CN110766687B - Brucella detection device, computer equipment and storage medium - Google Patents
Brucella detection device, computer equipment and storage mediumDownload PDFInfo
- Publication number
- CN110766687B CN110766687BCN201911054537.5ACN201911054537ACN110766687BCN 110766687 BCN110766687 BCN 110766687BCN 201911054537 ACN201911054537 ACN 201911054537ACN 110766687 BCN110766687 BCN 110766687B
- Authority
- CN
- China
- Prior art keywords
- image
- brucella
- test product
- detection test
- brucella detection
- 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.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明属于检测领域，尤其涉及一种布鲁氏杆菌检测装置、计算机设备和存储介质。The invention belongs to the detection field, and in particular relates to a Brucella detection device, computer equipment and a storage medium.
背景技术Background technique
布鲁氏杆菌是革兰氏阴性胞内寄生菌，无鞭毛、质粒，无荚膜。其根据宿主和致病性的不同可分为猪、牛、羊、沙林鼠、绵羊、犬，布氏杆菌6种19型，其中猪、牛、羊3种16型可通过气溶胶感染人类，寄生于单核巨噬细胞，破坏机体的免疫系统，是世界范围内广泛流行的亚种。Brucella is a Gram-negative intracellular parasite with no flagella, plasmids, and no capsule. According to different hosts and pathogenicity, it can be divided into pigs, cattle, sheep, squirrels, sheep, dogs, and 6 types of 19 types of Brucella, of which 3 types of 16 types of pigs, cattle, and sheep can infect humans through aerosols , which parasitizes mononuclear macrophages and destroys the immune system of the body, is a subspecies widely prevalent in the world.
当前布鲁氏杆菌的检测方法有多种：分离培养方法、PCR方法、基因探针方法、虎红平板凝集试验、试管凝集试验、补体结合试验、酶联免疫吸附试验等；目前我国诊断布鲁氏杆菌病的法定确诊方法为试管凝集试验和补体结合试验，在实际应用中，尤其是猪、牛、羊的养殖行业和流通环节，对布鲁氏杆菌进行检测诊断常用的方法为虎红平板凝集试验和试管凝集试验。There are many detection methods for Brucella at present: isolation and culture method, PCR method, gene probe method, tiger bengal plate agglutination test, test tube agglutination test, complement fixation test, enzyme-linked immunosorbent assay, etc.; The statutory diagnostic methods for bacillosis are test tube agglutination test and complement fixation test. In practical applications, especially in the breeding industry and circulation of pigs, cattle, and sheep, the commonly used method for detection and diagnosis of Brucella is tiger red plate. Agglutination test and tube agglutination test.
在试验检测过程中，需要实验人员进行手工操作，并手动拿取实验反应载体及人工用肉眼观察试验结果，从而判断实验结果为阳性或阴性，以此鉴别待测标本中是否含有布鲁氏杆菌，需要花费很长的时间进行观察并记录结果，效率低下，检测不一致，易出现混淆和判断失误。During the test and detection process, the experimenter needs to perform manual operations, and manually take the experimental reaction carrier and manually observe the test result with the naked eye, so as to judge whether the test result is positive or negative, so as to identify whether the specimen to be tested contains Brucella , It takes a long time to observe and record the results, the efficiency is low, the detection is inconsistent, and it is prone to confusion and misjudgment.
发明内容Contents of the invention
本发明实施例的目的在于提供一种布鲁氏杆菌检测装置，旨在解决人工检测混淆和判断失误的问题，确保检测的高效、稳定和一致性。The purpose of the embodiments of the present invention is to provide a brucella detection device, aiming to solve the problems of manual detection confusion and misjudgment, and ensure high efficiency, stability and consistency of detection.
本发明实施例是这样实现的，本发明的装置用于实施布鲁氏杆菌检测方法，所述方法包括如下步骤：The embodiment of the present invention is achieved like this, and device of the present invention is used for implementing Brucella detection method, and described method comprises the steps:
获取布鲁氏杆菌检测试验产物图像，从获取的布鲁氏杆菌检测试验产物图像中提取布鲁氏杆菌检测试验产物图像直方图特征，分割提取的布鲁氏杆菌检测试验产物图像直方图特征中的灰度阈值，用以区别不同的目标对象；Acquire the image of the Brucella detection test product, extract the histogram feature of the Brucella detection test product image from the acquired Brucella detection test product image, and segment the extracted Brucella detection test product image histogram feature The gray threshold value is used to distinguish different target objects;
对获取的布鲁氏杆菌检测试验产物图像作掩膜处理，将布鲁氏杆菌检测试验产物图像的亮度、色调以及饱和度参数独立定量控制，用于准确定量的表征颜色特征；Perform mask processing on the obtained image of the Brucella detection test product, and independently quantitatively control the brightness, hue, and saturation parameters of the Brucella detection test product image for accurate and quantitative characterization of color characteristics;
根据提取的直方图特征图像抽取并分离布鲁氏杆菌检测试验产物图像的特征参数，将掩膜处理得到的图像进行轮廓追踪并作加强边缘化算子处理；According to the extracted histogram feature image, the feature parameters of the Brucella detection test product image are extracted and separated, and the image obtained by the mask processing is subjected to contour tracking and enhanced marginalization operator processing;
将加强边缘化算子处理得到的数据与分离的布鲁氏杆菌检测试验产物图像特征参数作形态计算并与含有标准布鲁氏杆菌检测试验产物图像信息的数据库对比，确定待检测的标本中是否含有布鲁氏杆菌。Perform morphological calculations on the data obtained by strengthening the marginalization operator and the image feature parameters of the isolated Brucella detection test product, and compare it with the database containing the image information of the standard Brucella detection test product to determine whether the sample to be detected is Contains Brucella.
本发明实施例的另一目的在于，一种布鲁氏杆菌检测装置，所述布鲁氏杆菌检测装置包括：Another object of the embodiment of the present invention is, a kind of brucella detection device, described brucella detection device comprises:
提取单元，用于从获取的布鲁氏杆菌检测试验产物图像中提取布鲁氏杆菌检测试验产物图像直方图特征，分割提取的布鲁氏杆菌检测试验产物图像直方图特征中的灰度阈值，以区别不同的目标对象；The extraction unit is used to extract the histogram feature of the Brucella detection test product image from the acquired Brucella detection test product image, and segment the gray threshold in the extracted Brucella detection test product image histogram feature, to distinguish between different target audiences;
色彩抽取单元，用于将布鲁氏杆菌检测试验产物图像的亮度、色调以及饱和度参数独立定量控制作掩膜处理；The color extraction unit is used to independently quantitatively control the brightness, hue and saturation parameters of the Brucella detection test product image as a mask;
分析单元，用于根据提取的直方图特征图像抽取并分离布鲁氏杆菌检测试验产物图像的特征参数，将掩膜处理得到的图像进行轮廓追踪并作加强边缘化算子处理，将加强边缘化算子处理得到的数据与分离的布鲁氏杆菌检测试验产物图像特征参数作形态计算，与含有标准布鲁氏杆菌检测试验产物图像信息的数据库对比，确定待检测的标本中是否含有布鲁氏杆菌。The analysis unit is used to extract and separate the characteristic parameters of the Brucella detection test product image according to the extracted histogram feature image, perform contour tracking on the image obtained by mask processing and perform enhanced marginalization operator processing, and strengthen the marginalization The data obtained by the operator processing and the image characteristic parameters of the isolated Brucella detection test product are used for morphological calculation, and compared with the database containing the image information of the standard Brucella detection test product, to determine whether the specimen to be detected contains Brucella bacilli.
本发明实施例的另一目的在于，一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机程序，所述计算机程序被所述处理器执行时，使得所述处理器执行所述布鲁氏杆菌检测方法的步骤。Another object of the embodiments of the present invention is a computer device, including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the Steps in the Brucella detection method.
本发明实施例的另一目的在于，一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时，使得所述处理器执行布鲁氏杆菌检测方法的步骤。Another object of the embodiments of the present invention is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processor executes the Bruce Steps in the bacilli detection method.
本发明实施例提供的一种布鲁氏杆菌检测装置，利用图像采集设备对布鲁氏杆菌检测实验产物进行图像采集识别，通过对得到的反应产物的图像的边界、层次、轮廓、形状、大小、颜色等综合型态进行计算和分析，实现对反应终产物的准确识别，最后得出实验结论并对布鲁氏杆菌的检测实验结果给予判定和评价。A brucella detection device provided in an embodiment of the present invention uses an image acquisition device to collect and identify images of the experimental products of brucella detection. Calculation and analysis of comprehensive forms such as color, color, etc., to realize accurate identification of the final product of the reaction, and finally draw the experimental conclusion and give judgment and evaluation on the detection experiment results of Brucella.
附图说明Description of drawings
图1为本发明实施例提供的布鲁氏杆菌检测装置的系统图；Fig. 1 is the system diagram of the brucella detection device that the embodiment of the present invention provides;
图2为本发明实施例提供的布鲁氏杆菌检测方法的流程图。Fig. 2 is a flow chart of the Brucella detection method provided by the embodiment of the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。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 make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
如图2所示，在一个实施例中，本发明装置实施的布鲁氏杆菌检测方法，所述方法包括如下步骤：As shown in Figure 2, in one embodiment, the brucella detection method that device of the present invention implements, described method comprises the steps:
获取布鲁氏杆菌检测试验产物图像，从获取的布鲁氏杆菌检测试验产物图像中提取布鲁氏杆菌检测试验产物图像直方图特征，分割提取的布鲁氏杆菌检测试验产物图像直方图特征中的灰度阈值，用以区别不同的目标对象；Acquire the image of the Brucella detection test product, extract the histogram feature of the Brucella detection test product image from the acquired Brucella detection test product image, and segment the extracted Brucella detection test product image histogram feature The gray threshold value is used to distinguish different target objects;
直方图是反映一幅图像中的灰度级数与出现这种灰度的概率之间的关系图。将摄录的图像变成灰度图像，用以区别不同的目标对象；对于灰度图像，利用图像灰度统计信息的方法显示灰度分布，而分割的阈值选择在不同山谷处，采用直方图阈值化方法。设(x，y)是二位数字图像的平面坐标，图像灰度的取值范围为G＝{0,1,2，…L-1}(习惯上0表示最暗的灰度级，L-1表示最亮的灰度级)，位于坐标(x，y)上的像素点的灰度值以f(x，y)表示。假设分割阈值τ∈G，而B＝{b0，b1}，b0，b1∈G代表一个二值灰度级，则图像{f(x，y)}在阈值τ上的分割结果可以表示为：A histogram is a graph reflecting the relationship between the number of gray levels in an image and the probability of such gray levels appearing. Turn the recorded image into a grayscale image to distinguish different target objects; for the grayscale image, use the image grayscale statistical information method to display the grayscale distribution, and select the segmentation threshold at different valleys, using the histogram Thresholding method. Let (x, y) be the plane coordinates of the two-digit digital image, and the value range of the gray scale of the image is G={0,1,2,...L-1} (customarily, 0 represents the darkest gray level, L -1 represents the brightest gray level), and the gray value of the pixel located on the coordinate (x, y) is represented by f(x, y). Suppose the segmentation threshold τ∈G, and B={b0 , b1 }, b0 , b1 ∈G represents a binary gray level, then the segmentation result of the image {f(x, y)} on the threshold τ It can be expressed as:
基于阈值的选取的图像分割实际就是按照某个准则函数求最优阈值的过程。The image segmentation based on threshold selection is actually the process of finding the optimal threshold according to a certain criterion function.
对获取的布鲁氏杆菌检测试验产物图像作掩膜处理，将布鲁氏杆菌检测试验产物图像的亮度、色调以及饱和度参数独立定量控制，用于准确定量的表征颜色特征；Perform mask processing on the obtained image of the Brucella detection test product, and independently quantitatively control the brightness, hue, and saturation parameters of the Brucella detection test product image for accurate and quantitative characterization of color characteristics;
RGB颜色空间：(Red、Green、Blue)，色彩空间一种，即三基色模式，通过对红(R)、绿(G)、蓝(B)三个颜色通道的变化以及它们相互之间的叠加来得到各式各样的颜色的色彩模式。RGB color space: (Red, Green, Blue), a kind of color space, that is, the three-primary color mode, through the change of the three color channels of red (R), green (G), and blue (B) and the relationship between them Color modes that stack to get a variety of colors.
HLS颜色空间：(Hue、Saturation、Lightness)，色彩空间的一种，即色调、饱和度和亮度空间。HLS color space: (Hue, Saturation, Lightness), a kind of color space, that is, hue, saturation and brightness space.
色调、饱和度和亮度是颜色所包含的三个要素,利用彩色六棱锥空间模型对图像进行处理，从人的视觉系统出发，更加符合人的视觉特性对于颜色的理解，将亮度与反应色彩本质特征的两个参数——色调、饱和度分开，使得图像处理的时候能够针对性更强；在色调、饱和度和亮度空间中三分量色调、饱和度和亮度具有相对独立性，可分别对它们进行控制，能够准确定量地描述颜色特征。Hue, saturation and brightness are the three elements contained in color. Using the color hexagonal pyramid space model to process images, starting from the human visual system, it is more in line with the understanding of human visual characteristics. The two parameters of the feature—hue and saturation are separated, so that the image processing can be more targeted; in the hue, saturation and brightness space, the three-component hue, saturation and brightness are relatively independent, and they can be respectively Controlled, can accurately and quantitatively describe the color characteristics.
根据提取的直方图特征图像抽取并分离布鲁氏杆菌检测试验产物图像的特征参数，将掩膜处理得到的图像进行轮廓追踪并作加强边缘化算子处理；According to the extracted histogram feature image, the feature parameters of the Brucella detection test product image are extracted and separated, and the image obtained by the mask processing is subjected to contour tracking and enhanced marginalization operator processing;
将加强边缘化算子处理得到的数据与分离的布鲁氏杆菌检测试验产物图像特征参数作形态计算，图像的边界、层次、轮廓、形状、大小、颜色等综合型态进行计算和分析，并与含有标准布鲁氏杆菌检测试验产物图像信息的数据库对比，确定待检测的标本中是否含有布鲁氏杆菌。The data obtained by strengthening the marginalization operator processing and the image characteristic parameters of the isolated Brucella detection test product are used for morphological calculation, and the comprehensive types of image boundaries, layers, contours, shapes, sizes, colors, etc. are calculated and analyzed, and Compared with the database containing the image information of standard Brucella detection test products, it is determined whether the specimen to be detected contains Brucella.
在一个实施例中，所述获取布鲁氏杆菌检测试验产物图像之前，还包括布鲁氏杆菌检测试验产物图像的采集，采集的图像为彩色图像，为所述掩膜处理提供参数对象；In one embodiment, before the acquisition of the Brucella detection test product image, it also includes the acquisition of the Brucella detection test product image, and the collected image is a color image, which provides parameter objects for the mask processing;
具体是通过图像采集设备进行采集，包括但不限于摄像头、扫描设备、照相机、摄像机等可进行图像采集或对终产物进行成像的设备。Specifically, it is collected through image acquisition equipment, including but not limited to cameras, scanning equipment, cameras, video cameras and other equipment that can perform image acquisition or image the final product.
在一个实施例中，所述抽取并分离布鲁氏杆菌检测试验产物图像的特征参数，包括布鲁氏杆菌检测试验产物图像直方图特征的几何特征参数计算：In one embodiment, the extraction and separation of the feature parameters of the Brucella detection test product image includes the geometric feature parameter calculation of the Brucella detection test product image histogram feature:
紧凑度计算，在提取的布鲁氏杆菌检测试验产物图像直方图特征中，根据标记的区域面积和周长计算目标区域的形状复杂程度的特征量；Calculation of compactness, in the histogram feature of the extracted Brucella detection test product image, calculate the feature quantity of the shape complexity of the target area according to the area and perimeter of the marked area;
重心位置计算，计算连通区域中像素坐标的平均值，面积等于目标区域中包含的像素数，对每个像素点统计连通区域。Center of gravity position calculation, calculate the average value of pixel coordinates in the connected area, the area is equal to the number of pixels contained in the target area, and count the connected area for each pixel.
特征参数计算，计算长度、宽度、欧拉数特征参数。Characteristic parameter calculation, calculate the characteristic parameters of length, width and Euler number.
在产物的各种几何特征中，紧凑度和重心为最重要的特征之一。Among the various geometric features of a product, compactness and center of gravity are one of the most important features.
紧凑度是在面积和周长的基础上，计算目标(或区域)的形状复杂程度的特征量；其计算方程为：Compactness is a feature quantity for calculating the shape complexity of the target (or region) on the basis of area and perimeter; its calculation equation is:
面积等于区域中包含的像素数，对每个像素点的统计通过连通物体计算Connect函数中的像素总数Count来实现，用于创建与指定外部端口的连接。The area is equal to the number of pixels contained in the area. The statistics of each pixel is realized by calculating the total number of pixels Count in the Connect function of connected objects, which is used to create a connection with the specified external port.
重心位置计算，为求连通区域中像素坐标的平均值。若其像素的坐标为(xi，yi)(i＝0,1,2，…，n-1)，其重心坐标(x0，y0)可以由下列公式求得：The calculation of the center of gravity position is to find the average value of the pixel coordinates in the connected area. If the coordinates of its pixels are (xi, yi) (i=0, 1, 2, ..., n-1), the coordinates of its center of gravity (x0, y0) can be obtained by the following formula:
最后计算长度、宽度、欧拉数等许多特征参数。Finally, many characteristic parameters such as length, width, Euler number, etc. are calculated.
在一个实施例中，所述标记的区域在所述从获取的布鲁氏杆菌检测试验产物图像中提取布鲁氏杆菌检测试验产物图像直方图特征中进行二值化处理并孔洞填充后标记；In one embodiment, the marked region carries out binarization processing and marks after hole filling in the extraction of the Brucella detection test product image histogram feature from the acquired Brucella detection test product image;
二值化就是将图像上的像素点的灰度值设置为0或255,也就是将整个图像呈现出明显的只有黑和白的视觉效果。Binarization is to set the gray value of the pixels on the image to 0 or 255, that is, to present the entire image with an obvious visual effect of only black and white.
孔洞是二值图像内部八连通点阵组成的闭合圈内的像素点集，孔洞填充的基本步骤如下：A hole is a set of pixels in a closed circle composed of eight connected lattices inside a binary image. The basic steps of hole filling are as follows:
确定二值图像像素[0,0]为初始种子点，这里认为[0,0]像素点为背景点，而非某个孔洞内部的点；Determine the binary image pixel [0,0] as the initial seed point, here the [0,0] pixel is considered as the background point, not a point inside a hole;
以种子点为起点，采用形态学膨胀算法对背景进行填充。膨胀到不能膨胀为止；膨胀运算采用四连通结构元；Starting from the seed point, the background is filled with the morphological expansion algorithm. Expand until it cannot be expanded; the expansion operation uses four connected structural elements;
背景填充结束后，对得到的二值图像取反得到新的二值图像，此时图像为全部孔洞的点集；After the background filling is completed, invert the obtained binary image to obtain a new binary image, at this time the image is the point set of all holes;
将第三步骤得到的二值图像与原二值图像相加及得到孔洞填充的结果。Add the binary image obtained in the third step to the original binary image and obtain the hole filling result.
在一个实施例中，所述二值化处理并孔洞填充后的图像进行腐蚀去噪并细化后作区域标记，用以忽略干扰图像。In one embodiment, the binarized and hole-filled image is subjected to erosion, denoising and thinning for area marking to ignore interference images.
在一个实施例中，所述掩膜处理得到的图像进行轮廓追踪之前，还包括二值化处理和腐蚀去杂质处理，用以对凸显图像中的目标；In one embodiment, before the contour tracking of the image obtained by the mask processing, binarization processing and etching and impurity removal processing are also included to highlight the target in the image;
具体是先进行二值化处理，再进行腐蚀去杂质，从而得到较为清晰的图像，对其进行细化处理，获取轮廓并进行追踪。Specifically, the binarization process is performed first, and then the impurities are etched to obtain a clearer image, which is thinned, and the contour is obtained and tracked.
在一个实施例中，所述掩膜处理还包括颜色空间转换，将布鲁氏杆菌检测试验产物图像的RGB颜色空间与HSL颜色空间进行互相转换，用于将产物从图像中分离开来进而得到识别；In one embodiment, the masking process also includes color space conversion, and the RGB color space and the HSL color space of the Brucella detection test product image are converted to each other, so as to separate the product from the image and then obtain identification;
在对图像进行处理和分析时，需要将RGB颜色空间和HSL颜色空间进行互相转换，从而可以研究图像中产物的特征和量，再加上选择参数的变化范围约束，即可将产物从图像中分离开来进而得到识别。When processing and analyzing the image, it is necessary to convert the RGB color space and the HSL color space to each other, so that the characteristics and quantity of the product in the image can be studied, coupled with the constraints of the change range of the selected parameters, the product can be extracted from the image separated and identified.
如图1所示，在一个实施例中，提供了一种布鲁氏杆菌检测装置，所述布鲁氏杆菌检测装置包括：As shown in Figure 1, in one embodiment, a kind of brucella detection device is provided, and described brucella detection device comprises:
提取单元，用于从获取的布鲁氏杆菌检测试验产物图像中提取布鲁氏杆菌检测试验产物图像直方图特征，分割提取的布鲁氏杆菌检测试验产物图像直方图特征中的灰度阈值，以区别不同的目标对象；The extraction unit is used to extract the histogram feature of the Brucella detection test product image from the acquired Brucella detection test product image, and segment the gray threshold in the extracted Brucella detection test product image histogram feature, to distinguish between different target audiences;
色彩抽取单元，用于将布鲁氏杆菌检测试验产物图像的亮度、色调以及饱和度参数独立定量控制作掩膜处理；The color extraction unit is used to independently quantitatively control the brightness, hue and saturation parameters of the Brucella detection test product image as a mask;
分析单元，用于根据提取的直方图特征图像抽取并分离布鲁氏杆菌检测试验产物图像的特征参数，将掩膜处理得到的图像进行轮廓追踪并作加强边缘化算子处理，将加强边缘化算子处理得到的数据与分离的布鲁氏杆菌检测试验产物图像特征参数作形态计算，并与含有标准布鲁氏杆菌检测试验产物图像信息的数据库对比，确定待检测的标本中是否含有布鲁氏杆菌。The analysis unit is used to extract and separate the characteristic parameters of the Brucella detection test product image according to the extracted histogram feature image, perform contour tracking on the image obtained by mask processing and perform enhanced marginalization operator processing, and strengthen the marginalization The data obtained by the operator processing and the image characteristic parameters of the isolated Brucella detection test product are used for morphological calculation, and compared with the database containing the image information of the standard Brucella detection test product to determine whether the specimen to be detected contains Brucella. coli.
在一个实施例中，所述提取单元包括提取直方图特征模块210，用于提取布鲁氏杆菌检测试验产物图像直方图特征；In one embodiment, described extracting unit comprises extracting
特征参数计算模块211，用于紧凑度计算，在提取的布鲁氏杆菌检测试验产物图像直方图特征中，根据标记的区域面积和周长计算目标区域的形状复杂程度的特征量；和重心位置计算，计算连通区域中像素坐标的平均值，面积等于目标区域中包含的像素数，对每个像素点统计连通区域；以及特征参数计算，计算长度、宽度、欧拉数特征参数。Feature
在一个实施例中，所述处理单元包括：In one embodiment, the processing unit includes:
掩膜处理模块220，用于将亮度(L)与反应色彩本质特征的两个参数——色调(H)、饱和度(S)分开，使得图像处理的时候能够针对性更强；The
边缘化算子处理模块221，图像的边缘对人的视觉具有重要的意义，一般而言，当人们看-个有边缘的物体时，首先感觉到的便是边缘。灰度或结构等信息的突变处称为边缘。边缘是一个区域的结束，也是另一个区域的开始，利用该特征可以分割图像。需要指出的是，检测出的边缘并不等同于实际目标的真实边缘。由于图像数据是二维的，而实际物体是三维的，从三维到二维的投影必然会造成信息的丢失，再加上成像过程中的光照不均和噪声等因素的影响，使得有边缘的地方不一定能被检测出来，而检测出的边缘也不一定代表实际边缘。图像的边缘有方向和幅度两个属性，沿边缘方向像素变化平缓，垂直于边缘方向像素变化剧烈。边缘上的这种变化可以用微分算子检测出来，通常用一阶或两阶导数来检测边缘。In the edge operator processing module 221, the edge of an image is of great significance to human vision. Generally speaking, when people look at an object with an edge, the edge is the first thing people feel. The sudden change of information such as grayscale or structure is called edge. An edge is the end of one region and the beginning of another, and this feature can be used to segment an image. It should be pointed out that the detected edges are not equal to the real edges of the actual object. Since the image data is two-dimensional, but the actual object is three-dimensional, the projection from three-dimensional to two-dimensional will inevitably cause the loss of information, coupled with the influence of factors such as uneven illumination and noise in the imaging process, making the edge Places may not necessarily be detected, and detected edges may not necessarily represent actual edges. The edge of the image has two attributes, direction and magnitude. The pixels change smoothly along the edge direction, and the pixels change sharply perpendicular to the edge direction. Such changes on edges can be detected using differential operators, usually using first or second derivatives to detect edges.
在一个实施例中，所述色彩抽取单元中包括型态计算模块300，用于对掩膜处理和直方图特征提取的图像进行计算分析，与含有标准布鲁氏杆菌检测试验产物图像信息的数据库对比，得出实验结论，并给出阴性或阳性的判定结果。In one embodiment, the color extraction unit includes a
在一个实施例中，所述病菌检测装置还包括布鲁氏杆菌检测试验产物图像获取模块100，用于通过采集设备采集布鲁氏杆菌检测试验产物的彩色图像。In one embodiment, the germ detection device further includes a Brucella detection test product
在一个实施例中，一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机程序，所述计算机程序被所述处理器执行时，使得所述处理器执行所述布鲁氏杆菌检测方法的步骤。In one embodiment, a computer device includes a memory and a processor, a computer program is stored in the memory, and when the computer program is executed by the processor, the processor is made to execute the brucella The steps of the detection method.
在一个实施例中，一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时，使得所述处理器执行所述布鲁氏杆菌检测方法的步骤。In one embodiment, a computer-readable storage medium, a computer program is stored on the computer-readable storage medium, when the computer program is executed by a processor, the processor is made to perform the detection of brucella method steps.
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。The above-mentioned embodiments only express several implementation modes of the present invention, and the description thereof is relatively specific and detailed, but should not be construed as limiting the patent scope of the present invention. It should be pointed out that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention should be based on the appended claims.
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. within range.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911054537.5ACN110766687B (en) | 2019-10-31 | 2019-10-31 | Brucella detection device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911054537.5ACN110766687B (en) | 2019-10-31 | 2019-10-31 | Brucella detection device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110766687A CN110766687A (en) | 2020-02-07 |
| CN110766687Btrue CN110766687B (en) | 2023-03-28 |
Family
ID=69335496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911054537.5AActiveCN110766687B (en) | 2019-10-31 | 2019-10-31 | Brucella detection device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110766687B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114299493A (en)* | 2021-12-31 | 2022-04-08 | 四川上太科技有限公司 | A spore identification system and method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012168085A (en)* | 2011-02-16 | 2012-09-06 | Ncd:Kk | Method for detecting specific microbial components |
| US9864901B2 (en)* | 2015-09-15 | 2018-01-09 | Google Llc | Feature detection and masking in images based on color distributions |
| CN105678793B (en)* | 2016-02-26 | 2019-01-15 | 浙江大学 | A kind of method of early diagnosis and device of the Prospect on Kiwifruit Bacterial Canker based on image co-registration |
| CN109948544B (en)* | 2019-03-20 | 2021-04-30 | 南京师范大学 | Automatic positioning and identifying method for target bacterial colony |
- 2019
- 2019-10-31CNCN201911054537.5Apatent/CN110766687B/enactiveActive
Non-Patent Citations (2)
| Title |
|---|
| 基于计算机视觉技术快速检测食品中蜡样芽孢杆菌的研究;王慧莹;《知网》;20110915;13-55* |
| 食品中沙门氏菌快速检测方法的研究;任秀;《知网》;20111015;41-51* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110766687A (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7148581B2 (en) | Colony contrast collection | |
| CN107909138B (en) | A method for counting round-like particles based on Android platform | |
| CN107580715B (en) | Method and system for automatically counting microbial colonies | |
| CN105574527B (en) | A kind of quick object detecting method based on local feature learning | |
| CN105427275B (en) | Crop field environment wheat head method of counting and device | |
| CN104794502A (en) | Image processing and mode recognition technology-based rice blast spore microscopic image recognition method | |
| CN108564085A (en) | A kind of method of automatic reading pointer type instrument reading | |
| JP2011188496A (en) | Backlight detection device and backlight detection method | |
| US10395091B2 (en) | Image processing apparatus, image processing method, and storage medium identifying cell candidate area | |
| US11257301B2 (en) | Image analysis apparatus, image analysis method, and image analysis program | |
| CN105844242A (en) | Method for detecting skin color in image | |
| CN110866932A (en) | Multi-channel tongue edge detection device and method and storage medium | |
| CN113421301B (en) | A method and system for locating central area of field crops | |
| Kiruthika et al. | Matching of different rice grains using digital image processing | |
| CN114998290A (en) | Fabric flaw detection method, device, equipment and medium based on supervised mode | |
| CN119919410B (en) | Method for measuring size and appearance of O-rings | |
| Ghosh et al. | An automatic bleeding detection technique in wireless capsule endoscopy from region of interest | |
| CN113506242A (en) | Corn aflatoxin detection method based on YOLO | |
| CN111222371A (en) | Sublingual vein feature extraction device and method | |
| CN110766687B (en) | Brucella detection device, computer equipment and storage medium | |
| CN103377375A (en) | Method for processing gastroscope image | |
| CN113853607A (en) | System and method for monitoring bacterial growth and predicting colony biomass of colonies | |
| CN113706515B (en) | Tongue image anomaly determination method, tongue image anomaly determination device, computer equipment and storage medium | |
| Hashim et al. | Optic disc boundary detection from digital fundus images | |
| CN104463182A (en) | NBI gastroscope image processing method based on key point detection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | Denomination of invention:A Brucella detection device, computer equipment, and storage medium Granted publication date:20230328 Pledgee:Shenzhen Rural Commercial Bank Co.,Ltd. Dapeng Branch Pledgor:Shenzhen Zhongke Tonghui Technology Co.,Ltd. Registration number:Y2024980052665 | |
| PE01 | Entry into force of the registration of the contract for pledge of patent right |