmentation template;将待检测的舌面图像和舌腹面分割模板输入到opencv开源库中的grabCut函数中分割出舌腹面图像；Input the tongue image and tongue and ventral segmentation template to be detected into the grabCut function in opencv open source library to segment the tongue and ventral image;通过输出单元将舌腹面图像输出至显示器上显示或打印机上打印。The image of the tongue and ventral surface is output to the display or printed on the printer through the output unit.
- 如权利要求1所述的舌面图像分割装置，其特征在于，所述多个正负样本包括多个正样本和多个负样本，一个正样本包括一个舌面样本图像中舌腹面区域的图像数据，一个负样本包括一个舌面样本图像中非舌腹面区域的图像数据。The tongue image segmentation device according to claim 1, wherein the plurality of positive and negative samples include a plurality of positive samples and a plurality of negative samples, and one positive sample includes an image of the ventral surface area of a tongue sample image For data, a negative sample includes image data of a non-lingual ventral surface area in a tongue sample image.
- 如权利要求1所述的舌面图像分割装置，其特征在于，所述对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域的步骤包括：The tongue image segmentation device according to claim 1, wherein the step of performing threshold segmentation processing on the intercepted tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface includes:对截取的舌腹面进行阈值分割处理；Threshold segmentation of the intercepted tongue and ventral surface;对分割处理的结果进行形态学变换以去除舌腹面图像中的斑点杂质，得到舌腹面的暗影区域和牙齿区域。Morphological transformation is performed on the result of the segmentation process to remove speckle impurities in the image of the tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface.
- 如权利要求1所述的舌面图像分割装置，其特征在于，所述利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板的步骤包括：The tongue image segmentation device as claimed in claim 1, wherein the step of creating a tongue and ventral segmentation template using the shadow area and the tooth area of the tongue and ventral surface includes:利用canny边缘检测算法提取舌腹面暗影区域的轮廓线，提取轮廓线的所有n个坐标点，并将提取的所有n个坐标点两两配对组成n×(n-1)/2条边；Use the canny edge detection algorithm to extract the contour line of the shadow area of the tongue and ventral surface, extract all n coordinate points of the contour line, and pair all the n coordinate points extracted to form n×(n-1)/2 edges;对于每条边，检查剩余的(n-2)个点是否在该条边的同一侧；For each edge, check whether the remaining (n-2) points are on the same side of the edge;如果所有点都在该条边的一侧，则将该条边加入凸包集合中直到所有边都被遍历过为止，并将该凸包集合作为舌腹面暗影区域的轮廓线；If all points are on one side of the edge, add the edge to the convex hull set until all edges have been traversed, and use the convex hull set as the outline of the shadow area of the tongue and ventral surface;创建原始舌面图像大小的单通道模板图像，并将舌腹面暗影区域的轮廓线映射到单通道模板图像的相应位置；Create a single-channel template image with the size of the original tongue image, and map the contour line of the shadow area on the ventral surface of the tongue to the corresponding position of the single-channel template image;将轮廓线内部非白色区域所有像素值全部置为1，将轮廓线内部白色区域所有像素值置为3，将轮廓线外部区域所有像素值全部置0，依照舌腹面牙齿区域将单通道模板图像相应位置的像素值置为0，得到舌腹面分割模板。Set all pixel values in the non-white area inside the contour line to 1, set all pixel values in the white area inside the contour line to 3, and set all pixel values in the outside area of the contour line to 0. According to the tongue and ventral teeth area, the single-channel template image The pixel value of the corresponding position is set to 0, and the tongue and ventral segmentation template is obtained.
- 一种舌面图像分割方法，其特征在于，该方法包括如下步骤：A tongue image segmentation method, characterized in that the method includes the following steps:通过输入单元输入不同的舌面样本图像构建多个正负样本；Input multiple different tongue surface sample images through the input unit to construct multiple positive and negative samples;利用opencv开源库中的opencv_createsamples程序对多个正负样本进行处理生成一个训练数据集；Use the opencv_createsamples program in the opencv open source library to process multiple positive and negative samples to generate a training data set;利用opencv开源库中的opencv_traincascade程序对训练数据集进行训练生成舌腹面检测器；Use the opencv_traincascade program in the opencv open source library to train the training data set to generate the tongue and ventral surface detector;利用舌腹面检测器从待检测的舌面图像中检测出包含嘴唇的舌腹面；The tongue and ventral surface detector is used to detect the tongue and ventral surface including lips from the tongue and facial image to be detected;基于待检测的舌面图像确定舌腹面的位置信息，并根据舌腹面的位置信息截取包含嘴唇的舌腹面；Determine the position information of the tongue and ventral surface based on the tongue image to be detected, and intercept the tongue and ventral surface including the lips according to the position information of the tongue and ventral surface;对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域；Thresholding the tongue and ventral surface by threshold segmentation to obtain the shadow area and tooth area of the tongue and ventral surface;利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板；Use the shadow area and tooth area of the tongue and ventral surface to create a tongue and ventral segmentation template;将待检测的舌面图像和舌腹面分割模板输入到opencv开源库中的grabCut函数中分割出舌腹面图像；Input the tongue image and tongue and ventral segmentation template to be detected into the grabCut function in opencv open source library to segment the tongue and ventral image;通过输出单元将舌腹面图像输出至显示器上显示或打印机上打印。The image of the tongue and ventral surface is output to the display or printed on the printer through the output unit.
- 如权利要求5所述的舌面图像分割方法，其特征在于，所述多个正负样本包括多个正样本和多个负样本，一个正样本包括一个舌面样本图像中舌腹面区域的图像数据，一个负样本包括一个舌面样本图像中非舌腹面区域的图像数据。The tongue image segmentation method according to claim 5, wherein the plurality of positive and negative samples include a plurality of positive samples and a plurality of negative samples, and one positive sample includes an image of the ventral surface area of a tongue sample image For data, a negative sample includes image data of a non-lingual ventral surface area in a tongue sample image.
- 如权利要求5所述的舌面图像分割方法，其特征在于，所述对截取的舌腹面进行阈值分割处理得到舌腹面的暗影区域和牙齿区域的步骤包括：The tongue image segmentation method according to claim 5, wherein the step of performing threshold segmentation processing on the intercepted tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface includes:对截取的舌腹面进行阈值分割处理；Threshold segmentation of the intercepted tongue and ventral surface;对分割处理的结果进行形态学变换以去除舌腹面图像中的斑点杂质，得到舌腹面的暗影区域和牙齿区域。Morphological transformation is performed on the result of the segmentation process to remove speckle impurities in the image of the tongue and ventral surface to obtain the shadow area and the tooth area of the tongue and ventral surface.
- 如权利要求5所述的舌面图像分割方法，其特征在于，所述利用舌腹面的暗影区域和牙齿区域创建舌腹面分割模板的步骤包括：The tongue image segmentation method according to claim 5, wherein the step of creating a tongue and ventral segmentation template using the shadow area and the tooth area of the tongue and ventral surface includes:利用canny边缘检测算法提取舌腹面暗影区域的轮廓线，提取轮廓线的所有n个坐标点，并将提取的所有n个坐标点两两配对组成n×(n-1)/2条边；Use the canny edge detection algorithm to extract the contour line of the shadow area of the tongue and ventral surface, extract all n coordinate points of the contour line, and pair all the n coordinate points extracted to form n×(n-1)/2 edges;对于每条边，检查剩余的(n-2)个点是否在该条边的同一侧；For each edge, check whether the remaining (n-2) points are on the same side of the edge;如果所有点都在该条边的一侧，则将该条边加入凸包集合中直到所有边都被遍历过为止，并将该凸包集合作为舌腹面暗影区域的轮廓线；If all points are on one side of the edge, add the edge to the convex hull set until all edges have been traversed, and use the convex hull set as the outline of the shadow area of the tongue and ventral surface;创建原始舌面图像大小的单通道模板图像，并将舌腹面暗影区域的轮廓线映射到单通道模板图像的相应位置；Create a single-channel template image with the size of the original tongue image, and map the contour line of the shadow area on the ventral surface of the tongue to the corresponding position of the single-channel template image;将轮廓线内部非白色区域所有像素值全部置为1，将轮廓线内部白色区域所有像素值置为3，将轮廓线外部区域所有像素值全部置0，依照舌腹面牙齿区域将单通道模板图像相应位置的像素值置为0，得到舌腹面分割模板。Set all pixel values in the non-white area inside the contour line to 1, set all pixel values in the white area inside the contour line to 3, and set all pixel values in the outside area of the contour line to 0. According to the tongue and ventral teeth area, the single-channel template image The pixel value of the corresponding position is set to 0, and the tongue and ventral segmentation template is obtained.
- 一种计算机可读存储介质，该计算机可读存储介质存储多条计算机程序指令，其特征在于，所述计算机程序指令由计算机装置的处理器加载并执行如权利要求5至8任一项所述舌面图像分割方法的各项方法步骤。A computer-readable storage medium storing a plurality of computer program instructions, characterized in that the computer program instructions are loaded and executed by a processor of a computer device according to any one of claims 5 to 8. Various method steps of tongue image segmentation method.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811418860.1 | 2018-11-26 | ||
| CN201811418860.1A CN111223117A (en) | 2018-11-26 | 2018-11-26 | Tongue surface image segmentation device, method and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020108436A1 true WO2020108436A1 (en) | 2020-06-04 |
Family
ID=70827778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/120644 WO2020108436A1 (en) | 2018-11-26 | 2019-11-25 | Tongue surface image segmentation device and method, and computer storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111223117A (en) |
| WO (1) | WO2020108436A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115908464A (en) * | 2023-01-09 | 2023-04-04 | 智慧眼科技股份有限公司 | Tongue image segmentation method and system |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667500A (en) * | 2020-06-04 | 2020-09-15 | 天津市天中依脉科技开发有限公司 | Tongue picture segmentation algorithm based on image block prior |
| CN113409304B (en) * | 2021-07-15 | 2022-05-20 | 深圳市圆道妙医科技有限公司 | Holographic-based multidimensional tongue image analysis method, system, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009038376A1 (en) * | 2007-09-21 | 2009-03-26 | Korea Institute Of Oriental Medicine | Extraction method of tongue region using graph-based approach and geometric properties |
| CN104537373A (en) * | 2015-01-13 | 2015-04-22 | 哈尔滨工业大学 | Multispectral sublingual image feature extraction method for sublingual microvascular complication diagnosis |
| CN106295139A (en) * | 2016-07-29 | 2017-01-04 | 姹ゅ钩 | A kind of tongue body autodiagnosis health cloud service system based on degree of depth convolutional neural networks |
| CN107977671A (en) * | 2017-10-27 | 2018-05-01 | 浙江工业大学 | A kind of tongue picture sorting technique based on multitask convolutional neural networks |
| CN108109160A (en) * | 2017-11-16 | 2018-06-01 | 浙江工业大学 | It is a kind of that interactive GrabCut tongue bodies dividing method is exempted from based on deep learning |
-
2018
- 2018-11-26 CN CN201811418860.1A patent/CN111223117A/en active Pending
-
2019
- 2019-11-25 WO PCT/CN2019/120644 patent/WO2020108436A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009038376A1 (en) * | 2007-09-21 | 2009-03-26 | Korea Institute Of Oriental Medicine | Extraction method of tongue region using graph-based approach and geometric properties |
| CN104537373A (en) * | 2015-01-13 | 2015-04-22 | 哈尔滨工业大学 | Multispectral sublingual image feature extraction method for sublingual microvascular complication diagnosis |
| CN106295139A (en) * | 2016-07-29 | 2017-01-04 | 姹ゅ钩 | A kind of tongue body autodiagnosis health cloud service system based on degree of depth convolutional neural networks |
| CN107977671A (en) * | 2017-10-27 | 2018-05-01 | 浙江工业大学 | A kind of tongue picture sorting technique based on multitask convolutional neural networks |
| CN108109160A (en) * | 2017-11-16 | 2018-06-01 | 浙江工业大学 | It is a kind of that interactive GrabCut tongue bodies dividing method is exempted from based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115908464A (en) * | 2023-01-09 | 2023-04-04 | 智慧眼科技股份有限公司 | Tongue image segmentation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111223117A (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A benchmark for comparison of dental radiography analysis algorithms | |
| US20220051405A1 (en) | Image processing method and apparatus, server, medical image processing device and storage medium | |
| WO2020108436A1 (en) | Tongue surface image segmentation device and method, and computer storage medium | |
| WO2021114817A1 (en) | Oct image lesion detection method and apparatus based on neural network, and medium | |
| WO2020108437A1 (en) | Sublingual vein feature extraction apparatus and method | |
| CN111986206A (en) | Lung lobe segmentation method and device based on UNet network and computer-readable storage medium | |
| CN111950595A (en) | Liver focus image processing method, system, storage medium, program, and terminal | |
| Li et al. | Natural tongue physique identification using hybrid deep learning methods | |
| Yue et al. | Automatic acetowhite lesion segmentation via specular reflection removal and deep attention network | |
| WO2020114346A1 (en) | Traditional chinese medicine tongue tip redness detection apparatus, method and computer storage medium | |
| Kumar | RYOLO v4-tiny: A deep learning based detector for detection of COVID and Non-COVID Pneumonia in CT scans and X-RAY images | |
| CN110063753B (en) | Method and device for measuring head circumference of fetus in ultrasonic image | |
| CN113989269B (en) | Traditional Chinese medicine tongue image tooth trace automatic detection method based on convolutional neural network multi-scale feature fusion | |
| CN116664592A (en) | Image-based arteriovenous blood vessel separation method and device, electronic equipment and medium | |
| US20220405916A1 (en) | Method for detecting the presence of pneumonia area in medical images of patients, detecting system, and electronic device employing method | |
| Oyelade et al. | Deep Learning Model for Improving the Characterization of Coronavirus on Chest X-ray Images Using CNN | |
| CN111768845B (en) | Pulmonary nodule auxiliary detection method based on optimal multi-scale perception | |
| Zhang et al. | A Comparison of Applying Image Processing and Deep Learning in Acne Region Extraction | |
| Smistad et al. | GPU-based airway segmentation and centerline extraction for image guided bronchoscopy | |
| Kumar et al. | Pulmonary Nodules Diagnosis from X-Ray Imaging using Image Processing | |
| WO2019232688A1 (en) | Method, apparatus, and computing device for segmenting veins in magnetic susceptibility weighted image | |
| Zhao et al. | Automatic tooth segmentation and classification in dental panoramic X-ray images | |
| Li et al. | PMJAF-Net: Pyramidal multi-scale joint attention and adaptive fusion network for explainable skin lesion segmentation | |
| Lin et al. | Dental Positioning Medical Assistance System for BW Radiograph Based on YOLOV4 | |
| CN116385756B (en) | Medical image recognition method and related device based on enhancement annotation and deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19889201 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19889201 Country of ref document: EP Kind code of ref document: A1 |