CN115861135A - Image enhancement and identification method applied to box panoramic detection - Google Patents
Image enhancement and identification method applied to box panoramic detection Download PDFInfo
- Publication number
- CN115861135A CN115861135A CN202310179040.6A CN202310179040A CN115861135A CN 115861135 A CN115861135 A CN 115861135A CN 202310179040 A CN202310179040 A CN 202310179040A CN 115861135 A CN115861135 A CN 115861135A
- Authority
- CN
- China
- Prior art keywords
- gray
- pixel point
- index
- pixel
- panoramic
- 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.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to an image enhancement and identification method applied to box panoramic detection. The method comprises the steps of obtaining a local gray index according to gray levels in a preset neighborhood of pixel points in a panoramic image, obtaining a spatial distribution index based on the gray levels of the pixel points at the edge of a scale window, obtaining a structural distribution index according to the gray values of the pixel points in the preset neighborhood of the pixel points, and obtaining a characteristic index by combining the three indexes; and enhancing the panoramic image based on the characteristic indexes to obtain a panoramic enhanced image, acquiring characteristic similarity according to the gray value and the gray entropy of pixel points in a super pixel block in the panoramic enhanced image, and dividing the panoramic enhanced image into areas according to the characteristic similarity. The method analyzes the characteristic information of the pixel points from the aspects of gray level distribution, spatial distribution and structural distribution to obtain the characteristic indexes of the pixel points, and performs self-adaptive enhancement processing on the panoramic image based on the characteristic indexes, thereby improving the enhancement effect of the panoramic image.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an image enhancement and identification method applied to box panoramic detection.
Background
When the box is detected based on the image, in order to improve the box condition detection precision and improve the accuracy of effective information in the image, the image is generally enhanced before the detection based on the image, and improper enhancement processing easily causes the problems of poor enhancement effect of image edge detail information, loss of image detail information and the like.
When an image is enhanced, an appropriate enhancement method can improve the contrast of the image and better store detail information in the image, and the existing image enhancement method comprises the following steps: obtaining fuzzy images with different fuzzy degrees in different scale spaces by carrying out scale transformation on an original RGB image, calculating the weight of each fuzzy image in different scale spaces, obtaining the local feature and the global feature of each fuzzy image and carrying out fusion to obtain a feature matrix corresponding to each fuzzy image, carrying out fusion on each feature matrix through the weight to obtain a fusion feature matrix of the original RGB image, extracting each key point in the original RGB image, taking the information entropy of pixel points in the neighborhood range of the key point as the key point weight of each key point, and enhancing the key point according to the key point weight and the fusion feature matrix to further obtain an enhanced image corresponding to the original RGB image; the method directly strengthens the corresponding key points according to the weight of the key points, does not consider the gray distribution, the spatial distribution and the structural distribution of each pixel point in a specific image, and can not effectively ensure the accuracy of the weight of the key points representing the strengthening indexes, so that the method for realizing accurate image strengthening and identification by applying to the panoramic detection of the box body is needed.
Disclosure of Invention
In order to solve the problem that the conventional image enhancement method cannot sufficiently analyze each pixel point of an image, so that the enhancement index is inaccurate, and the image enhancement effect is poor, the invention aims to provide an image enhancement and identification method applied to box panoramic detection, and the adopted technical scheme is as follows:
the invention provides an image enhancement and identification method applied to box panoramic detection, which comprises the following steps:
acquiring a panoramic image of the box body;
obtaining a local gray index of each pixel point according to the gray value distribution characteristics in the preset neighborhood range of each pixel point in the panoramic image; dividing at least two scale windows in a preset neighborhood range of each pixel point, and acquiring a spatial distribution index of a corresponding pixel point according to gray level distribution of pixel points at the edge of the scale window in each scale window; acquiring a structural distribution index of each pixel point based on the gray difference between each pixel point and a neighborhood pixel point in a preset neighborhood range;
combining the local gray index, the spatial distribution index and the structural distribution index to obtain a characteristic index of each pixel point; enhancing the panoramic image based on the characteristic indexes to obtain a panoramic enhanced image;
and dividing the panoramic enhanced image into at least two superpixel blocks, classifying the superpixel blocks according to the characteristic similarity of the gray distribution characteristics among the superpixel blocks, and identifying each subarea according to the classification result.
Further, the method for obtaining the spatial distribution index includes:
for any gray level in a preset neighborhood range of each pixel point, respectively counting the number of edge pixel points corresponding to the gray level in each scale window as a first number, and counting the number of pixel points corresponding to the gray level in the preset neighborhood range as a second number; taking the ratio of the first number to the second number as the occurrence probability of the gray level in each scale window; regarding any scale window of the gray level, taking the logarithm of the occurrence probability with a natural constant e as a base number as a first logarithm value, and taking the product of the occurrence probability and the first logarithm value as a second logarithm value; taking the opposite number of the sum of the second logarithm values corresponding to all the scale windows as the gray level distribution index of the gray level; and taking the sum of the gray level distribution indexes of each gray level in the preset neighborhood range of each pixel point as the spatial distribution index of the corresponding pixel point.
Further, the method for acquiring the structural distribution index includes:
respectively obtaining the gray difference between each pixel point and each corresponding neighborhood pixel point, taking the square of each gray difference as a first difference value, calculating the evolution of the mean value of the first difference values as a second difference value, and taking the mean value of the second difference values of all the pixel points in the preset neighborhood range of each pixel point as the structural distribution index of the corresponding pixel point.
Further, the method for acquiring the characteristic index includes:
taking a value obtained by setting a first constant as a base number and a spatial distribution index as an index as a first result; taking the local gray index as a numerator, and taking a ratio obtained by taking the first result as a denominator as a second result; and taking the product of the structural distribution index and the second result as the characteristic index of the pixel point.
Further, the method for enhancing the panoramic image based on the characteristic index to obtain the panoramic enhanced image includes:
normalizing the characteristic index of each pixel point in the panoramic image to obtain a normalized characteristic index corresponding to each pixel point;
setting a first threshold and a second threshold, enabling the first threshold to be smaller than the second threshold, and taking the product of the gray value of the pixel and the normalized characteristic index as the enhanced gray value of the corresponding pixel when the normalized characteristic index of the pixel is smaller than or equal to the first threshold;
when the normalized characteristic index of the pixel point is larger than the first threshold and smaller than the second threshold, the gray value of the corresponding pixel point is kept unchanged;
when the normalized characteristic index of the pixel point is larger than or equal to the second threshold, calculating and setting the sum of a second constant and the normalized characteristic index as a third result, and taking the product of the gray value of the pixel point and the third result as the enhanced gray value of the corresponding pixel point;
and the image formed by the enhanced gray value of each pixel point in the panoramic image is a panoramic enhanced image.
Further, the method for acquiring the gray distribution characteristics includes:
for any superpixel block, filtering the superpixel block to obtain a texture extraction gray image, and acquiring the image entropy of the texture extraction gray image;
for any super-pixel block, a Gaussian model is constructed according to the gray values of the pixel points in the super-pixel block, the mean value and the variance of the Gaussian model are obtained, the gray entropy and the mean value and the variance of the Gaussian model are combined to form a feature vector of the super-pixel block, and the feature vector is used as the gray distribution feature.
Further, the method for acquiring feature similarity includes:
and calculating Euclidean distance between the gray level distribution characteristics of any two superpixel blocks as characteristic distance, and taking the result obtained by carrying out negative correlation mapping on the characteristic distance as the characteristic similarity between the two corresponding superpixel blocks.
Further, the method of classifying superpixels based on feature similarity of gray distribution features between superpixels, comprising:
and setting an aggregation threshold, and classifying the two super-pixel blocks into a category to obtain at least two categories when the characteristic similarity between the two super-pixel blocks is greater than the aggregation threshold, wherein each category corresponds to a sub-region.
Further, the method for acquiring the local gray scale index includes:
and counting the gray levels of the pixels in the preset neighborhood range of each pixel, calculating an information entropy based on each gray level in the preset neighborhood range, and taking the information entropy as a local gray index of the corresponding pixel.
The invention has the following beneficial effects:
in the embodiment of the invention, in the process of acquiring the characteristic index of each pixel point in the panoramic image, each pixel point in the preset neighborhood range of each pixel point is analyzed in detail from three aspects of gray level distribution, space distribution and structure distribution, so that the accuracy of the characteristic index of each pixel point is effectively improved; because the relevance between each pixel point and the corresponding pixel point in the preset neighborhood range of the set size of the pixel point is larger, the information of the corresponding pixel point can be well represented, when the characteristic index of the pixel point is obtained, each pixel point in the preset neighborhood range of the pixel point is taken as a target for analysis, the local gray index representing the disordered gray distribution degree of each pixel point in the preset neighborhood range of the pixel point is obtained by analyzing the gray distribution, the preset neighborhood range of the pixel point is divided into a plurality of scale windows with different scale spans, the spatial distribution of gray levels in each scale window can be accurately obtained, the spatial distribution index representing the aggregation degree of the spatial distribution of each gray level in the preset neighborhood range of the pixel point is further obtained, the structural distribution index representing the detail change of image information is obtained by analyzing the structural distribution, and the three aspects of the gray distribution, the spatial distribution and the structural distribution of the pixel point are sequentially analyzed, the enhancement degree required by each pixel point can be more accurately reflected by combining the characteristic indexes of the local distribution index, the spatial distribution index and the structural distribution index of the pixel point, the self-adaptive enhancement of panoramic images is realized on the basis of the characteristic indexes of different pixel points, and the panoramic image is completely enhanced effect is obtained by combining the enhancement operation, and the panoramic enhancement effect is obtained; the panoramic enhanced image is preliminarily divided into the plurality of superpixel blocks, so that the characteristic similarity of the superpixel blocks is acquired by finely dividing the panoramic enhanced image, the division of the panoramic enhanced image into areas is realized according to the characteristic similarity, and the accuracy of accurately identifying the panoramic image is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart illustrating steps of an image enhancement and identification method applied to panoramic detection of a box according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description, the structure, the features and the effects of an image enhancement and identification method applied to panoramic detection of a box according to the present invention will be provided with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the image enhancement and identification method applied to the panoramic detection of the box body in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of an image enhancement and identification method applied to box panoramic detection according to an embodiment of the present invention is shown, where the method includes:
step S1: and acquiring a panoramic image of the box body.
And acquiring the panoramic image of the box body through image acquisition equipment of the panoramic detection system to obtain the panoramic image. In order to avoid the influence of noise data on the quality of the panoramic image, filtering operation is carried out on the panoramic image through a Gaussian filtering algorithm, so that the purpose of reducing noise in the panoramic image is achieved, and the influence of the noise data on effective information in the panoramic image is prevented. The gaussian filtering algorithm is a known technique, and the specific method is not described herein.
It should be noted that, in order to facilitate analysis of subsequent algorithms, the panoramic image is obtained and then converted into a grayscale image in the embodiment of the present invention, and the grayscale image conversion method is a technical means well known to those skilled in the art and is not described herein again.
Step S2: obtaining a local gray index of each pixel point according to the gray value distribution characteristics of each pixel point in the panoramic image within the preset neighborhood range; dividing at least two scale windows in a preset neighborhood range of each pixel point, and acquiring a spatial distribution index of a corresponding pixel point according to gray level distribution of pixel points at the edge of the scale window in each scale window; and acquiring the structural distribution index of each pixel point based on the gray difference between each pixel point and the adjacent pixel point in the preset adjacent range.
In order to obtain the characteristic information of each pixel point in the panoramic image, the pixel points are sequentially analyzed from three aspects of gray distribution, spatial distribution and structural distribution, and the local gray index, the spatial distribution index and the structural distribution index of each pixel point are sequentially obtained, wherein the specific method for obtaining the three indexes comprises the following steps:
(1) And analyzing from the aspect of gray distribution to obtain the local gray index of the pixel point. The gray level of each pixel point in the preset neighborhood range of the pixel point is analyzed, and the local gray level index for representing the information amount in the preset neighborhood range of the pixel point and the disordered gray level distribution degree of the pixel point is obtained according to the number of the pixel points corresponding to each gray level in the preset neighborhood range. The calculation method of the local gray index of the pixel point comprises the following steps: and counting the gray levels of the pixels in the preset neighborhood range of each pixel, calculating an information entropy based on each gray level in the preset neighborhood range, and taking the information entropy as a local gray index of the corresponding pixel.
As an example, to improve the accuracy of feature analysis of a pixel, in the embodiment of the present invention, feature information of a pixel is extracted based on a preset neighborhood range, any one pixel is selected from a panoramic image, taking a pixel k as an example, and the pixel k is taken as a center point to obtain a set size of the pixel k
The preset neighborhood range of the pixel point k is obtained.
The size of the neighborhood range is preset in the embodiment of the invention
Experience 11
。
Counting the gray levels of the pixels in the preset neighborhood range of the pixel k, recording the total number of the gray levels as U, taking the gray level U of the pixels in the preset neighborhood range of the pixel k as an example, and taking the ratio of the number of the pixels corresponding to the gray level U in the preset neighborhood range to the total number of the pixels in the preset neighborhood range as the occurrence probability of the gray level U
Calculating the occurrence probability of each gray level in a preset neighborhood range of the pixel point k, taking the occurrence probability of each gray level in the preset neighborhood range as a parameter of an information entropy formula to obtain a local gray level index of the pixel point k, and then obtaining the local gray level index of the pixel point k
The calculation formula of (a) is as follows:
in the formula (I), the compound is shown in the specification,
is the local gray scale index of the pixel point k,
is the total number of gray levels of the pixel points within the preset neighborhood range of the pixel point k,
the occurrence probability of the gray level u in the preset neighborhood range of the pixel point k is obtained;
is a logarithmic function based on a constant 2.
It should be noted that the probability of occurrence
Is calculated byComprises the following steps: the ratio of the number of the pixels corresponding to the gray level u in the preset neighborhood range of the pixel point k to the total number of the pixels in the preset neighborhood range is used as the occurrence probability of the gray level u in the preset neighborhood range of the pixel point k
When the number of pixels corresponding to the gray level u in the preset neighborhood range of the pixel k is larger, the probability is increased
The larger the index is, the more the local gray scale index of the pixel point k is
The larger the area is, the more disordered the gray scale distribution in the preset neighborhood range of the pixel point k is, the larger the contained information amount is, and the more the enhancement processing needs to be performed on the pixel point k.
(2) Analyzing from the aspect of spatial distribution, and acquiring spatial distribution indexes of pixel points: for any gray level in a preset neighborhood range of each pixel point, respectively counting the number of edge pixel points corresponding to the gray level in each scale window as a first number, and counting the number of pixel points corresponding to the gray level in the preset neighborhood range as a second number; taking the ratio of the first number to the second number as the occurrence probability of the gray level in each scale window; regarding any scale window of the gray level, taking the logarithm of the occurrence probability with a natural constant e as a base number as a first logarithm value, and taking the product of the occurrence probability and the first logarithm value as a second logarithm value; taking the opposite number of the sum of the second logarithm values corresponding to all the scale windows as the gray level distribution index of the gray level; and taking the sum of the gray level distribution indexes of each gray level in the preset neighborhood range of each pixel point as the spatial distribution index of the corresponding pixel point.
As an example, from the aspect of visual characteristics, if the distribution of a certain gray level is more concentrated in the preset neighborhood range, the visual effect is larger, and therefore, the present invention extracts the spatial distribution index of the pixel points in the preset neighborhood range.
Let the size of pixel point k be
The preset neighborhood range of the pixel point k is divided into a plurality of scale spans, the number of the acquired scale windows is T, the number T of the scale windows in the invention is 5 of the experience value, the preset neighborhood range of the pixel point k can obtain 5 scale windows, the T-th scale window has a corresponding scale span,
then the size of the 5 scale windows is sequentially
And the 5 scale windows all take the pixel point k as a central point.
Taking the gray level u of the preset neighborhood range of the pixel point k as an example, counting the number of the pixel points corresponding to the gray level u in the tth scale window of the pixel point k
And counting the number of the pixel points corresponding to the gray level u in the preset neighborhood range of the pixel point k
Will be
Expressing the occurrence probability of the gray level u in the tth scale window of the pixel point k, obtaining the occurrence probability of the gray level u in each scale window of the pixel point k, and obtaining the gray level distribution index of the gray level u by taking the occurrence probability of the gray level u in each scale window of the pixel point k as a parameter.
The gray level distribution index of the gray level u in the preset neighborhood range of the pixel point k
The calculation formula of (c) is as follows:
in the formula (I), the compound is shown in the specification,
is a gray level distribution index of the gray level u in the preset neighborhood range of the pixel point k,
the number of scale windows in the preset neighborhood range of the pixel point k,
the number of pixels corresponding to the gray level u in the t-th scale window of the pixel k,
the number of the pixel points corresponding to the gray level u in the preset neighborhood range of the pixel point k is obtained;
is a logarithmic function with the natural constant e as the base.
It should be noted that, in the following description,
the method for calculating the occurrence probability of the gray level u in the tth scale window of the pixel point k comprises the following steps: the number of pixel points corresponding to the gray level u in the tth scale window of the pixel point k
The number of pixel points corresponding to the gray level u in the preset neighborhood range
When the number of pixels corresponding to the gray level in each scale window of the pixel k is larger, the probability is increased
The larger the gray level distribution index of the gray level u in the preset neighborhood range of the pixel point k is, the larger the gray level distribution index of the gray level u is
The larger the gray level u is, the more scattered the distribution of the gray level u in the preset neighborhood range is; when the gray level of the gray level u in the preset neighborhood range of the pixel point kDistribution index
The larger the gray level u is, the higher the aggregation degree of the spatial distribution of the gray level u in the preset neighborhood range is, the larger the visual influence is, and the higher the saliency is.
Obtaining the space distribution index of the pixel point k according to the gray level distribution index of each gray level in the preset neighborhood range of the pixel point k, namely respectively calculating the gray level distribution index of each gray level in the preset neighborhood range of the pixel point k
The sum of the gray level distribution indexes of all gray levels in the preset neighborhood range of the pixel point k is recorded as
Will be
As the spatial distribution index of the pixel point k.
(3) Analyzing from the aspect of structure distribution, and acquiring the structure distribution index of the pixel points: respectively obtaining the gray difference between each pixel point and each corresponding neighborhood pixel point, taking the square of each gray difference as a first difference value, calculating the evolution of the mean value of the first difference values as a second difference value, and taking the mean value of the second difference values of all the pixel points in the preset neighborhood range of each pixel point as the structural distribution index of the corresponding pixel point.
As an example, to further improve the extraction accuracy of the pixel point features, a structural distribution index representing the local detail change condition of the pixel point is obtained based on the gray value of the neighborhood pixel point of each pixel point in the preset neighborhood range.
Taking any pixel point in the preset neighborhood range of the pixel point k, taking the pixel point c as an example, respectively obtaining the gray difference between each four-neighborhood pixel point of the pixel point c and the pixel point c, and sequentially recording the gray difference as
Wherein, in the step (A),
is the first gray scale difference between the pixel point of the first four neighboring domains of the pixel point c and the pixel point c,
is the second gray scale difference between the pixel point of the second four-adjacent domain of the pixel point c and the pixel point c,
is the third gray scale difference between the third four-adjacent domain pixel point of the pixel point c and the pixel point c,
a fourth gray scale difference value between a fourth adjacent domain pixel point of the pixel point c and the pixel point c; according to the method for acquiring the first gray difference value, the second gray difference value, the third gray difference value and the fourth gray difference value of the pixel point c, the first gray difference value, the second gray difference value, the third gray difference value and the fourth gray difference value of each pixel point in the preset neighborhood range of the pixel point k are acquired, the first gray difference value, the second gray difference value, the third gray difference value and the fourth gray difference value of each pixel point in the preset neighborhood range of the pixel point k are combined to acquire the structural distribution index of the pixel point k, and then the structural distribution index of the pixel point k is acquired
The calculation formula of (a) is as follows:
in the formula (I), the compound is shown in the specification,
is the structural distribution index of the pixel point k,
is the first gray scale difference value of the pixel point c,
is the second gray scale difference value of the pixel point c,
is the third gray scale difference value of the pixel point c,
is the fourth gray scale difference value of the pixel point c,
is the size of pixel point k
The number of pixels in the preset neighborhood range.
It should be noted that, when the gray difference between each four-neighborhood pixel point of the pixel point c and the pixel point c in the preset neighborhood range of the pixel point k is larger, that is to say, the gray difference is larger
The larger the difference is, the more obvious the detail change at the pixel point c in the preset neighborhood range is, and the structural distribution index of the pixel point k is the second difference value of all the pixel points
The more the image detail information at the pixel point k is, the larger the structural distribution index of the pixel point k is.
And step S3: combining the local gray index, the spatial distribution index and the structural distribution index to obtain a characteristic index of each pixel point; and enhancing the panoramic image based on the characteristic indexes to obtain a panoramic enhanced image.
The method and the device have the advantages that the characteristic indexes of each pixel point in the panoramic image are obtained by combining the local gray level indexes, the spatial distribution indexes and the structural distribution indexes of the pixel points, the corresponding pixel points are subjected to self-adaptive enhancement mainly based on the characteristic indexes of the pixel points, special enhancement is not needed for the areas which are distributed uniformly and contain less information, corresponding enhancement processing needs to be set for the areas which contain more image detail information, different enhancement processing effects of different pixel points are realized, and the enhancement effect of the panoramic image is further improved. The specific method of the characteristic index of the pixel point is as follows: taking a value obtained by setting a first constant as a base number and a spatial distribution index as an index as a first result; taking the local gray index as a numerator, and taking a ratio obtained by taking the first result as a denominator as a second result; and taking the product of the structural distribution index and the second result as the characteristic index of the pixel point.
As an example, the local gray level indexes of the pixel points k are obtained by the above method respectively
Index of spatial distribution
And structural distribution index
Based on the three indexes of the pixel point k, the characteristic index representing the characteristic significance of the pixel point k is obtained, and then the characteristic index of the pixel point k
The calculation formula of (a) is as follows:
in the formula (I), the compound is shown in the specification,
is a characteristic index of the pixel point k,
is a local gray scale index of the pixel point k,
is the index of the spatial distribution of the pixel point k,
the structural distribution index of the pixel point k is obtained;
to make the natural constantThe number e is an exponential function of the base number.
It should be noted that, when the local gray level index of the pixel point k
The larger the gray scale distribution is, the more uneven the gray scale distribution in the preset neighborhood range of the pixel point k is, the larger the information content contained in the pixel point k is, the more the enhancement processing needs to be carried out on the pixel point k, and the larger the characteristic index of the pixel point k is; space distribution index of pixel point k
The smaller the gray level of the pixel point k is, the higher the aggregation degree of the spatial distribution of the gray level of the pixel point k in a preset neighborhood range is, the larger the visual influence is, the larger the enhancement degree of the pixel point k needs to be, and the larger the characteristic index of the pixel point k is; when the structural distribution index of the pixel point k
The larger the size is, the more obvious the detail change of each pixel point in the preset neighborhood range representing the pixel point k is, so that the more the image detail information of the pixel point k is, the more important the pixel point k is, the more the pixel point k needs to be enhanced, and the larger the characteristic index of the pixel point k is.
The characteristics of each pixel point in the panoramic image can be analyzed based on the characteristic indexes, the pixel points with large information content and high importance degree are remarkably processed, and the pixel points with larger characteristic indexes are enhanced; and for the pixel points with smaller characteristic indexes and lower importance degrees, the gray value of the pixel point is restrained to improve the contrast of the panoramic image and realize the self-adaptive enhancement effect of the panoramic image.
The method for enhancing the panoramic image based on the characteristic indexes to obtain the panoramic enhanced image comprises the following steps: normalizing the characteristic index of each pixel point in the panoramic image to obtain a normalized characteristic index corresponding to each pixel point; setting a first threshold and a second threshold, enabling the first threshold to be smaller than the second threshold, and taking the product of the gray value of the pixel and the normalized characteristic index as the enhanced gray value of the corresponding pixel when the normalized characteristic index of the pixel is smaller than or equal to the first threshold; when the normalized characteristic index of the pixel point is larger than the first threshold and smaller than the second threshold, the gray value of the corresponding pixel point is kept unchanged; when the normalized characteristic index of the pixel point is larger than or equal to the second threshold, calculating and setting the sum of a second constant and the normalized characteristic index as a third result, and taking the product of the gray value of the pixel point and the third result as the enhanced gray value of the corresponding pixel point; and the image formed by the enhanced gray value of each pixel point in the panoramic image is a panoramic enhanced image.
As an example, the characteristic index of each pixel point in the panoramic image is obtained, normalization processing is performed on the characteristic index of the pixel point to facilitate subsequent visual analysis, the normalization characteristic index corresponding to each pixel point is obtained, and it is ensured that the normalization characteristic index of each pixel point is located
. Then, the process of adaptively enhancing each pixel point in the panoramic image is as follows:
in the formula (I), the compound is shown in the specification,
is a coordinate of
The pixel point of (1) is subjected to gray value before self-adaptive enhancement,
is a coordinate of
The pixel points are subjected to self-adaptive enhancement to enhance the gray value,
is a coordinate of
Normalizing characteristic indexes of the pixel points;
taking a passing experience value of 0.3 as a first threshold value;
the second threshold value is 0.6.
It should be noted that when the coordinates are
Normalized characteristic index of pixel point
The smaller the value is, the lower the importance degree of the pixel point is, in order to improve the contrast of the image, the gray value of the pixel point needs to be restrained, and the smaller the enhanced gray value of the pixel point after self-adaptive enhancement is; when the coordinates are
Normalized characteristic index of pixel point
The larger the gray value is, the higher the importance degree of the pixel point is and the larger the amount of information contained in the pixel point is, and the gray value of the pixel point needs to be enhanced, so that the enhanced gray value of the pixel point after adaptive enhancement is larger.
By the method, each pixel point of the panoramic image is subjected to self-adaptive enhancement, the enhanced gray value of each pixel point after the self-adaptive enhancement processing is obtained, and an image formed by the enhanced gray value of each pixel point in the panoramic image is used as the panoramic enhanced image.
And step S4: and dividing the panoramic enhancement image into at least two super-pixel blocks, classifying the super-pixel blocks according to the characteristic similarity of the gray distribution characteristics among the super-pixel blocks, and identifying each sub-area according to the classification result.
The panoramic enhancement image after the self-adaptive enhancement processing increases the contrast of the image, improves the feature definition of each pixel point in the panoramic enhancement image, and is convenient for segmenting the panoramic enhancement image more accurately in the follow-up process.
Firstly, performing superpixel segmentation on a panoramic enhanced image preliminarily to obtain a plurality of superpixel blocks, segmenting the panoramic enhanced image so as to identify each region of the panoramic enhanced image and achieve the purpose of improving the segmentation precision of the panoramic enhanced image, and setting the number of the segmented superpixel blocks to be N.
The number N of superpixel blocks in the embodiment of the present invention takes the empirical value of 300.
It should be noted that, in the present invention, a super-pixel segmentation technique is selected to segment the panorama enhanced image, and a specific method is not described here and is a technical means well known to those skilled in the art.
Secondly, considering that the panoramic enhanced image can be more finely divided by setting a large number of super pixel blocks in the super pixel block dividing process, but the problem of excessive division exists, in order to improve the box dividing precision, the super pixel block obtained by preliminarily dividing the panoramic enhanced image by the super pixel blocks is further analyzed.
Taking any super-pixel block in the panoramic enhancement image, taking the super-pixel block n as an example, and constructing a Gaussian model based on the gray value of each pixel point in the super-pixel block n
Obtaining the Gaussian model corresponding to the super pixel block n
Mean value of
Sum variance
. It should be noted that the construction technique of the gaussian model is a well-known technique, and is not specifically described here.
In order to improve the dividing precision of the superpixel blocks, the characteristics of the superpixel blocks are further extracted, and the gray entropy of each superpixel block is obtained. The method for acquiring the gray distribution characteristics of the super pixel block comprises the following steps: for any super pixel block, filtering the super pixel block to obtain a texture extraction gray image, and acquiring the image entropy of the texture extraction gray image; for any super-pixel block, a Gaussian model is constructed according to the gray values of the pixel points in the super-pixel block, the mean value and the variance of the Gaussian model are obtained, the gray entropy and the mean value and the variance of the Gaussian model are combined to form a feature vector of the super-pixel block, and the feature vector is used as the gray distribution feature.
As an example, filtering processing is performed on the super pixel block n through a Gabor filter to obtain a texture extraction gray map corresponding to the super pixel block n, entropy of the corresponding texture extraction gray map is obtained through image entropy, and the corresponding entropy is used as gray entropy of the super pixel block n
(ii) a When the gray entropy of a super-pixel block n
The larger the texture distribution within a superpixel block n is indicated to be more cluttered; when the gray level entropy of a super-pixel block n
The smaller the texture distribution within a superpixel block n is indicated to be more uniform. Taking the sum of superpixels n as an example, the feature vector corresponding to the superpixel block is formed based on the mean and variance of the Gaussian model corresponding to the superpixel block and the image entropy, and then the feature vector of the superpixel block n is
I.e. the feature vector is
Is the gray scale distribution characteristic of the super pixel block n. It should be noted that the entropy of the image is a well-known technique and is not specifically described here.
And acquiring the characteristic similarity between the super pixel blocks based on the gray distribution characteristics of any two super pixel blocks. The method for acquiring the characteristic similarity among the super pixel blocks comprises the following steps: and calculating Euclidean distance between the gray level distribution characteristics of any two superpixel blocks as characteristic distance, and taking the result obtained by carrying out negative correlation mapping on the characteristic distance as the characteristic similarity between the two corresponding superpixel blocks.
As an example, any two super-pixel blocks in the panorama enhancement map are taken, and taking the super-pixel block n and the super-pixel block s as an example, the gray distribution characteristic of the super-pixel block n is obtained
And the gray distribution of the super pixel block s is characterized by
Calculating the gray distribution characteristics of the superpixel block n
With the gray distribution characteristic of the super-pixel block s
European distance between
. Taking integer 2 as a molecule, and taking natural constant e as a base number and Euclidean distance
The sum of the value obtained for the exponential function of the exponent and the integer 1 is taken as the denominator, and the resulting ratio is taken as the feature similarity between the superpixel block n and the superpixel block s
. Then the feature similarity between the superpixel block n and the superpixel block s
The calculation formula of (a) is as follows:
in the formula (I), the compound is shown in the specification,
for the feature similarity between the superpixel block n and the superpixel block s,
as feature vectors
And feature vector
European distance between
；
Is a natural constant.
It should be noted that when feature vectors
And feature vector
European distance between
The smaller, indicating a higher degree of similarity between superpixel block n and superpixel block s, the greater the feature similarity between superpixel block n and superpixel block s
The larger; when the feature vector
And feature vector
European distance between
The larger, meaning the greater the difference between a superpixel block n and a superpixel block s, the greater the feature similarity between superpixel block n and superpixel block s
The smaller; the value range of the characteristic similarity of any two super-pixel blocks is
。
And classifying the super-pixel blocks into categories based on the characteristic similarity between any two super-pixel blocks so as to realize the division of the panoramic enhanced image into regions. The specific method for classifying the superpixel blocks comprises the following steps: and setting an aggregation threshold, and classifying the two super-pixel blocks into a category to obtain at least two categories when the characteristic similarity between the two super-pixel blocks is greater than the aggregation threshold, wherein each category corresponds to a sub-region. The super-pixel blocks with higher similarity are classified into one category, so that the segmentation precision of the panoramic enhancement image can be improved, and the problem of excessive segmentation is effectively avoided.
In the embodiment of the invention, the aggregation threshold value is 0.75 empirically obtained.
And finishing the self-adaptive enhancement processing of the panoramic image, and segmenting the panoramic enhanced image obtained after the enhancement processing to accurately obtain each subarea of the panoramic enhanced image.
In summary, in the embodiment of the present invention, a local gray index is obtained according to the gray level of the pixel point in the preset neighborhood in the panoramic image, a spatial distribution index is obtained based on the gray level of the pixel point at the edge of the scale window, a structural distribution index is obtained according to the gray level of the pixel point in the preset neighborhood of the pixel point, and a characteristic index is obtained by combining these three indexes; and enhancing the panoramic image based on the characteristic indexes to obtain a panoramic enhanced image, acquiring characteristic similarity according to the gray value and the gray entropy of pixel points in a super pixel block in the panoramic enhanced image, and dividing the panoramic enhanced image into areas according to the characteristic similarity. The method analyzes the characteristic information of the pixel points from the aspects of gray level distribution, spatial distribution and structural distribution to obtain the characteristic indexes of the pixel points, and performs self-adaptive enhancement processing on the panoramic image based on the characteristic indexes, thereby improving the enhancement effect of the panoramic image.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that are within the spirit of the present invention are intended to be included therein.
Claims (9)
1. An image enhancement and identification method applied to box panoramic detection is characterized by comprising the following steps:
acquiring a panoramic image of the box body;
obtaining a local gray index of each pixel point according to the gray value distribution characteristics of each pixel point in the panoramic image within the preset neighborhood range; dividing at least two scale windows in a preset neighborhood range of each pixel point, and acquiring a spatial distribution index of the corresponding pixel point according to gray level distribution of the pixel point at the edge of the scale window in each scale window; acquiring a structural distribution index of each pixel point based on the gray difference between each pixel point and a neighborhood pixel point in a preset neighborhood range;
combining the local gray index, the spatial distribution index and the structural distribution index to obtain a characteristic index of each pixel point; enhancing the panoramic image based on the characteristic indexes to obtain a panoramic enhanced image;
and dividing the panoramic enhanced image into at least two superpixel blocks, classifying the superpixel blocks according to the characteristic similarity of the gray distribution characteristics among the superpixel blocks, and identifying each subarea according to the classification result.
2. The image enhancement and identification method applied to panoramic detection of the box body according to claim 1, wherein the method for acquiring the spatial distribution indexes comprises the following steps:
for any gray level in a preset neighborhood range of each pixel point, respectively counting the number of edge pixel points corresponding to the gray level in each scale window as a first number, and counting the number of pixel points corresponding to the gray level in the preset neighborhood range as a second number; taking the ratio of the first number to the second number as the occurrence probability of the gray level in each scale window; regarding any scale window of the gray level, taking the logarithm of the occurrence probability with a natural constant e as a base number as a first logarithm value, and taking the product of the occurrence probability and the first logarithm value as a second logarithm value; taking the opposite number of the sum of the second logarithm values corresponding to all the scale windows as the gray level distribution index of the gray level; and taking the sum of the gray level distribution indexes of each gray level in the preset neighborhood range of each pixel point as the spatial distribution index of the corresponding pixel point.
3. The image enhancement and identification method applied to box panoramic detection according to claim 1, wherein the method for acquiring the structure distribution index comprises the following steps:
respectively obtaining the gray difference between each pixel point and each corresponding neighborhood pixel point, taking the square of each gray difference as a first difference value, calculating the evolution of the mean value of the first difference values as a second difference value, and taking the mean value of the second difference values of all the pixel points in the preset neighborhood range of each pixel point as the structural distribution index of the corresponding pixel point.
4. The image enhancement and identification method applied to box panoramic detection according to claim 1, wherein the characteristic index acquisition method comprises the following steps:
taking a value obtained by setting a first constant as a base number and a spatial distribution index as an index as a first result; taking the local gray index as a numerator, and taking a ratio obtained by taking the first result as a denominator as a second result; and taking the product of the structural distribution index and the second result as the characteristic index of the pixel point.
5. The image enhancement and identification method applied to box panoramic detection according to claim 1, wherein the method for enhancing the panoramic image based on the characteristic index to obtain the panoramic enhanced image comprises the following steps:
normalizing the characteristic index of each pixel point in the panoramic image to obtain a normalized characteristic index corresponding to each pixel point;
setting a first threshold and a second threshold, enabling the first threshold to be smaller than the second threshold, and taking the product of the gray value of the pixel and the normalized characteristic index as the enhanced gray value of the corresponding pixel when the normalized characteristic index of the pixel is smaller than or equal to the first threshold;
when the normalized characteristic index of the pixel point is larger than the first threshold and smaller than the second threshold, the gray value of the corresponding pixel point is kept unchanged;
when the normalized characteristic index of the pixel point is larger than or equal to the second threshold, calculating and setting the sum of a second constant and the normalized characteristic index as a third result, and taking the product of the gray value of the pixel point and the third result as the enhanced gray value of the corresponding pixel point;
and the image formed by the enhanced gray value of each pixel point in the panoramic image is a panoramic enhanced image.
6. The image enhancement and identification method applied to box panoramic detection according to claim 1, wherein the method for acquiring the gray distribution features comprises the following steps:
for any superpixel block, filtering the superpixel block to obtain a texture extraction gray image, and acquiring the image entropy of the texture extraction gray image;
for any super-pixel block, a Gaussian model is constructed according to the gray values of the pixel points in the super-pixel block, the mean value and the variance of the Gaussian model are obtained, the gray entropy and the mean value and the variance of the Gaussian model are combined to form a feature vector of the super-pixel block, and the feature vector is used as the gray distribution feature.
7. The image enhancement and identification method applied to panoramic detection of the box body according to claim 6, wherein the characteristic similarity obtaining method comprises the following steps:
and calculating Euclidean distance between the gray distribution characteristics of any two superpixel blocks as characteristic distance, and taking the result obtained by carrying out negative correlation mapping on the characteristic distance as the characteristic similarity between the two corresponding superpixel blocks.
8. The image enhancement and identification method applied to box body panoramic detection according to claim 1, wherein the method for classifying the superpixel blocks according to the feature similarity of the gray distribution features among the superpixel blocks comprises the following steps:
and setting an aggregation threshold, and classifying the two super-pixel blocks into a category to obtain at least two categories when the characteristic similarity between the two super-pixel blocks is greater than the aggregation threshold, wherein each category corresponds to a sub-region.
9. The image enhancement and identification method applied to panoramic detection of the box body according to claim 1, wherein the method for acquiring the local gray index comprises the following steps:
and counting the gray levels of the pixels in the preset neighborhood range of each pixel, calculating an information entropy based on each gray level in the preset neighborhood range, and taking the information entropy as a local gray index of the corresponding pixel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310179040.6A CN115861135B (en) | 2023-03-01 | 2023-03-01 | Image enhancement and recognition method applied to panoramic detection of box body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310179040.6A CN115861135B (en) | 2023-03-01 | 2023-03-01 | Image enhancement and recognition method applied to panoramic detection of box body |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115861135A true CN115861135A (en) | 2023-03-28 |
| CN115861135B CN115861135B (en) | 2023-05-23 |
Family
ID=85659409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310179040.6A Active CN115861135B (en) | 2023-03-01 | 2023-03-01 | Image enhancement and recognition method applied to panoramic detection of box body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115861135B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109658A (en) * | 2023-04-07 | 2023-05-12 | 山东金大丰机械有限公司 | Harvester control data processing method based on 5G technology |
| CN116188465A (en) * | 2023-04-26 | 2023-05-30 | 济宁市保田农机技术推广专业合作社 | Crop growth state detection method based on image processing technology |
| CN116233479A (en) * | 2023-04-28 | 2023-06-06 | 中译文娱科技(青岛)有限公司 | Live broadcast information content auditing system and method based on data processing |
| CN116309609A (en) * | 2023-05-25 | 2023-06-23 | 山东曙岳车辆有限公司 | Intelligent detection method for welding corrugated plates of container door panels |
| CN116385436A (en) * | 2023-06-02 | 2023-07-04 | 胜利油田中心医院 | Cholelithiasis auxiliary detection system based on CT image |
| CN116452464A (en) * | 2023-06-09 | 2023-07-18 | 天津市肿瘤医院（天津医科大学肿瘤医院） | Chest image enhancement processing method based on deep learning |
| CN116342588B (en) * | 2023-05-22 | 2023-08-11 | 徕兄健康科技(威海)有限责任公司 | Cerebrovascular image enhancement method |
| CN116596806A (en) * | 2023-07-14 | 2023-08-15 | 山东绿洲智能科技有限公司 | Combined stacking regulation and control method for vision stacking robot |
| CN116665137A (en) * | 2023-08-01 | 2023-08-29 | 聊城市彩烁农业科技有限公司 | Livestock breeding wastewater treatment method based on machine vision |
| CN116704516A (en) * | 2023-08-07 | 2023-09-05 | 山东禾之源现代农业发展有限公司 | Visual inspection method for water-soluble fertilizer package |
| CN117036347A (en) * | 2023-10-08 | 2023-11-10 | 山东柯林瑞尔管道工程有限公司 | Visual detection method and system for pipeline lining leakage based on image enhancement |
| CN117115468A (en) * | 2023-10-19 | 2023-11-24 | 齐鲁工业大学(山东省科学院) | Image recognition method and system based on artificial intelligence |
| CN117409373A (en) * | 2023-12-14 | 2024-01-16 | 艾信智慧医疗科技发展（苏州）有限公司 | Medical logistics box full-period intelligent monitoring system |
| CN117455779A (en) * | 2023-12-22 | 2024-01-26 | 天津市胸科医院 | Auxiliary enhancement system of medical ultrasonic imaging instrument |
| CN117475157A (en) * | 2023-12-25 | 2024-01-30 | 浙江大学山东(临沂)现代农业研究院 | Agricultural planting enhancement monitoring method based on unmanned aerial vehicle remote sensing |
| CN117541484A (en) * | 2024-01-09 | 2024-02-09 | 巨野县龙祥面粉有限公司 | Image enhancement method for detecting bran star of flour |
| CN117689590A (en) * | 2024-01-31 | 2024-03-12 | 天津灵境智游科技有限公司 | AR object interactive display method based on AI technology |
| CN117745563A (en) * | 2024-02-21 | 2024-03-22 | 深圳市格瑞邦科技有限公司 | Dual-camera combined tablet personal computer enhanced display method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059870A (en) * | 2007-05-23 | 2007-10-24 | 华中科技大学 | Image cutting method based on attribute histogram |
| WO2017121018A1 (en) * | 2016-01-11 | 2017-07-20 | 中兴通讯股份有限公司 | Method and apparatus for processing two-dimensional code image, and terminal and storage medium |
| WO2018019282A1 (en) * | 2016-07-29 | 2018-02-01 | 腾讯科技（深圳）有限公司 | Binocular panorama image obtaining method and apparatus, and storage medium |
| CN107730530A (en) * | 2017-10-31 | 2018-02-23 | 西华大学 | A kind of remote emergency management control method based on smart city |
| CN108681737A (en) * | 2018-05-25 | 2018-10-19 | 长安大学 | A kind of complex illumination hypograph feature extracting method |
| CN115100201A (en) * | 2022-08-25 | 2022-09-23 | 淄博齐华制衣有限公司 | Blending defect detection method of flame-retardant fiber material |
| CN115170572A (en) * | 2022-09-08 | 2022-10-11 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
| CN115294338A (en) * | 2022-09-29 | 2022-11-04 | 中威泵业(江苏)有限公司 | Impeller surface defect identification method |
| CN115512231A (en) * | 2022-11-15 | 2022-12-23 | 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) | Remote sensing interpretation method suitable for homeland space ecological restoration |
-
2023
- 2023-03-01 CN CN202310179040.6A patent/CN115861135B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059870A (en) * | 2007-05-23 | 2007-10-24 | 华中科技大学 | Image cutting method based on attribute histogram |
| WO2017121018A1 (en) * | 2016-01-11 | 2017-07-20 | 中兴通讯股份有限公司 | Method and apparatus for processing two-dimensional code image, and terminal and storage medium |
| WO2018019282A1 (en) * | 2016-07-29 | 2018-02-01 | 腾讯科技（深圳）有限公司 | Binocular panorama image obtaining method and apparatus, and storage medium |
| CN107730530A (en) * | 2017-10-31 | 2018-02-23 | 西华大学 | A kind of remote emergency management control method based on smart city |
| CN108681737A (en) * | 2018-05-25 | 2018-10-19 | 长安大学 | A kind of complex illumination hypograph feature extracting method |
| CN115100201A (en) * | 2022-08-25 | 2022-09-23 | 淄博齐华制衣有限公司 | Blending defect detection method of flame-retardant fiber material |
| CN115170572A (en) * | 2022-09-08 | 2022-10-11 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
| CN115294338A (en) * | 2022-09-29 | 2022-11-04 | 中威泵业(江苏)有限公司 | Impeller surface defect identification method |
| CN115512231A (en) * | 2022-11-15 | 2022-12-23 | 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) | Remote sensing interpretation method suitable for homeland space ecological restoration |
Non-Patent Citations (4)
| Title |
|---|
| RAMAN MAINI AND HIMANSHU AGGARWAL: "A Comprehensive Review of Image Enhancement Techniques", 《JOURNAL OF COMPUTING》 * |
| ZHENHUA GUO ET AL.: "ROTATION INVARIANT TEXTURE CLASSIFICATION USING ADAPTIVE LBP WITH DIRECTIONAL STATISTICAL FEATURES", 《 2010 IEEE 17TH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING》 * |
| 耿喆: "超声C扫描系统成像质量评价方法研究", 《中国优秀硕士学位论文全文数据库 基础科学辑 》 * |
| 邬锋: "铁轨表面缺陷检测算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109658A (en) * | 2023-04-07 | 2023-05-12 | 山东金大丰机械有限公司 | Harvester control data processing method based on 5G technology |
| CN116188465A (en) * | 2023-04-26 | 2023-05-30 | 济宁市保田农机技术推广专业合作社 | Crop growth state detection method based on image processing technology |
| CN116188465B (en) * | 2023-04-26 | 2023-07-04 | 济宁市保田农机技术推广专业合作社 | Crop growth state detection method based on image processing technology |
| CN116233479B (en) * | 2023-04-28 | 2023-07-21 | 中译文娱科技(青岛)有限公司 | Live broadcast information content auditing system and method based on data processing |
| CN116233479A (en) * | 2023-04-28 | 2023-06-06 | 中译文娱科技(青岛)有限公司 | Live broadcast information content auditing system and method based on data processing |
| CN116342588B (en) * | 2023-05-22 | 2023-08-11 | 徕兄健康科技(威海)有限责任公司 | Cerebrovascular image enhancement method |
| CN116309609A (en) * | 2023-05-25 | 2023-06-23 | 山东曙岳车辆有限公司 | Intelligent detection method for welding corrugated plates of container door panels |
| CN116309609B (en) * | 2023-05-25 | 2023-08-04 | 山东曙岳车辆有限公司 | Intelligent detection method for welding corrugated plates of container door panels |
| CN116385436A (en) * | 2023-06-02 | 2023-07-04 | 胜利油田中心医院 | Cholelithiasis auxiliary detection system based on CT image |
| CN116385436B (en) * | 2023-06-02 | 2023-08-15 | 胜利油田中心医院 | Cholelithiasis auxiliary detection system based on CT image |
| CN116452464A (en) * | 2023-06-09 | 2023-07-18 | 天津市肿瘤医院（天津医科大学肿瘤医院） | Chest image enhancement processing method based on deep learning |
| CN116452464B (en) * | 2023-06-09 | 2023-08-22 | 天津市肿瘤医院（天津医科大学肿瘤医院） | Chest image enhancement processing method based on deep learning |
| CN116596806A (en) * | 2023-07-14 | 2023-08-15 | 山东绿洲智能科技有限公司 | Combined stacking regulation and control method for vision stacking robot |
| CN116596806B (en) * | 2023-07-14 | 2023-09-19 | 山东绿洲智能科技有限公司 | Combined stacking regulation and control method for vision stacking robot |
| CN116665137B (en) * | 2023-08-01 | 2023-10-10 | 聊城市彩烁农业科技有限公司 | Livestock breeding wastewater treatment method based on machine vision |
| CN116665137A (en) * | 2023-08-01 | 2023-08-29 | 聊城市彩烁农业科技有限公司 | Livestock breeding wastewater treatment method based on machine vision |
| CN116704516B (en) * | 2023-08-07 | 2023-10-24 | 山东禾之源现代农业发展有限公司 | Visual inspection method for water-soluble fertilizer package |
| CN116704516A (en) * | 2023-08-07 | 2023-09-05 | 山东禾之源现代农业发展有限公司 | Visual inspection method for water-soluble fertilizer package |
| CN117036347A (en) * | 2023-10-08 | 2023-11-10 | 山东柯林瑞尔管道工程有限公司 | Visual detection method and system for pipeline lining leakage based on image enhancement |
| CN117036347B (en) * | 2023-10-08 | 2024-02-02 | 山东柯林瑞尔管道工程有限公司 | Visual detection method and system for pipeline lining leakage based on image enhancement |
| CN117115468A (en) * | 2023-10-19 | 2023-11-24 | 齐鲁工业大学(山东省科学院) | Image recognition method and system based on artificial intelligence |
| CN117115468B (en) * | 2023-10-19 | 2024-01-26 | 齐鲁工业大学(山东省科学院) | Image recognition method and system based on artificial intelligence |
| CN117409373A (en) * | 2023-12-14 | 2024-01-16 | 艾信智慧医疗科技发展（苏州）有限公司 | Medical logistics box full-period intelligent monitoring system |
| CN117409373B (en) * | 2023-12-14 | 2024-02-09 | 艾信智慧医疗科技发展（苏州）有限公司 | Medical logistics box full-period intelligent monitoring system |
| CN117455779B (en) * | 2023-12-22 | 2024-03-26 | 天津市胸科医院 | Auxiliary enhancement system of medical ultrasonic imaging instrument |
| CN117455779A (en) * | 2023-12-22 | 2024-01-26 | 天津市胸科医院 | Auxiliary enhancement system of medical ultrasonic imaging instrument |
| CN117475157A (en) * | 2023-12-25 | 2024-01-30 | 浙江大学山东(临沂)现代农业研究院 | Agricultural planting enhancement monitoring method based on unmanned aerial vehicle remote sensing |
| CN117475157B (en) * | 2023-12-25 | 2024-03-15 | 浙江大学山东(临沂)现代农业研究院 | Agricultural planting enhancement monitoring method based on unmanned aerial vehicle remote sensing |
| CN117541484A (en) * | 2024-01-09 | 2024-02-09 | 巨野县龙祥面粉有限公司 | Image enhancement method for detecting bran star of flour |
| CN117541484B (en) * | 2024-01-09 | 2024-05-14 | 巨野县龙祥面粉有限公司 | Image enhancement method for detecting bran star of flour |
| CN117689590A (en) * | 2024-01-31 | 2024-03-12 | 天津灵境智游科技有限公司 | AR object interactive display method based on AI technology |
| CN117689590B (en) * | 2024-01-31 | 2024-04-16 | 天津灵境智游科技有限公司 | AR object interactive display method based on AI technology |
| CN117745563A (en) * | 2024-02-21 | 2024-03-22 | 深圳市格瑞邦科技有限公司 | Dual-camera combined tablet personal computer enhanced display method |
| CN117745563B (en) * | 2024-02-21 | 2024-05-14 | 深圳市格瑞邦科技有限公司 | Dual-camera combined tablet personal computer enhanced display method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115861135B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115861135B (en) | Image enhancement and recognition method applied to panoramic detection of box body | |
| CN109522908B (en) | Image significance detection method based on region label fusion | |
| CN111340824B (en) | Image feature segmentation method based on data mining | |
| WO2018103608A1 (en) | Text detection method, device and storage medium | |
| CN109711416B (en) | Target identification method and device, computer equipment and storage medium | |
| WO2006083023A1 (en) | Computer implemented method for extracting integral histogram from sampled data | |
| CN108829711B (en) | Image retrieval method based on multi-feature fusion | |
| CN111583279A (en) | Super-pixel image segmentation method based on PCBA | |
| CN109635733B (en) | Parking lot and vehicle target detection method based on visual saliency and queue correction | |
| CN113298809B (en) | Composite material ultrasonic image defect detection method based on deep learning and superpixel segmentation | |
| CN112749673A (en) | Method and device for intelligently extracting stock of oil storage tank based on remote sensing image | |
| CN112085126B (en) | Single sample target detection method focusing on classification task | |
| CN112926592A (en) | Trademark retrieval method and device based on improved Fast algorithm | |
| CN116932492B (en) | Storage optimization method for layout file identification data | |
| CN107704864B (en) | Salient object detection method based on image object semantic detection | |
| CN111127407B (en) | Fourier transform-based style migration forged image detection device and method | |
| Zhang et al. | Saliency detection via image sparse representation and color features combination | |
| Ghandour et al. | Building shadow detection based on multi-thresholding segmentation | |
| CN113744241A (en) | Cell image segmentation method based on improved SLIC algorithm | |
| CN114511862A (en) | Form identification method and device and electronic equipment | |
| CN110276260B (en) | Commodity detection method based on depth camera | |
| Tsai et al. | Real-time automatic multilevel color video thresholding using a novel class-variance criterion | |
| CN117935177B (en) | Road vehicle dangerous behavior identification method and system based on attention neural network | |
| CN110675372A (en) | Brain area automatic segmentation method and system of brain tissue three-dimensional image with horizontal cell resolution | |
| CN117558068B (en) | Intelligent device gesture recognition method based on multi-source data fusion |
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 |