CN115311375A - Compression storage and transmission method and system for data of check fabric - Google Patents
Compression storage and transmission method and system for data of check fabric Download PDFInfo
- Publication number
- CN115311375A CN115311375A CN202211235883.5A CN202211235883A CN115311375A CN 115311375 A CN115311375 A CN 115311375A CN 202211235883 A CN202211235883 A CN 202211235883A CN 115311375 A CN115311375 A CN 115311375A
- Authority
- CN
- China
- Prior art keywords
- image
- images
- degree
- category
- value
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a compression storage and transmission method and a system for checkered fabric data, wherein the method comprises the following steps: acquiring a gray level image of the check fabric, determining a value range of the number of clusters according to the number of maximum and minimum values in a gray level histogram of the image, and acquiring corresponding cluster segmentation images according to the number of different clusters; preprocessing the cluster segmentation images corresponding to different cluster numbers to obtain class images corresponding to various classes, and performing curve fitting according to gray value curves of uplink pixel points of the class images to obtain lines and curves; calculating the periodic degree of the category images according to the difference of derivative directions of adjacent points on the line and the curve; obtaining the optimal degree of the number of clusters corresponding to the image according to the cycle degree of all the class images corresponding to the cluster segmentation image; and acquiring the cluster segmentation image corresponding to the maximum value of the preference degree, and compressing, storing and transmitting the cluster segmentation image. The invention realizes the selection of the number of the self-adaptive clusters.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for compression storage and transmission of checkered fabric data.
Background
In order to reduce the memory space and improve the transmission efficiency, compression is usually adopted during image transmission, and the compression reduces the data size by improving the spatial redundancy so as to save the storage space and the transmission time. Most of the current compression methods are based on spatial redundancy, i.e. repeated data. Some areas in the image of the check fabric are consistent in pixels, but due to reasons such as real illumination and imaging, pixels are inconsistent, noise is brought to data compression, the degree of compression is reduced, and unnecessary storage space is increased.
In the prior art, the spatial redundancy degree is increased by changing the resolution, but the definition degree of an image can be reduced, or the image is processed by using a filtering and denoising method, but the filtering selectivity is more, different filtering has different effects, and the self-adaptive selection is difficult, so that the compression effect is influenced.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a method for compressing, storing and transmitting data of a checkered fabric, which adopts the following technical solutions:
acquiring a gray level image of the check fabric, counting a gray level histogram corresponding to the image, determining a value range of the number of clusters according to the number of maximum values and minimum values in the gray level histogram, and acquiring a corresponding cluster segmentation image according to the number of different clusters;
preprocessing the cluster segmentation images corresponding to different cluster numbers to obtain category images corresponding to various categories, and performing curve fitting according to the accumulated numerical value of gray values of uplink pixel points of the category images to obtain a line and a curve; calculating the periodic degree of the category images according to the difference of derivative directions of adjacent points on the line and the curve;
accumulating the periodic degrees of all the category images corresponding to the cluster segmentation images to obtain the optimal degree of the number of the clusters corresponding to the images; and acquiring a cluster segmentation image corresponding to the maximum value of the optimal degree, and compressing, storing and transmitting the cluster segmentation image.
Preferably, the determining the value range of the number of clusters according to the number of the maximum values and the minimum values in the gray level histogram specifically includes:
and recording the number of the maximum values as a, recording the number of the minimum values as b, calculating the sum of the number of the maximum values and the number of the minimum values as c = a + b, and then setting the numeric area of the cluster number as [ a, c ].
Preferably, the method for acquiring the category image corresponding to each category specifically includes:
the value of each cluster number K corresponds to a set of K categories, all pixel points belonging to the set of category 1 are marked as 1, other pixel points are marked as 0, a binary mask image is obtained, the binary mask image is multiplied by the original cluster segmentation image, a category image corresponding to the pixel point of the set of category 1 is obtained, and then all category images are obtained.
Preferably, before calculating the degree of periodicity of the category image according to the difference between the line and the derivative direction of the adjacent point on the curve, the method further comprises:
and calculating derivative values of all points on the line and curve, removing points without derivative values, and carrying out interval division on the line and curve after the points are removed to obtain each discontinuous interval.
Preferably, the degree of periodicity of the category images calculated from the difference in the derivative directions of the line and the adjacent points on the curve is specifically:
forming an angle sequence of derivative directions by the angles in the reciprocal directions of each point in each discontinuous interval on the line and curve, calculating the difference value of two adjacent elements in the sequence to obtain a difference value sequence, and calculating the variance of all the elements in the difference value sequence to obtain the abnormal degree of the discontinuous interval; and normalizing the abnormal degrees of all the discontinuous intervals corresponding to the category images and then accumulating to obtain the periodic degree of the category images.
The invention also provides a system for compressed storage and transmission of the data of the check fabric, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the steps of the method for compressed storage and transmission of the data of the check fabric when being executed by the processor.
The embodiment of the invention at least has the following beneficial effects:
according to the method, the number range of clusters is obtained by combining the color characteristics of the image of the check fabric, the optimal K value is obtained through the periodic characteristics of the check fabric, the defect that the K value needs to be manually preset in a clustering algorithm is overcome, the dependence on manual setting is reduced when the image is segmented by using the K-means clustering algorithm, and the selection of the self-adaptive K value is realized. The images after clustering and segmentation are carried out on the check fabric images according to the self-adaptive K value, so that unnecessary noise points generated in the transmission and acquisition processes are removed, the spatial redundancy of the images is improved, the compression degree of the images is improved, and the storage space or the transmission space is saved.
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 of a method for compression storage and transmission of data of a check fabric according to 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 will be given to a method and a system for compressing, storing and transmitting data of a check fabric according to the present invention, with reference to the accompanying drawings and preferred embodiments, and the detailed description thereof, the structure thereof, the features thereof and the effects thereof. 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 a method and a system for compression storage and transmission of the data of the check fabric provided by the invention in detail with reference to the accompanying drawings.
The main purposes of the invention are: for the image to be compressed, the invention combines the periodic characteristics of the check fabric to obtain the optimal cluster number, and the image is segmented according to the cluster number to be compressed.
The invention aims at the following scenes: the image needs to be compressed when being transmitted, the redundancy degree of the image is lower due to the characteristics and the color distribution rule of the check fabric image, the consumed space is larger when the image is directly compressed, the image is processed by utilizing a clustering segmentation method, and then the image is compressed, so that the storage space can be reduced.
Example 1:
referring to fig. 1, a flowchart of a method for compressed storage and transmission of data of a check fabric according to an embodiment of the present invention is shown, where the method includes the following steps:
the method comprises the steps of firstly, obtaining a gray level image of the check fabric, counting a gray level histogram corresponding to the image, determining a value range of the number of clusters according to the number of maximum and minimum values in the gray level histogram, and obtaining a corresponding cluster segmentation image according to the number of different clusters.
Specifically, a collecting device is arranged above the production line, and produced check fabric images are collected under the appropriate illumination condition. Firstly, carrying out graying processing on an acquired grid fabric image to obtain a corresponding grayscale image, namely converting the image into a binary image by an Otsu threshold method, setting the pixel point value of a background area at the moment to be 0, multiplying the obtained binary image with an original image, removing the background area of a production line to obtain a grid fabric area image, and carrying out weighted average graying processing on the grid fabric area image to obtain the grid fabric grayscale image.
It should be noted that, when clustering is performed on an image, when the value of the set number of clusters is too large, some unnecessary classes to be segmented are obtained, and when the value of the set number of clusters is too small, image quality is lost, and a large amount of information of the image is lost. Therefore, in order to analyze the clustering effect corresponding to the number of different clusters, the value of the number of clusters needs to be obtained first.
Meanwhile, the gray level histogram can reflect probability density information of image pixel points, and the value range of the cluster number can be roughly obtained according to the gray level histogram corresponding to the image. In order to determine under which condition the image segmentation is optimal, the range of the obtained cluster number needs to be traversed.
And counting a gray histogram corresponding to the gray image of the check fabric, wherein the gray histogram can represent probability density information of the image, and if the number of the gray pixel points in the image is more, the vertical coordinate value corresponding to the gray value in the gray histogram is larger. For the image of the check fabric, the image presents periodic arrangement, and the approximate color number range of the image can be obtained through the number of extreme points in the gray level histogram.
Before counting the gray level histogram of the image, the image needs to be smoothed to remove the influence of the maximum value and the minimum value, and further obtain the number of the maximum value and the number of the minimum value. And recording the number of the maximum values as a, recording the number of the minimum values as b, calculating the sum of the number of the maximum values and the number of the minimum values as c = a + b, wherein the value range of the number of the clusters is [ a, c ], and the value of the clusters is an integer. Traversing each numerical value in the value range, and respectively carrying out clustering segmentation processing on the images to obtain corresponding clustering segmentation images.
Preprocessing the cluster segmentation images corresponding to different cluster numbers to obtain class images corresponding to various classes, and performing curve fitting according to the numerical values of gray value accumulation of uplink pixel points of the class images to obtain lines and curves; the degree of periodicity of the class images is calculated from the difference in derivative direction of adjacent points on the line and curve.
First, it should be noted that, since the cluster division images with different cluster numbers are obtained, the corresponding optimal division cluster numbers are different for different corrugated fabrics. And analyzing each obtained clustering segmentation image, obtaining the optimization degree of each clustering segmentation image according to the periodicity of the check fabric image, and further obtaining the number of clusters corresponding to the optimal segmentation according to the optimization degree.
For the image obtained by segmentation, the ideal segmentation effect is to remove noise caused by imaging and transmission while retaining most information of the image. For the check fabric, if the number of clusters is small, most information of the image is lost, and if the number of clusters is large, noise points are increased, and the image quality is affected. Therefore, each clustering result needs to be analyzed, and the reasonable degree of the K value is further obtained according to the periodic characteristics of the check fabric, so that the optimal cluster number is obtained.
Because the grid-woven fabric has periodicity, the periodicity of the pixel points in each category can be obtained according to the position information of the pixel points in each category of image. Therefore, the cluster segmentation images corresponding to different cluster numbers need to be preprocessed to obtain corresponding class images. The value of each cluster number K corresponds to a set of K categories, all pixel points belonging to the set of category 1 are marked as 1, other pixel points are marked as 0 to obtain a binary mask image, the binary mask image is multiplied by the original cluster segmentation image to obtain a category image corresponding to the pixel point of the set of category 1, and the pixel points of all categories are traversed according to the method to obtain all category images.
Then, since the segmentation of each image category has different effects, it is necessary to analyze the periodicity of all the pixels in each image category. Specifically, for any category image, the gray values of the pixel points in each line of the category image are accumulated respectively, and curve fitting is performed according to the numerical values obtained through accumulation and the line number in the category image to obtain the line and curve of the category image.
The line and curve can reflect the position interval of the pixel points of the image, and the periodicity of the image can be obtained by analyzing the line and curve. Since the resulting rows and curves exhibit a periodic arrangement when the class of images achieves a more reasonable segmentation, the curves are smoother. When the image is not completely or excessively segmented, more noise points exist in each image category, which are reflected on the lines and the curves, and abrupt changes exist in the lines and the curves.
Since the derivative direction of each point on the line and curve shows a more smooth change when the segmentation is more complete in the class image, when the segmentation in the class image has noisy points or is incomplete, the derivative direction of each point on the line and curve has abrupt changes. The lines and curves of the obtained category images are recorded as
Calculating derivative value corresponding to each point on the curve, recording the number of points where the derivative does not exist as N, firstly removing the influence of the points, and recording the line and curve without the points as
Since the points whose derivative is not 0 are distributed in a plurality of concentration at the edge portion of the lattice-woven-fabric region, the obtained curve
And obtaining the discontinuous areas on the line and the curve for a plurality of discontinuous intervals.
Obtaining reciprocal direction of each point in each discontinuous interval on the line and curve, the derivative direction of the first point is
Obtaining the included angle between the derivative direction and the abscissa axis as
Further obtain the angle corresponding to the derivative direction of each point on the curve
Value, all to be obtained
Angular sequence of values into derivative direction
In (1). For each interval of discontinuity, the angular sequence of derivative directions obtained
The angle difference of the derivative direction between the two points is small, which shows that the segmentation degree in the interval is good, and when the obtained angle sequence of the derivative direction is
When the angle difference of the derivative direction between the two points is large, the judgment of the influence of the noise point in the interval is shown.
Angle sequence for recording derivative direction
Is as follows
And the element in the difference sequence is the difference value of two adjacent elements in the angle sequence in the derivative direction, so as to calculate the abnormal degree of the discontinuous interval, and the abnormal degree is expressed by a formula as follows:
wherein the content of the first and second substances,
representing a sequence of pairs
The variance of the data in (1) is calculated to embody the sequence
The fluctuation degree of the value of the middle element can reflect the abnormal degree of the current discontinuous interval, if the segmentation effect is better, the data difference in the difference sequence is smaller, the fluctuation degree of the data in the sequence is smaller,
has small value, if the segmentation is poor, the discontinuous interval has noise, the data difference in the difference sequence is large, the fluctuation degree of the data in the sequence is large,
the value of (a) is large.
According to the method, the abnormal degree of each discontinuous area is further obtained, normalization operation is carried out on the abnormal degree corresponding to each discontinuous section, the periodic degree of each discontinuous section is obtained, and the periodic degree is expressed by a formula as follows:
wherein, the first and the second end of the pipe are connected with each other,
indicating the degree of periodicity of the m-th discontinuity interval,
indicates the degree of abnormality P corresponding to the m-th intermittent section,
indicates the maximum value of the degree of abnormality in all the intervals,
indicating the minimum value of the degree of abnormality in all the intervals. When the degree of abnormality of the intermittent section is larger,
the larger the value of the number of the terminal,
the smaller the value, the worse the degree of periodicity of the intermittent section, the worse the degree of division, and when the degree of abnormality of the intermittent section is smaller,
the smaller the value is,
the larger the interval, the better the degree of periodicity, and the better the degree of segmentation. And accumulating the periodic degrees of all the discontinuous areas corresponding to the category images to obtain the periodic degree of the category images.
Accumulating the periodic degrees of all the category images corresponding to the cluster segmentation images to obtain the optimal degree of the number of the clusters corresponding to the images; and acquiring the cluster segmentation image corresponding to the maximum value of the preference degree, and compressing, storing and transmitting the cluster segmentation image.
Specifically, in each category image, the lines and curves of all category images are obtained, the period degree corresponding to the category image is calculated, when the period degree of the category image is smaller than a threshold value, the category image is marked as a period image, and when the period degree of the category image is larger than the threshold value, the period image is marked as an abnormal image, and the processing result of each category image is obtained. Wherein, the value of the threshold value needs to be set by an implementer according to the actual situation.
For the value of each cluster number, the value corresponds to a cluster segmentation image, the cycle degrees of all the class images corresponding to the cluster segmentation image are accumulated to obtain the optimal degree of the cluster number corresponding to the image, and the optimal degree is expressed by a formula as follows:
wherein A represents the optimization degree corresponding to the value of the cluster number K,
and N represents the number of the class images of the cluster segmentation image corresponding to the cluster class number.
All the class images corresponding to the K valueAnd summing the degrees of periodicity to represent the reasonable degree corresponding to the value of K. When the segmentation degree corresponding to the K value is better, the preference degree of each image category under the K value is larger,
the larger the value. Conversely, the more preferable the image of each category at the K value is when the degree of segmentation in the graph is poor,
the smaller the value.
Further, a cluster segmentation image corresponding to the maximum value of the optimal degree is obtained, the segmentation degree of the image is optimal, the value of the number K of clusters corresponding to the cluster segmentation image is recorded as the optimal segmentation cluster number, and the segmentation image obtained by utilizing the optimal segmentation cluster number is recorded as an optimal segmentation result.
The cluster segmentation image of the optimal segmentation result is compressed by adopting a run length coding mode, when each row in the image has pixels with the same color, only the pixel value of one pixel and the number of pixels with the pixel value need to be stored, for example, if the pixel value of the row is 120, 120, 120, 130, 130, 130, the row can be compressed into (120,4) (130,3). And traversing all pixel points in the image, compressing the image to obtain a compressed checkered fabric image, and storing and transmitting the image.
Example 2:
the embodiment provides a system for compressed storage and transmission of the data of the check fabric, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program realizes the steps of a method for compressed storage and transmission of the data of the check fabric when being executed by the processor. Since embodiment 1 has already described a detailed method for compressing, storing and transmitting data of a check fabric, it is not described here too much.
The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; the modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application, and are included in the protection scope of the present application.
Claims (6)
1. A compression storage and transmission method for data of a check fabric is characterized by comprising the following steps:
acquiring a gray level image of the check fabric, counting a gray level histogram corresponding to the image, determining a value range of the number of clusters according to the number of maximum values and minimum values in the gray level histogram, and acquiring a corresponding cluster segmentation image according to the number of different clusters;
preprocessing the cluster segmentation images corresponding to different cluster numbers to obtain class images corresponding to various classes, and performing curve fitting according to the numerical values of gray value accumulation of uplink pixel points of the class images to obtain lines and curves; calculating the periodic degree of the category images according to the difference of derivative directions of adjacent points on the line and the curve;
accumulating the periodic degrees of all the category images corresponding to the cluster segmentation images to obtain the optimal degree of the number of the clusters corresponding to the images; and acquiring the cluster segmentation image corresponding to the maximum value of the preference degree, and compressing, storing and transmitting the cluster segmentation image.
2. The method for compression storage and transmission of the data of the check fabric according to claim 1, wherein the determining the value range of the number of the clusters according to the number of the maximum values and the minimum values in the gray histogram specifically comprises:
and recording the number of the maximum values as a, recording the number of the minimum values as b, calculating the sum of the number of the maximum values and the number of the minimum values as c = a + b, and then, the value range of the number of the clusters is [ a, c ].
3. The method for compressing, storing and transmitting the data of the check fabric according to claim 1, wherein the method for acquiring the class image corresponding to each class specifically comprises:
the value of each cluster number K corresponds to a set of K categories, all pixel points belonging to the set of category 1 are marked as 1, other pixel points are marked as 0, a binary mask image is obtained, the binary mask image is multiplied by the original cluster segmentation image, a category image corresponding to the pixel point of the set of category 1 is obtained, and then all category images are obtained.
4. The method as claimed in claim 1, wherein the step of calculating the degree of periodicity of the class image according to the difference between the line and the derivative direction of the adjacent point on the curve further comprises:
and calculating derivative values of all points on the line and curve, removing points without derivative values, and performing interval division on the line and curve after removing the points to obtain each discontinuous interval.
5. The method for compressed storage and transmission of the data of the check fabric according to claim 1, wherein the calculating the degree of periodicity of the category images according to the difference of the derivative directions of the line and the adjacent points on the curve specifically comprises:
forming an angle sequence of derivative directions by the angles in the reciprocal directions of each point in each discontinuous interval on the line and curve, calculating the difference value of two adjacent elements in the sequence to obtain a difference value sequence, and calculating the variance of all the elements in the difference value sequence to obtain the abnormal degree of the discontinuous interval; and normalizing the abnormal degrees of all the discontinuous intervals corresponding to the category images and then accumulating to obtain the periodic degree of the category images.
6. A system for compressed storage and transmission of data for a corrugated fabric, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program, when executed by the processor, implements the steps of a method for compressed storage and transmission of data for a corrugated fabric according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211235883.5A CN115311375B (en) | 2022-10-10 | 2022-10-10 | Compression storage and transmission method and system for data of check fabric |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211235883.5A CN115311375B (en) | 2022-10-10 | 2022-10-10 | Compression storage and transmission method and system for data of check fabric |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115311375A true CN115311375A (en) | 2022-11-08 |
| CN115311375B CN115311375B (en) | 2023-04-07 |
Family
ID=83868118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211235883.5A Active CN115311375B (en) | 2022-10-10 | 2022-10-10 | Compression storage and transmission method and system for data of check fabric |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115311375B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115802056A (en) * | 2023-01-31 | 2023-03-14 | 南通凯沃智能装备有限公司 | User data compression storage method for mobile terminal |
| CN115834895A (en) * | 2023-02-22 | 2023-03-21 | 创银科技(南通)有限公司 | Data efficient compression storage method for unmanned aerial vehicle |
| CN116503633A (en) * | 2023-07-03 | 2023-07-28 | 山东艾迈科思电气有限公司 | Intelligent detection control method for switch cabinet state based on image recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060171589A1 (en) * | 2005-01-11 | 2006-08-03 | Fujitsu Limited | Grayscale character dictionary generation apparatus |
| CN105354814A (en) * | 2015-08-17 | 2016-02-24 | 电子科技大学 | Infrared image segmentation method |
| CN114758185A (en) * | 2022-06-16 | 2022-07-15 | 南通倍佳机械科技有限公司 | Injection molding parameter control method and system based on gray level chromatic aberration |
-
2022
- 2022-10-10 CN CN202211235883.5A patent/CN115311375B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060171589A1 (en) * | 2005-01-11 | 2006-08-03 | Fujitsu Limited | Grayscale character dictionary generation apparatus |
| CN105354814A (en) * | 2015-08-17 | 2016-02-24 | 电子科技大学 | Infrared image segmentation method |
| CN114758185A (en) * | 2022-06-16 | 2022-07-15 | 南通倍佳机械科技有限公司 | Injection molding parameter control method and system based on gray level chromatic aberration |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115802056A (en) * | 2023-01-31 | 2023-03-14 | 南通凯沃智能装备有限公司 | User data compression storage method for mobile terminal |
| CN115834895A (en) * | 2023-02-22 | 2023-03-21 | 创银科技(南通)有限公司 | Data efficient compression storage method for unmanned aerial vehicle |
| CN115834895B (en) * | 2023-02-22 | 2023-12-15 | 上海每时每刻文化传播有限公司 | Efficient data compression and storage method for unmanned aerial vehicle |
| CN116503633A (en) * | 2023-07-03 | 2023-07-28 | 山东艾迈科思电气有限公司 | Intelligent detection control method for switch cabinet state based on image recognition |
| CN116503633B (en) * | 2023-07-03 | 2023-09-05 | 山东艾迈科思电气有限公司 | Intelligent detection control method for switch cabinet state based on image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115311375B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115311375B (en) | Compression storage and transmission method and system for data of check fabric | |
| US20060245499A1 (en) | Detection of artifacts resulting from image signal decompression | |
| CN116310360A (en) | Reactor surface defect detection method | |
| CN114926436A (en) | Defect detection method for periodic pattern fabric | |
| CN113808138A (en) | Artificial intelligence-based wire and cable surface defect detection method | |
| CN115661669B (en) | Method and system for monitoring illegal farmland occupancy based on video monitoring | |
| CN112232356A (en) | Event camera denoising method based on cluster degree and boundary characteristics | |
| US20080205786A1 (en) | Method and system for filtering images in video coding | |
| CN117291843B (en) | Efficient management method for image database | |
| CN111709964B (en) | PCBA target edge detection method | |
| CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
| CN114972575A (en) | Linear fitting algorithm based on contour edge | |
| CN117496359B (en) | Plant planting layout monitoring method and system based on three-dimensional point cloud | |
| CN114820625A (en) | Automobile top block defect detection method | |
| CN115439804A (en) | Monitoring method and device for high-speed rail maintenance | |
| CN110324617B (en) | Image processing method and device | |
| CN111738931A (en) | Shadow removal algorithm for aerial image of photovoltaic array unmanned aerial vehicle | |
| CN116563168A (en) | Geological mapping data real-time acquisition and storage method and system | |
| CN115994870B (en) | Image processing method for enhancing denoising | |
| CN111242051A (en) | Vehicle identification optimization method and device and storage medium | |
| CN117423113B (en) | Adaptive denoising method for archive OCR (optical character recognition) image | |
| CN117541582B (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN112614069B (en) | Face picture dimension reduction fuzzy preprocessing method | |
| CN117475157B (en) | Agricultural planting enhancement monitoring method based on unmanned aerial vehicle remote sensing | |
| CN117523502B (en) | Urban road rubbish intelligent monitoring system based on machine vision |
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 |