CN111797706A - Image-based parasite egg shape recognition system and method - Google Patents
Image-based parasite egg shape recognition system and method Download PDFInfo
- Publication number
- CN111797706A CN111797706A CN202010531459.XA CN202010531459A CN111797706A CN 111797706 A CN111797706 A CN 111797706A CN 202010531459 A CN202010531459 A CN 202010531459A CN 111797706 A CN111797706 A CN 111797706A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- egg
- gray
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/693—Acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of image recognition, and discloses a parasite egg shape recognition system and method based on images, wherein the parasite egg shape recognition system based on images comprises: the system comprises a sampling module, an image acquisition module, an illumination compensation module, an image preprocessing module, a central processing and control module, an image segmentation module, a feature extraction module, a feature identification module, a judgment and calibration module, an image library construction module and a display module. According to the invention, the worm egg specimen can be automatically collected through the sampling module, the automatic collection of the image is realized through the image collection module, the image noise can be effectively removed through carrying out median filtering on the collected image, the fuzzy effect on the original image is low while the noise is reduced, more details can be reserved, the performance of dividing each attribute of the decision tree into a certain data set is measured by obtaining the information gain of the attribute, the current data set is divided, the identification efficiency is improved, and the identification accuracy is ensured.
Description
Technical Field
The invention belongs to the technical field of image recognition, and particularly relates to a parasite egg shape recognition system and method based on images.
Background
At present, due to a plurality of reasons such as climate, biology, nature, population mobility, social and economic changes, reduction of parasite control strength and the like, sudden cases of various parasites are successively generated in parts of China, the number of acute infected people is greatly increased, and the epidemic situation of the parasites is in a rising state. Especially in vast remote mountainous areas and rural areas, the parasitic disease seriously affects the body health of local people. How to efficiently diagnose the parasitic diseases and discover the parasitic diseases in advance has important significance for preventing and treating the parasitic diseases.
At present, the parasite detection in disease prevention and control centers and hospitals is mainly to observe whether worm eggs or protozoa exist in excrement or body fluid slices of patients under a microscope. This method is effective when the number of pictures is small, but when the number of pictures is large, missed detection and false detection of the parasitic disease are often caused by insufficient experience, fatigue, inattention and the like of detection personnel. Scholars at home and abroad propose automatic identification methods for parasite pathogens, however, the methods are usually carried out on the basis of a relatively ideal state, the experimental method is difficult to meet the actual detection requirement, particularly, under the condition of more impurities, a stable identification result is difficult to obtain, and the identification efficiency is not high.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) when the number of pictures is large, missed detection and wrong detection of the parasitic diseases are often caused by insufficient experience, fatigue, inattention and the like of detection personnel.
(2) The existing automatic identification method for the parasite pathogens is difficult to obtain a stable identification result, and the identification efficiency is not high.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a parasite egg shape recognition system and method based on images.
The invention is realized in such a way that the image-based parasite egg shape recognition method comprises the following steps:
step one, a sample collecting unit of a sampling module collects a quantitative excrement sample by using a parasitic ovum automatic sampling device and puts the excrement sample into an ovum collecting sample box, and then a stirring unit adds diluent by using a mechanical arm and uniformly stirs the mixture.
And step two, after the mixture is uniformly mixed, the sample after dilution and uniform mixing is conveyed into a flow counting cell of a microscope by a conveying unit through a sample suction needle and then is conveyed onto a glass slide through a thin tube, and the sampling operation of the worm egg sample to be identified is completed.
Acquiring an original image of the worm egg sample by using a microscope lens through an image acquisition module; and the illumination compensation module is used for performing illumination compensation on the worm egg sample by using the illuminating lamp during image acquisition.
Acquiring the gray value of each pixel in the original image of the worm egg sample by using a gray processing unit through an image preprocessing module to obtain a gray matrix; and obtaining a balanced array according to the distribution trend of the row/column gray levels in the gray level matrix.
And fifthly, correcting the gray matrix according to the balanced array, carrying out gray processing on the collected egg images, and converting the collected color egg images into gray images.
And step six, sorting the pixels of the local area according to the gray level through a median filtering unit, separating the foreground from the background of the image, and taking the median of the gray levels in the sequence as the gray level value of the current pixel.
And seventhly, converting the gray value of the image pixel into a single image gray change curve, performing curve fitting correction on the image gray change curve, and determining the image cutting position according to the corrected gray change curve.
And step eight, receiving the acquired data information by using a central processing unit through a central processing and controlling module, and performing coordination control on each controlled module of the image-based parasite egg shape recognition system through the acquired information and preset parameters.
Step nine, accurately positioning the worm egg image to be segmented according to the image cutting position determined in the step seven by a template matching measurement similarity algorithm; and intercepting the position of the positioned worm egg image through an image segmentation module, and segmenting the preprocessed image by adopting an edge detection-based segmentation method.
And step ten, extracting the geometric shape features, the gray level features and the texture features of the eggs in the image by using a feature extraction program through a feature extraction module, and converting the geometric shape features, the gray level features and the texture features into feature vectors capable of being identified by a computer.
And step eleven, performing pattern recognition on the extracted egg image features by using a decision tree method through a feature recognition module, performing off-line training on parasite egg category samples, determining weights, performing operation on the weights and the obtained feature vectors, and recognizing the egg images to be recognized.
Step twelve, comparing the egg image recognition result with the same type of egg information stored in the database by using a judgment program through a judgment and calibration module, and judging the accuracy of the recognition result; and aiming at the difference, carrying out calibration processing on the image recognition result through a calibration program.
And thirteen, constructing an image library by using a database construction program through an image library construction module, and storing the original image, the preprocessing result, the image segmentation result, the characteristic vector, the image identification result and the calibration result of the worm egg sample.
And step fourteen, displaying the original image of the worm egg sample, the preprocessing result, the image segmentation result, the feature vector, the image recognition result and the real-time data of the calibration result by using a display through a display module.
Further, in step four, the distribution trend of the elements in the equalization array is opposite to the row/column gray distribution trend;
the obtaining of the balanced array according to the row/column gray distribution trend in the gray matrix includes:
(I) fitting to obtain a row/column gray distribution line according to the gray value sum of each row/column in the gray matrix;
(II) respectively substituting the gray value and the serial number into the row/column gray distribution line to obtain a undetermined value of the gray value of each row/column;
and (III) dividing the mean value of the gray value sum by each row/column gray undetermined value to obtain each numerical value in the balanced array.
Further, in step six, the method for median filtering processing includes:
(1) roaming a filter template of a sliding window containing a plurality of points in the image, and overlapping the center of the template with a certain pixel position in the image;
(2) reading the gray value of each corresponding pixel in the template;
(3) arranging the gray values from small to large;
(4) the intermediate data of this column of data is taken and assigned to the pixel corresponding to the center position of the template.
Further, in the step (4), if the window has odd number of elements, the middle value is the gray value of the middle element after the elements are sorted according to the size of the gray value; if even number of elements exist in the window, the median value is the average value of the gray levels of the middle two elements after the elements are sorted according to the gray level value.
Further, in the ninth step, the formula for cutting and intercepting the position of the positioned egg image by the image segmentation module is as follows:
X＝(width/10)*4，Y＝(height/9)*3，W＝(width/10)*5，H＝(height/9)*3；
wherein X is an abscissa when the cutting and intercepting are started, Y is an ordinate when the cutting and intercepting are started, W is the length of the preprocessed image, and H is the width of the preprocessed image; width is the length of the egg image to be segmented, and height is the width of the egg image to be segmented.
Further, in the eleventh step, the method for performing pattern recognition on the egg image by using the decision tree method includes:
1) integrating picture information, and combining the image data information through an image processing process to form an information data source; generalizing image data, removing irrelevant attributes, and generating a decision tree training set;
2) constructing a branch for each possible value of each attribute, and learning a classification model from a training data set to generate an initial decision tree;
3) cutting branches which can not increase the judgment error rate of the decision tree; and extracting classification rules from the pruned decision tree, and screening and warehousing each path from the root to the leaf to generate the decision tree with the most strategy.
Another object of the present invention is to provide an image-based parasite egg shape recognition system applying the image-based parasite egg shape recognition method, the image-based parasite egg shape recognition system comprising:
the sampling module is connected with the central processing and control module and is used for sampling the worm egg sample to be identified through the automatic parasitic egg sampling device;
the image acquisition module is connected with the central processing and control module and is used for acquiring an original image of the worm egg sample through a microscope lens;
the illumination compensation module is connected with the central processing and control module and is used for performing illumination compensation on the worm egg sample during image acquisition through an illuminating lamp;
the image preprocessing module is connected with the central processing and control module and is used for carrying out gray processing and median filtering processing on the collected egg images through an image preprocessing program so as to separate the foreground and the background of the images;
the central processing and control module is connected with the sampling module, the image acquisition module, the illumination compensation module, the image preprocessing module, the image segmentation module, the feature extraction module, the feature identification module, the judgment and calibration module, the image library construction module and the display module, and is used for receiving acquired data information through a central processing unit and carrying out coordination control on each controlled module of the image-based parasite egg shape identification system through acquired information and preset parameters;
the image segmentation module is connected with the central processing and control module and is used for carrying out segmentation processing on the preprocessed image by adopting a segmentation method based on edge detection;
the characteristic extraction module is connected with the central processing and control module and used for extracting the geometric shape characteristics, the gray level characteristics and the texture characteristics of the eggs in the image through a characteristic extraction program and converting the geometric shape characteristics, the gray level characteristics and the texture characteristics into characteristic vectors which can be identified by a computer;
the characteristic identification module is connected with the central processing and control module and used for carrying out pattern identification on the extracted egg image characteristics by using a decision tree method, carrying out off-line training on parasite egg category samples, determining a weight, carrying out operation on the weight and the obtained characteristic vector and identifying the egg image to be identified;
the judging and calibrating module is connected with the central processing and controlling module and is used for comparing the egg image recognition result with the same type of egg information stored in the database through a judging program and judging the accuracy of the recognition result; aiming at the difference, carrying out calibration processing on the image recognition result through a calibration program;
the image library construction module is connected with the central processing and control module and used for constructing an image library through a database construction program and storing an original image, a preprocessing result, an image segmentation result, a characteristic vector, an image identification result and a calibration result of the egg sample;
and the display module is connected with the central processing and control module and is used for displaying the original image, the preprocessing result, the image segmentation result, the characteristic vector, the image identification result and the real-time data of the calibration result of the worm egg sample through a display.
Further, the sampling module comprises: the device comprises a sample collecting unit, a stirring unit and a conveying unit;
the sample collection unit is used for collecting a quantitative excrement sample and putting the excrement sample into the egg collection sample box;
the stirring unit is used for adding the diluent into the egg collecting specimen box through the mechanical arm and stirring and uniformly mixing;
the conveying unit is used for conveying the diluted and uniformly mixed sample into a flow counting cell of a microscope through a sample sucking needle and then conveying the sample onto a glass slide through a thin tube;
the central processing and control module comprises: the device comprises a display unit, a configuration unit, a data processing unit and an instruction output unit;
the display unit is used for displaying and outputting the running state and the working parameters of the system through a display screen;
the configuration unit is used for presetting and configuring the working parameters of the system through external input equipment;
the data processing unit is used for receiving external acquisition information and processing the acquisition information according to preset parameters;
the instruction output unit is used for generating corresponding control instructions according to the processing results and the preset parameters and transmitting the control instructions to each controlled module;
the image preprocessing module comprises: a gray processing unit and a median filtering unit;
the gray processing unit is used for converting the collected color worm egg image into a gray image;
and the median filtering unit is used for sorting the pixels of the local area according to the gray level, and taking the median of the gray level in the area as the gray level value of the current pixel.
It is another object of the present invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the image-based parasite egg shape identification method when executed on an electronic device.
It is another object of the present invention to provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the image-based parasite egg shape identification method.
By combining all the technical schemes, the invention has the advantages and positive effects that: according to the invention, the worm egg specimen can be automatically collected through the sampling module, and the image is automatically collected through the image collecting module; the balanced array is obtained through the distribution trend of the row/column gray in the gray matrix, and the balanced array can balance the distribution trend of the row/column gray in the gray matrix and balance the distribution of the gray in the gray matrix, so that the brightness of an over-dark area is improved, the brightness of an over-bright area is reduced, and the effect of increasing the definition of a target image is realized; meanwhile, image noise can be effectively removed by carrying out median filtering on the collected image, the fuzzy effect on the original image is low while noise is reduced, and more details can be reserved. The method for refining and refining the established empty decision tree by the decision tree method continuously adds nodes until the decision tree can effectively classify sample data, measures the performance of the attribute to a certain data set by obtaining the information gain of each attribute of the decision tree based on an information theory, further divides the current data set, constructs a tree structure which is divided by target attribute values and represents a classification rule by continuously repeating the data set division steps, achieves induction and classification of data, improves the identification efficiency and ensures the identification accuracy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
FIG. 1 is a flow chart of a method for identifying the shape of an egg of a parasite based on an image according to an embodiment of the present invention.
FIG. 2 is a block diagram of an image-based parasite egg shape recognition system provided by an embodiment of the present invention;
in the figure: 1. a sampling module; 2. an image acquisition module; 3. an illumination compensation module; 4. an image preprocessing module; 5. a central processing and control module; 6. an image segmentation module; 7. a feature extraction module; 8. a feature identification module; 9. a judgment and calibration module; 10. an image library construction module; 11. and a display module.
Fig. 3 is a flowchart of a method for performing gray processing on an acquired egg image by a gray processing unit according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for performing median filtering processing on an acquired egg image by a median filtering unit according to an embodiment of the present invention.
Fig. 5 is a flowchart of a method for performing pattern recognition on extracted egg image features by using a decision tree method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In view of the problems of the prior art, the present invention provides a system and a method for recognizing the shape of an egg of a parasite based on an image, which are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the image-based parasite egg shape recognition method provided by the embodiment of the present invention comprises the following steps:
s101, sampling an egg sample to be identified by using a parasitic egg automatic sampling device through a sampling module; acquiring an original image of the insect egg sample by using a microscope lens through an image acquisition module; and the illumination compensation module is used for performing illumination compensation on the worm egg sample by using the illuminating lamp during image acquisition.
S102, carrying out gray processing and median filtering processing on the collected egg image by using an image preprocessing program through an image preprocessing module, and separating the foreground and the background of the image.
And S103, receiving the acquired data information by using a central processing unit through a central processing and controlling module, and performing coordination control on each controlled module of the image-based parasite egg shape identification system through the acquired information and preset parameters.
And S104, performing segmentation processing on the preprocessed image by adopting a segmentation method based on edge detection through an image segmentation module.
And S105, extracting the geometric shape features, the gray level features and the texture features of the eggs in the image by using a feature extraction program through a feature extraction module, and converting the geometric shape features, the gray level features and the texture features into feature vectors which can be identified by a computer.
And S106, performing pattern recognition on the extracted egg image features by using a decision tree method through a feature recognition module, performing off-line training on parasite egg category samples, determining weights, performing operation on the weights and the obtained feature vectors, and recognizing the egg images to be recognized.
S107, comparing the egg image recognition result with the same type of egg information stored in the database by using a judgment program through a judgment and calibration module, and judging the accuracy of the recognition result; and aiming at the difference, carrying out calibration processing on the image recognition result through a calibration program.
And S108, constructing an image library by using a database construction program through an image library construction module, and storing an original image, a preprocessing result, an image segmentation result, a characteristic vector, an image identification result and a calibration result of the egg sample.
And S109, displaying the original image, the preprocessing result, the image segmentation result, the feature vector, the image recognition result and the real-time data of the calibration result of the worm egg sample by using a display through a display module.
As shown in fig. 2, an image-based parasite egg shape recognition system provided by an embodiment of the present invention includes: the system comprises a sampling module 1, an image acquisition module 2, an illumination compensation module 3, an image preprocessing module 4, a central processing and control module 5, an image segmentation module 6, a feature extraction module 7, a feature identification module 8, a judgment and calibration module 9, an image library construction module 10 and a display module 11.
The sampling module 1 is connected with the central processing and control module 5 and is used for sampling the worm egg sample to be identified through the automatic parasitic egg sampling device;
the image acquisition module 2 is connected with the central processing and control module 5 and is used for acquiring an original image of the worm egg sample through a microscope lens;
the illumination compensation module 3 is connected with the central processing and control module 5 and is used for performing illumination compensation on the worm egg sample during image acquisition through an illuminating lamp;
the image preprocessing module 4 is connected with the central processing and control module 5 and is used for carrying out gray processing and median filtering processing on the collected egg images through an image preprocessing program so as to separate the foreground and the background of the images;
the central processing and control module 5 is connected with the sampling module 1, the image acquisition module 2, the illumination compensation module 3, the image preprocessing module 4, the image segmentation module 6, the feature extraction module 7, the feature recognition module 8, the judgment and calibration module 9, the image library construction module 10 and the display module 11, and is used for receiving acquired data information through a central processing unit and carrying out coordination control on each controlled module of the image-based parasite egg shape recognition system through acquired information and preset parameters;
the image segmentation module 6 is connected with the central processing and control module 5 and is used for carrying out segmentation processing on the preprocessed image by adopting a segmentation method based on edge detection;
the characteristic extraction module 7 is connected with the central processing and control module 5 and is used for extracting the geometric shape characteristics, the gray level characteristics and the texture characteristics of the eggs in the image through a characteristic extraction program and converting the geometric shape characteristics, the gray level characteristics and the texture characteristics into characteristic vectors which can be identified by a computer;
the characteristic identification module 8 is connected with the central processing and control module 5 and is used for carrying out pattern identification on the extracted egg image characteristics by using a decision tree method, carrying out off-line training on parasite egg category samples, determining weight values, carrying out operation on the weight values and the obtained characteristic vectors, and identifying the egg images to be identified;
the judging and calibrating module 9 is connected with the central processing and controlling module 5 and is used for comparing the egg image recognition result with the same type of egg information stored in the database through a judging program and judging the accuracy of the recognition result; aiming at the difference, carrying out calibration processing on the image recognition result through a calibration program;
the image library construction module 10 is connected with the central processing and control module 5 and is used for constructing an image library through a database construction program and storing an original image, a preprocessing result, an image segmentation result, a characteristic vector, an image identification result and a calibration result of the egg sample;
and the display module 11 is connected with the central processing and control module 5 and is used for displaying the original image, the preprocessing result, the image segmentation result, the characteristic vector, the image identification result and the real-time data of the calibration result of the worm egg sample through a display.
The sampling module 1 provided by the embodiment of the invention comprises: the device comprises a sample collecting unit 1-1, a stirring unit 1-2 and a conveying unit 1-3;
the sample collecting unit 1-1 is used for collecting a quantitative excrement sample and putting the excrement sample into an egg collecting sample box;
the stirring unit 1-2 is used for adding the diluent into the egg collecting specimen box through the mechanical arm and uniformly stirring;
and the conveying unit 1-3 is used for conveying the diluted and uniformly mixed sample into a flow counting cell of a microscope through a sample sucking needle and then conveying the sample onto a glass slide through a thin tube.
The image preprocessing module 4 provided by the embodiment of the present invention includes: a gray processing unit 4-1 and a median filtering unit 4-2;
the gray level processing unit 4-1 is used for converting the collected color worm egg image into a gray level image;
and the median filtering unit 4-2 is used for sorting the pixels in the local area according to the gray level, and taking the median of the gray levels in the area as the gray level value of the current pixel.
The central processing and control module 5 provided by the embodiment of the present invention includes: the device comprises a display unit 5-1, a configuration unit 5-2, a data processing unit 5-3 and an instruction output unit 5-4;
the display unit 5-1 is used for displaying and outputting the running state and the working parameters of the system through a display screen;
the configuration unit 5-2 is used for presetting and configuring the working parameters of the system through external input equipment;
the data processing unit 5-3 is used for receiving external acquisition information and processing the acquisition information according to preset parameters;
and the instruction output unit 5-4 is used for generating a corresponding control instruction according to the processing result and the preset parameters and transmitting the control instruction to each controlled module.
The invention is further described with reference to specific examples.
Example 1
Fig. 1 shows an image-based parasite egg shape recognition method according to an embodiment of the present invention, and fig. 3 shows a preferred embodiment of the image-based parasite egg shape recognition method according to an embodiment of the present invention, where a gray processing unit performs gray processing on an acquired insect egg image, the method includes:
s201, acquiring the gray value of each pixel in the original image of the worm egg sample by using a gray processing unit through an image preprocessing module to obtain a gray matrix.
And S202, obtaining a balanced array according to the row/column gray distribution trend in the gray matrix.
S203, correcting the gray matrix according to the balanced array, carrying out gray processing on the collected egg images, and converting the collected color egg images into gray images.
S204, sorting the pixels of the local area according to the gray level through a median filtering unit, separating the foreground from the background of the image, and taking the median of the gray levels in the sequence as the gray level of the current pixel.
The distribution trend of the elements in the balanced array provided by the embodiment of the invention is opposite to the row/column gray distribution trend; the obtaining of the balanced array according to the row/column gray distribution trend in the gray matrix includes:
(I) and fitting to obtain a row/column gray distribution line according to the gray value sum of each row/column in the gray matrix.
And (II) substituting the gray value and the serial number into the row/column gray distribution line respectively to obtain a undetermined value of the gray value of each row/column.
And (III) dividing the mean value of the gray value sum by each row/column gray undetermined value to obtain each numerical value in the balanced array.
Example 2
The parasite egg shape recognition method based on the image provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 4, the method for performing median filtering processing on the collected worm egg image through a median filtering unit provided by the embodiment of the invention comprises the following steps:
s301, the filtering template of the sliding window containing a plurality of points is roamed in the image, and the center of the template is superposed with a certain pixel position in the image.
S302, reading the gray values of the corresponding pixels in the template, and arranging the gray values from small to large.
S303, the intermediate data of the row of data is taken and assigned to the pixel corresponding to the center position of the template.
In step S303 provided in the embodiment of the present invention, if there are odd number of elements in the window, the middle value is a gray value of a middle element obtained by sorting the elements according to the size of the gray value; if even number of elements exist in the window, the median value is the average value of the gray levels of the middle two elements after the elements are sorted according to the gray level value.
Example 3
The method for recognizing the shape of the parasite eggs based on the images, provided by the embodiment of the invention, is shown in fig. 1, and as a preferred embodiment, is shown in fig. 5, and the method for performing pattern recognition on the extracted image features of the parasite eggs by using a decision tree method, provided by the embodiment of the invention, comprises the following steps:
s401, integrating picture information, and combining image data information to form an information data source through an image processing process; and generalizing image data, removing irrelevant attributes, and generating a decision tree training set.
S402, constructing a branch for each possible value of each attribute, learning a classification model from a training data set, and generating an initial decision tree.
S403, cutting off branches which do not increase the judgment error rate of the decision tree; and extracting classification rules from the pruned decision tree, and screening and warehousing each path from the root to the leaf to generate the decision tree with the most strategy.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (ssd)), among others.
In the description of the present invention, "a plurality" means two or more unless otherwise specified; the terms "upper", "lower", "left", "right", "inner", "outer", "front", "rear", "head", "tail", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the invention. Furthermore, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (10)
1. An image-based parasite egg shape identification method, comprising the steps of:
firstly, a sample collecting unit of a sampling module collects a quantitative excrement sample by using a parasite egg automatic sampling device and puts the excrement sample into an egg collecting sample box, and then a stirring unit adds diluent by using a mechanical arm and uniformly stirs the mixture;
after the worm egg sample is uniformly mixed, the sample after being diluted and uniformly mixed is conveyed into a flowing counting cell of a microscope by a conveying unit through a sample sucking needle and then is conveyed onto a glass slide through a thin tube, and the sampling operation of the worm egg sample to be identified is completed;
acquiring an original image of the worm egg sample by using a microscope lens through an image acquisition module; the illumination compensation module is used for carrying out illumination compensation on the worm egg sample during image acquisition by using an illuminating lamp;
acquiring the gray value of each pixel in the original image of the worm egg sample by using a gray processing unit through an image preprocessing module to obtain a gray matrix; obtaining a balanced array according to the distribution trend of the row/column gray levels in the gray level matrix;
correcting the gray matrix according to the balanced array, carrying out gray processing on the collected worm egg image, and converting the collected color worm egg image into a gray image;
step six, sorting the pixels of the local area according to the gray level through a median filtering unit, separating the foreground from the background of the image, and taking the median of the gray levels in the sequence as the gray level of the current pixel;
step seven, converting the gray value of the image pixel into a single image gray change curve, performing curve fitting correction on the gray change curve of the image, and determining an image cutting position according to the corrected gray change curve;
step eight, receiving acquired data information by using a central processing unit through a central processing and controlling module, and performing coordination control on each controlled module of the image-based parasite egg shape recognition system through the acquired information and preset parameters;
step nine, accurately positioning the worm egg image to be segmented according to the image cutting position determined in the step seven by a template matching measurement similarity algorithm; intercepting the position of the positioned worm egg image through an image segmentation module, and segmenting the preprocessed image by adopting an edge detection-based segmentation method;
step ten, extracting the geometric shape features, the gray level features and the texture features of the eggs in the image by using a feature extraction program through a feature extraction module, and converting the geometric shape features, the gray level features and the texture features into feature vectors which can be identified by a computer;
step eleven, pattern recognition is carried out on the extracted egg image features through a feature recognition module by utilizing a decision tree method, off-line training is carried out on parasite egg category samples, weight is determined, operation is carried out on the weight and the obtained feature vectors, and the egg images to be recognized are recognized;
step twelve, comparing the egg image recognition result with the same type of egg information stored in the database by using a judgment program through a judgment and calibration module, and judging the accuracy of the recognition result; aiming at the difference, carrying out calibration processing on the image recognition result through a calibration program;
thirteen, constructing an image library by using a database construction program through an image library construction module, and storing an original image, a preprocessing result, an image segmentation result, a feature vector, an image identification result and a calibration result of the worm egg sample;
and step fourteen, displaying the original image of the worm egg sample, the preprocessing result, the image segmentation result, the feature vector, the image recognition result and the real-time data of the calibration result by using a display through a display module.
2. The image-based parasite egg shape recognition method of claim 1 wherein in step four, the distribution trend of the elements in said equalized array is opposite to said row/column gray scale distribution trend;
the obtaining of the balanced array according to the row/column gray distribution trend in the gray matrix includes:
(I) fitting to obtain a row/column gray distribution line according to the gray value sum of each row/column in the gray matrix;
(II) respectively substituting the gray value and the serial number into the row/column gray distribution line to obtain a undetermined value of the gray value of each row/column;
and (III) dividing the mean value of the gray value sum by each row/column gray undetermined value to obtain each numerical value in the balanced array.
3. The image-based parasite egg shape recognition method of claim 1 wherein in step six, said median filtering process comprises:
(1) roaming a filter template of a sliding window containing a plurality of points in the image, and overlapping the center of the template with a certain pixel position in the image;
(2) reading the gray value of each corresponding pixel in the template;
(3) arranging the gray values from small to large;
(4) the intermediate data of this column of data is taken and assigned to the pixel corresponding to the center position of the template.
4. The image-based parasite egg shape identification method of claim 3 wherein in step (4), if there are an odd number of elements in the window, the median value is the gray value of the middle element sorted by gray value size; if even number of elements exist in the window, the median value is the average value of the gray levels of the middle two elements after the elements are sorted according to the gray level value.
5. The image-based parasite egg shape recognition method of claim 1 wherein in step nine, said image segmentation module cuts and intercepts the location of said image of the located egg according to the following formula:
X＝(width/10)*4，Y＝(height/9)*3，W＝(width/10)*5，H＝(height/9)*3；
wherein X is an abscissa when the cutting and intercepting are started, Y is an ordinate when the cutting and intercepting are started, W is the length of the preprocessed image, and H is the width of the preprocessed image; width is the length of the egg image to be segmented, and height is the width of the egg image to be segmented.
6. The image-based parasite egg shape recognition method of claim 1 wherein in step eleven, said method of pattern recognition of an image of an egg using a decision tree method comprises:
1) integrating picture information, and combining the image data information through an image processing process to form an information data source; generalizing image data, removing irrelevant attributes, and generating a decision tree training set;
2) constructing a branch for each possible value of each attribute, and learning a classification model from a training data set to generate an initial decision tree;
3) cutting branches which can not increase the judgment error rate of the decision tree; and extracting classification rules from the pruned decision tree, and screening and warehousing each path from the root to the leaf to generate the decision tree with the most strategy.
7. An image-based parasite egg shape recognition system using the image-based parasite egg shape recognition method of any one of claims 1-6, wherein the image-based parasite egg shape recognition system comprises:
the sampling module is connected with the central processing and control module and is used for sampling the worm egg sample to be identified through the automatic parasitic egg sampling device;
the image acquisition module is connected with the central processing and control module and is used for acquiring an original image of the worm egg sample through a microscope lens;
the illumination compensation module is connected with the central processing and control module and is used for performing illumination compensation on the worm egg sample during image acquisition through an illuminating lamp;
the image preprocessing module is connected with the central processing and control module and is used for carrying out gray processing and median filtering processing on the collected egg images through an image preprocessing program so as to separate the foreground and the background of the images;
the central processing and control module is connected with the sampling module, the image acquisition module, the illumination compensation module, the image preprocessing module, the image segmentation module, the feature extraction module, the feature identification module, the judgment and calibration module, the image library construction module and the display module, and is used for receiving acquired data information through a central processing unit and carrying out coordination control on each controlled module of the image-based parasite egg shape identification system through acquired information and preset parameters;
the image segmentation module is connected with the central processing and control module and is used for carrying out segmentation processing on the preprocessed image by adopting a segmentation method based on edge detection;
the characteristic extraction module is connected with the central processing and control module and used for extracting the geometric shape characteristics, the gray level characteristics and the texture characteristics of the eggs in the image through a characteristic extraction program and converting the geometric shape characteristics, the gray level characteristics and the texture characteristics into characteristic vectors which can be identified by a computer;
the characteristic identification module is connected with the central processing and control module and used for carrying out pattern identification on the extracted egg image characteristics by using a decision tree method, carrying out off-line training on parasite egg category samples, determining a weight, carrying out operation on the weight and the obtained characteristic vector and identifying the egg image to be identified;
the judging and calibrating module is connected with the central processing and controlling module and is used for comparing the egg image recognition result with the same type of egg information stored in the database through a judging program and judging the accuracy of the recognition result; aiming at the difference, carrying out calibration processing on the image recognition result through a calibration program;
the image library construction module is connected with the central processing and control module and used for constructing an image library through a database construction program and storing an original image, a preprocessing result, an image segmentation result, a characteristic vector, an image identification result and a calibration result of the egg sample;
and the display module is connected with the central processing and control module and is used for displaying the original image, the preprocessing result, the image segmentation result, the characteristic vector, the image identification result and the real-time data of the calibration result of the worm egg sample through a display.
8. The image-based parasite egg shape recognition system of claim 7, wherein said sampling module comprises: the device comprises a sample collecting unit, a stirring unit and a conveying unit;
the sample collection unit is used for collecting a quantitative excrement sample and putting the excrement sample into the egg collection sample box;
the stirring unit is used for adding the diluent into the egg collecting specimen box through the mechanical arm and stirring and uniformly mixing;
the conveying unit is used for conveying the diluted and uniformly mixed sample into a flow counting cell of a microscope through a sample sucking needle and then conveying the sample onto a glass slide through a thin tube;
the central processing and control module comprises: the device comprises a display unit, a configuration unit, a data processing unit and an instruction output unit;
the display unit is used for displaying and outputting the running state and the working parameters of the system through a display screen;
the configuration unit is used for presetting and configuring the working parameters of the system through external input equipment;
the data processing unit is used for receiving external acquisition information and processing the acquisition information according to preset parameters;
the instruction output unit is used for generating corresponding control instructions according to the processing results and the preset parameters and transmitting the control instructions to each controlled module;
the image preprocessing module comprises: a gray processing unit and a median filtering unit;
the gray processing unit is used for converting the collected color worm egg image into a gray image;
and the median filtering unit is used for sorting the pixels of the local area according to the gray level, and taking the median of the gray level in the area as the gray level value of the current pixel.
9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing the image-based parasite egg shape recognition method of any one of claims 1-7 when executed on an electronic device.
10. A computer readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the method of image-based parasite egg shape identification according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531459.XA CN111797706A (en) | 2020-06-11 | 2020-06-11 | Image-based parasite egg shape recognition system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531459.XA CN111797706A (en) | 2020-06-11 | 2020-06-11 | Image-based parasite egg shape recognition system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111797706A true CN111797706A (en) | 2020-10-20 |
Family
ID=72803322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010531459.XA Pending CN111797706A (en) | 2020-06-11 | 2020-06-11 | Image-based parasite egg shape recognition system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797706A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344542A (en) * | 2021-06-23 | 2021-09-03 | 广州弘广畜禽设备有限公司 | Clear data processing system of excrement equipment |
| CN114299494A (en) * | 2022-01-20 | 2022-04-08 | 广东省农业科学院动物科学研究所 | Method and system for detecting worm oval characteristics of aquatic product image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392240A (en) * | 2014-10-28 | 2015-03-04 | 中国疾病预防控制中心寄生虫病预防控制所 | Parasite egg identification method based on multi-feature fusion |
| CN105606608A (en) * | 2016-03-28 | 2016-05-25 | 广州博厚生物科技有限公司 | Image gray-scale processing based data computing method and application thereof in detection field |
| CN106295458A (en) * | 2015-05-11 | 2017-01-04 | 青岛若贝电子有限公司 | Eyeball detection method based on image procossing |
| CN108564124A (en) * | 2018-04-13 | 2018-09-21 | 山东农业大学 | A kind of magnaporthe grisea spore microimage detection recognition methods based on support vector machines |
| CN110738603A (en) * | 2018-07-18 | 2020-01-31 | 中国商用飞机有限责任公司 | image gray scale processing method, device, computer equipment and storage medium |
-
2020
- 2020-06-11 CN CN202010531459.XA patent/CN111797706A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392240A (en) * | 2014-10-28 | 2015-03-04 | 中国疾病预防控制中心寄生虫病预防控制所 | Parasite egg identification method based on multi-feature fusion |
| CN106295458A (en) * | 2015-05-11 | 2017-01-04 | 青岛若贝电子有限公司 | Eyeball detection method based on image procossing |
| CN105606608A (en) * | 2016-03-28 | 2016-05-25 | 广州博厚生物科技有限公司 | Image gray-scale processing based data computing method and application thereof in detection field |
| CN108564124A (en) * | 2018-04-13 | 2018-09-21 | 山东农业大学 | A kind of magnaporthe grisea spore microimage detection recognition methods based on support vector machines |
| CN110738603A (en) * | 2018-07-18 | 2020-01-31 | 中国商用飞机有限责任公司 | image gray scale processing method, device, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| PEARSON, THOMAS 等: "INSECT EGG COUNTING BY IMAGE ANALYSIS AND LASER CUTTING OF EGG-LADEN MASS REARING OVIPOSITION PADS", 《APPLIED ENGINEERING IN AGRICULTURE》 * |
| 孟鑫: "基于机器视觉的寄生虫卵显微图像自动识别研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 陈国一: "基于模糊聚类的粪便镜检图像识别研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113344542A (en) * | 2021-06-23 | 2021-09-03 | 广州弘广畜禽设备有限公司 | Clear data processing system of excrement equipment |
| CN113344542B (en) * | 2021-06-23 | 2022-03-18 | 广州弘广畜禽设备有限公司 | Clear data processing system of excrement equipment |
| CN114299494A (en) * | 2022-01-20 | 2022-04-08 | 广东省农业科学院动物科学研究所 | Method and system for detecting worm oval characteristics of aquatic product image |
| CN114299494B (en) * | 2022-01-20 | 2022-07-22 | 广东省农业科学院动物科学研究所 | Method and system for detecting worm-egg-shaped characteristics of aquatic product image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11842556B2 (en) | Image analysis method, apparatus, program, and learned deep learning algorithm | |
| WO2021139258A1 (en) | Image recognition based cell recognition and counting method and apparatus, and computer device | |
| US7088854B2 (en) | Method and apparatus for generating special-purpose image analysis algorithms | |
| CN110084150B (en) | Automatic white blood cell classification method and system based on deep learning | |
| EP2302583A1 (en) | Image segmentation | |
| CN112380900A (en) | Deep learning-based cervical fluid-based cell digital image classification method and system | |
| CN111079620B (en) | White blood cell image detection and identification model construction method and application based on transfer learning | |
| CN110728666B (en) | Typing method and system for chronic nasosinusitis based on digital pathological slide | |
| CN110796661B (en) | Fungal microscopic image segmentation detection method and system based on convolutional neural network | |
| CN112819821B (en) | Cell nucleus image detection method | |
| JPH11510282A (en) | Apparatus and method for measuring robustness of classification | |
| CN111797706A (en) | Image-based parasite egg shape recognition system and method | |
| CN115909006B (en) | Mammary tissue image classification method and system based on convolution transducer | |
| JP3916395B2 (en) | Test system with sample pretreatment function | |
| Davidson et al. | Automated detection and staging of malaria parasites from cytological smears using convolutional neural networks | |
| CN114494197A (en) | Cerebrospinal fluid cell identification and classification method for small-complexity sample | |
| CN110648312A (en) | Method for identifying wool and cashmere fibers based on scale morphological characteristic analysis | |
| CN117576103B (en) | Urinary sediment microscopic examination analysis system integrating electric control microscope and deep learning algorithm | |
| CN110807754B (en) | Fungus microscopic image segmentation detection method and system based on deep semantic segmentation | |
| CN112084913A (en) | End-to-end human body detection and attribute identification method | |
| CN116258844A (en) | Rapid and accurate identification method for phenotype character of cotton leaf | |
| JP2001510894A (en) | Inspection system with sample inspection function | |
| CN117809124B (en) | Medical image association calling method and system based on multi-feature fusion | |
| CN115100187B (en) | Glaucoma image detection method based on federal learning | |
| CN114187480A (en) | Bone marrow image cell image detection and classification method and system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201020 |