CN113554615B - Image refinement processing method and device, electronic equipment and storage medium - Google Patents
Image refinement processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113554615B CN113554615B CN202110827005.1A CN202110827005A CN113554615B CN 113554615 B CN113554615 B CN 113554615B CN 202110827005 A CN202110827005 A CN 202110827005A CN 113554615 B CN113554615 B CN 113554615B
- Authority
- CN
- China
- Prior art keywords
- image
- feature
- layers
- vector
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000012216 screening Methods 0.000 claims abstract description 13
- 230000010354 integration Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000001629 suppression Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000007670 refining Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 241001270131 Agaricus moelleri Species 0.000 claims 1
- 238000001914 filtration Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application provides an image refinement processing method, an image refinement processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: performing size adjustment and rasterization processing on each target image in an image library to obtain a first image; screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image; carrying out graying, color space standardization and color gradation treatment on the second image to obtain a third image; dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image; and if the combined vector is the same as the feature vector, outputting the target image. The application can improve the filtering precision of the target image and reduce the workload of image processing.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image refinement method, an image refinement device, an electronic device, and a storage medium.
Background
At present, image screening is a demanded technology, and specific images are searched in an image library according to characteristics, so that the searching time of a user is reduced, and the method is often applied to aspects of search engines, advertisement popularization and the like.
In the existing image refinement processing scheme, special filters, blurring operation and the like on the surface of an image bring inconvenience to the feature recognition of the image, and the retrieval precision of the feature image is not high. In addition, the number of data in the image library is large, which increases the workload of image processing.
Disclosure of Invention
Accordingly, an object of the present application is to provide an image refinement method, apparatus, electronic device, and storage medium, which can improve the filtering accuracy of a target image and reduce the workload of image processing.
In a first aspect, an embodiment of the present application provides an image refinement processing method, including:
performing size adjustment and rasterization processing on each target image in an image library to obtain a first image;
screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image;
carrying out graying, color space standardization and color gradation treatment on the second image to obtain a third image;
dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image;
and if the combined vector is the same as the feature vector, outputting the target image.
In one possible implementation manner, for each target image in the image library, the steps of resizing and rasterizing the target image to obtain a first image include:
for each target image in an image library, scaling the target image into a preset size range according to the preset size range;
and converting the format of the target image after scaling from a vector image to a grid image to obtain a first image.
In one possible implementation manner, the step of screening out layers that meet a preset feature condition from the layers of the first image, and integrating a plurality of layers to obtain a second image includes:
comparing a first aspect ratio of image features in each layer of the first image with a second aspect ratio of image features in the feature images, and obtaining confidence;
if the confidence coefficient exceeds a target confidence coefficient threshold value, deleting the layer;
and integrating the multiple layers of which the confidence coefficient does not exceed the target confidence coefficient threshold value to obtain a second image.
In one possible embodiment, the method further comprises:
training the confidence threshold based on a non-maximum suppression algorithm to obtain a target confidence threshold.
In one possible implementation manner, the step of performing graying, color space normalization and color gradation processing on the second image to obtain a third image includes:
carrying out graying treatment on the second image to obtain a gray scale image;
performing color space standardization processing on the gray level map to remove pixels with brightness lower than first brightness and pixels with brightness higher than second brightness in the gray level map, so as to obtain a standard map;
and carrying out gradation processing on the standard graph to obtain a third image.
In one possible implementation manner, the step of dividing the third image into a plurality of pixel grids, and comparing the combined vector obtained by combining the gray-scale data of the color levels in the plurality of pixel grids with the feature vector of the feature image includes:
dividing the third image into a plurality of square pixel grids;
acquiring gray level data of a color level in each square pixel grid;
combining the gray level data of the color gradation in the square pixel grids to obtain a combined vector;
and comparing the combined vector with the characteristic vector of the characteristic image.
In one possible implementation, the step of combining the gray-scale data of the color levels in the square pixel grids to obtain a combined vector includes:
counting the gradient histogram of each square pixel grid based on the gray level data of the color level of each square pixel grid to form a feature descriptor of each square pixel grid;
forming pixel blocks by square pixel grids with each preset number;
the feature descriptors of the preset number of square pixel grids in each pixel block are connected in series to obtain feature descriptors of each pixel block;
and (5) connecting the feature descriptors of all the pixel blocks in series to obtain a combined vector.
In one possible embodiment, the method further comprises:
storing a plurality of characteristic images containing characteristics as an image library;
the image library is updated based on an update operation.
In one possible embodiment, the method further comprises:
temporarily storing the image in the image refining process into a cache image library;
and deleting the temporarily stored images in the cache image library according to a preset period.
In a second aspect, an embodiment of the present application further provides an image refinement apparatus, including:
the preprocessing module is used for carrying out size adjustment and rasterization processing on each target image in the image library to obtain a first image;
the integration module is used for screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image;
the processing module is used for carrying out graying, color space standardization and color gradation processing on the second image to obtain a third image;
the contrast module is used for dividing the third image into a plurality of pixel grids, and comparing the combined vector obtained by combining the tone gray data in the pixel grids with the feature vector of the feature image;
and the output module is used for outputting the target image if the combined vector is the same as the characteristic vector.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any of the possible implementations of the first aspect.
In a fourth aspect, embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the first aspect, or any of the possible implementation manners of the first aspect.
According to the image refinement processing method provided by the embodiment of the application, firstly, for each target image in an image library, the size adjustment and rasterization processing are carried out on the target image to obtain a first image; screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image; therefore, the image layer which does not meet the preset characteristic conditions can be removed, the recognition difficulty brought by special filters, fuzzy operation and the like on the surface of the image for image recognition can be effectively reduced, and the work load of image processing is reduced. Then, carrying out graying, color space standardization and color gradation treatment on the second image to obtain a third image; therefore, the high-light and excessively dark pixels in the gray level image can be removed, and the image recognition difficulty can be effectively reduced. Finally, dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image; and if the combined vector is the same as the feature vector, outputting the target image. Thus, the third image is divided into a plurality of pixel grids to be processed respectively, so that the workload of image processing can be reduced. Therefore, the embodiment of the application can improve the filtering precision of the target image and reduce the workload of image processing.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a flowchart of an image refinement processing method provided by an embodiment of the present application;
fig. 2 is a schematic structural diagram of an image refinement device according to an embodiment of the present application;
fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for the purpose of illustration and description only and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to or removed from the flow diagrams by those skilled in the art under the direction of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the term "comprising" will be used in embodiments of the application to indicate the presence of the features stated hereafter, but not to exclude the addition of other features.
In the existing image refinement processing scheme, the inconvenience of feature recognition of the image is brought to special filters, blurring operation and the like on the surface of the image, and the retrieval precision of the feature image is not high. In addition, the number of data in the image library is large, which increases the workload of image processing. Based on the above, the embodiment of the application provides an image refinement processing method, an image refinement processing device, electronic equipment and a storage medium, and the description is given below through the embodiment.
For the sake of understanding the present embodiment, first, a detailed description is given of an image refinement processing method disclosed in the embodiment of the present application.
Referring to fig. 1, fig. 1 is a flowchart of an image refinement method according to an embodiment of the present application. As shown in fig. 1, the method may include the steps of:
s101, performing size adjustment and rasterization processing on each target image in an image library to obtain a first image;
s102, screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image;
s103, carrying out gray level processing, color space standardization and color gradation processing on the second image to obtain a third image;
s104, dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image;
s105, outputting the target image if the combined vector is the same as the feature vector.
In step S101, the target image is an image stored in the image library. In a specific implementation, storing a plurality of feature images containing features as an image library; the image library is updated based on an update operation. The first image is an image obtained by performing size adjustment and rasterization on the target image.
In the step, aiming at each target image in an image library, scaling the target image into a preset size range according to the preset size range; and converting the format of the target image after scaling from a vector image to a grid image to obtain a first image.
In step S102, deleting the layers that do not meet the preset feature condition, and reorganizing the layers that meet the preset feature condition to obtain a second image. Therefore, the image layer which does not meet the preset characteristic conditions can be removed, the recognition difficulty brought by special filters, fuzzy operation and the like on the surface of the image for image recognition can be effectively reduced, and the work load of image processing is reduced.
In the step, for each image layer of the first image, comparing a first aspect ratio of image features in the image layer with a two aspect ratio of image features in the feature image, and obtaining a confidence coefficient; if the confidence coefficient exceeds a target confidence coefficient threshold value, deleting the layer; and integrating the multiple layers of which the confidence coefficient does not exceed the target confidence coefficient threshold value to obtain a second image.
Wherein the confidence threshold is trained based on a Non-maximum suppression algorithm (Non-Maximum Suppression, NMS) to obtain a target confidence threshold.
In step S103, graying processing is performed on the second image, so as to obtain a gray scale image; performing color space standardization processing on the gray level map to remove pixels with brightness lower than first brightness and pixels with brightness higher than second brightness in the gray level map, so as to obtain a standard map; and carrying out gradation processing on the standard graph to obtain a third image. Therefore, the high-light and excessively dark pixels in the gray level image can be removed, and the image recognition difficulty can be effectively reduced.
The specific process of the color space standardization processing comprises the following steps: the gray level image is regarded as a three-dimensional image of (x, y, z), and the Gamma correction method is adopted to carry out the standardized processing of the color space on the gray level image, so that the contrast of the gray level image can be regulated, the influence caused by the local shadow and illumination change of the gray level image can be reduced, and the noise interference can be restrained.
In step S104, the feature image is an image to be retrieved, and the target image identical to the feature vector of the feature image is retrieved from the image library.
In this step, the third image is divided into a plurality of pixel grids, and the combination vector obtained by combining the gray-scale data of the color levels in the plurality of pixel grids is compared with the feature vector of the feature image. Thus, the third image is divided into a plurality of pixel grids to be processed respectively, so that the workload of image processing can be reduced.
Specifically, step S104 may include the following sub-steps:
s1041, dividing the third image into a plurality of square pixel grids;
s1042, obtaining the gray level data of the color level in each square pixel grid;
s1043, combining the gray level data of the color gradation in the square pixel grids to obtain a combined vector;
s1044, comparing the combined vector with the feature vector of the feature image.
In step S1041, the pixel grid is a square pixel grid. For example, the third image is divided into 6*6 square grids of pixels.
In step S1042, each square pixel is subjected to gray scale data processing, so as to obtain gray scale data of each square pixel.
In step S1043, the gradient histogram of each square pixel cell is counted based on the gray level data of each square pixel cell, and a feature descriptor (descriptor) of each square pixel cell is formed; in this way, profile information can be captured while further attenuating the disturbance of the illumination. Forming pixel blocks from square pixel grids of every preset number (for example, every 9); the feature descriptors of the preset number of square pixel grids in each pixel block are connected in series to obtain feature descriptors of each pixel block; and (3) connecting the feature descriptors of all the pixel blocks in series to obtain a combined vector for classification.
In one possible embodiment, the method further comprises: temporarily storing the image in the image refining process into a cache image library; and deleting the temporarily stored images in the cache image library according to a preset period.
According to the image refinement processing method provided by the embodiment of the application, firstly, for each target image in an image library, the size adjustment and rasterization processing are carried out on the target image to obtain a first image; screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image; therefore, the image layer which does not meet the preset characteristic conditions can be removed, the recognition difficulty brought by special filters, fuzzy operation and the like on the surface of the image for image recognition can be effectively reduced, and the work load of image processing is reduced. Then, carrying out graying, color space standardization and color gradation treatment on the second image to obtain a third image; therefore, the high-light and excessively dark pixels in the gray level image can be removed, and the image recognition difficulty can be effectively reduced. Finally, dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image; and if the combined vector is the same as the feature vector, outputting the target image. Thus, the third image is divided into a plurality of pixel grids to be processed respectively, so that the workload of image processing can be reduced. Therefore, the embodiment of the application can improve the filtering precision of the target image and reduce the workload of image processing.
Based on the same technical concept, the embodiment of the application also provides an image refinement processing device, an electronic device, a computer storage medium and the like, and particularly can be seen in the following embodiments.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an image refinement apparatus according to an embodiment of the present application. As shown in fig. 2, the apparatus may include:
the preprocessing module 10 is configured to perform size adjustment and rasterization processing on each target image in the image library, so as to obtain a first image;
the integration module 20 is configured to screen out layers satisfying a preset feature condition from each layer of the first image, and integrate a plurality of layers to obtain a second image;
a processing module 30, configured to perform graying, color space standardization and color gradation processing on the second image, so as to obtain a third image;
the comparison module 40 is configured to divide the third image into a plurality of pixel grids, and compare a combined vector obtained by combining the gray-scale data of the color levels in the plurality of pixel grids with a feature vector of the feature image;
and an output module 50, configured to output the target image if the combined vector is the same as the feature vector.
In one possible implementation, the preprocessing module 10 includes:
a scaling unit, configured to scale, for each target image in an image library, the target image to a preset size range according to the preset size range;
and the conversion unit is used for converting the format of the scaled target image from a vector image to a grid image to obtain a first image.
In one possible implementation, the integration module 20 includes:
the aspect ratio comparison unit is used for comparing the first aspect ratio of the image features in each image layer of the first image with the two aspect ratios of the image features in the feature images to obtain confidence;
the deleting unit is used for deleting the layer if the confidence coefficient exceeds a target confidence coefficient threshold value;
and the integration unit is used for integrating the plurality of layers of which the confidence coefficient does not exceed the target confidence coefficient threshold value to obtain a second image.
In one possible implementation, the integration module 20 further includes:
the training unit is used for training the confidence coefficient threshold value based on the non-maximum value suppression algorithm to obtain a target confidence coefficient threshold value.
In one possible implementation, the processing module 30 includes:
the graying unit is used for graying the second image to obtain a gray image;
the normalization unit is used for carrying out color space normalization processing on the gray level image so as to remove pixels with brightness lower than the first brightness and pixels with brightness higher than the second brightness in the gray level image, so as to obtain a standard image;
and the color gradation unit is used for performing color gradation processing on the standard graph to obtain a third image.
In one possible implementation, the comparison module 40 includes:
the dividing unit is used for dividing the third image into a plurality of square pixel grids;
an acquisition unit for acquiring gradation data of a tone in each square pixel cell;
the combining unit is used for combining the gray level data of the color levels in the square pixel grids to obtain a combined vector;
and the vector comparison unit is used for comparing the combined vector with the characteristic vector of the characteristic image.
In one possible embodiment, the combination unit is specifically configured to:
counting the gradient histogram of each square pixel grid based on the gray level data of the color level of each square pixel grid to form a feature descriptor of each square pixel grid;
forming pixel blocks by square pixel grids with each preset number;
the feature descriptors of the preset number of square pixel grids in each pixel block are connected in series to obtain feature descriptors of each pixel block;
and (5) connecting the feature descriptors of all the pixel blocks in series to obtain a combined vector.
In one possible implementation, the apparatus further includes an image library management module, the image library management module including:
the storage unit is used for storing a plurality of characteristic images containing characteristics as an image library;
and the updating unit is used for updating the image library based on the updating operation.
In one possible implementation manner, the apparatus further includes a cached image library management module, where the cached image library management module includes:
the temporary storage unit is used for temporarily storing the images in the image refining process into a cache image library;
and the image deleting unit is used for deleting the temporarily stored images in the cache image library according to a preset period.
The embodiment of the application discloses an electronic device, as shown in fig. 3, comprising: a processor 301, a memory 302 and a bus 303, the memory 302 storing machine readable instructions executable by the processor 301, the processor 301 and the memory 302 communicating via the bus 303 when the electronic device is running, the processor 301 executing the machine readable instructions performing the steps of:
performing size adjustment and rasterization processing on each target image in an image library to obtain a first image;
screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image;
carrying out graying, color space standardization and color gradation treatment on the second image to obtain a third image;
dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image;
and if the combined vector is the same as the feature vector, outputting the target image.
In one possible implementation, the step of performing, by the processor 301, for each target image in the image library, resizing and rasterizing the target image to obtain a first image includes:
for each target image in an image library, scaling the target image into a preset size range according to the preset size range;
and converting the format of the target image after scaling from a vector image to a grid image to obtain a first image.
In one possible implementation manner, the step of screening out the layers satisfying the preset feature condition from the layers of the first image by the processor 301 and integrating a plurality of the layers to obtain the second image includes:
comparing a first aspect ratio of image features in each layer of the first image with a second aspect ratio of image features in the feature images, and obtaining confidence;
if the confidence coefficient exceeds a target confidence coefficient threshold value, deleting the layer;
and integrating the multiple layers of which the confidence coefficient does not exceed the target confidence coefficient threshold value to obtain a second image.
In one possible implementation, the processor 301 is further configured to perform:
training the confidence threshold based on a non-maximum suppression algorithm to obtain a target confidence threshold.
In one possible implementation, the step of performing, by the processor 301, graying, color space normalization and color gradation processing on the second image to obtain a third image includes:
carrying out graying treatment on the second image to obtain a gray scale image;
performing color space standardization processing on the gray level map to remove pixels with brightness lower than first brightness and pixels with brightness higher than second brightness in the gray level map, so as to obtain a standard map;
and carrying out gradation processing on the standard graph to obtain a third image.
In one possible implementation, the step of dividing the third image into a plurality of pixel cells by the processor 301 and comparing the combined vector obtained by combining the gray-scale data of the gray levels in the plurality of pixel cells with the feature vector of the feature image includes:
dividing the third image into a plurality of square pixel grids;
acquiring gray level data of a color level in each square pixel grid;
combining the gray level data of the color gradation in the square pixel grids to obtain a combined vector;
and comparing the combined vector with the characteristic vector of the characteristic image.
In one possible implementation, the step of combining the gray scale data of the gray scale in the square pixel grids by the processor 301 to obtain a combined vector includes:
counting the gradient histogram of each square pixel grid based on the gray level data of the color level of each square pixel grid to form a feature descriptor of each square pixel grid;
forming pixel blocks by square pixel grids with each preset number;
the feature descriptors of the preset number of square pixel grids in each pixel block are connected in series to obtain feature descriptors of each pixel block;
and (5) connecting the feature descriptors of all the pixel blocks in series to obtain a combined vector.
In one possible implementation, the processor 301 is further configured to perform:
storing a plurality of characteristic images containing characteristics as an image library;
the image library is updated based on an update operation.
In one possible implementation, the processor 301 is further configured to perform:
temporarily storing the image in the image refining process into a cache image library;
and deleting the temporarily stored images in the cache image library according to a preset period.
The computer program product of the image refinement processing method provided by the embodiment of the application comprises a computer readable storage medium storing non-volatile program code executable by a processor, wherein the program code comprises instructions for executing the method described in the method embodiment, and specific implementation can be seen in the method embodiment and will not be repeated here.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the method embodiments, and are not repeated in the present disclosure. In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, and for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, indirect coupling or communication connection of devices or modules, electrical, mechanical, or other form.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (12)
1. An image refinement processing method, characterized by comprising the following steps:
performing size adjustment and rasterization processing on each target image in an image library to obtain a first image;
screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image;
carrying out graying, color space standardization and color gradation treatment on the second image to obtain a third image;
dividing the third image into a plurality of pixel grids, and comparing a combined vector obtained by combining the gray level data of the color gradation in the plurality of pixel grids with a feature vector of the feature image; the characteristic image is an image to be retrieved;
and if the combined vector is the same as the feature vector, outputting the target image.
2. The method of claim 1, wherein the step of resizing and rasterizing the target image to obtain a first image for each target image in the image library comprises:
for each target image in an image library, scaling the target image into a preset size range according to the preset size range;
and converting the format of the target image after scaling from a vector image to a grid image to obtain a first image.
3. The method according to claim 1, wherein the step of screening out layers satisfying a preset feature condition from among the layers of the first image, and integrating a plurality of the layers to obtain a second image comprises:
comparing a first aspect ratio of image features in each layer of the first image with a second aspect ratio of image features in the feature images, and obtaining confidence;
if the confidence coefficient exceeds a target confidence coefficient threshold value, deleting the layer;
and integrating the multiple layers of which the confidence coefficient does not exceed the target confidence coefficient threshold value to obtain a second image.
4. A method according to claim 3, characterized in that the method further comprises:
training the confidence threshold based on a non-maximum suppression algorithm to obtain a target confidence threshold.
5. The method of claim 1, wherein the step of subjecting the second image to gray scale, color space normalization, and color gradation processing to obtain a third image comprises:
carrying out graying treatment on the second image to obtain a gray scale image;
performing color space standardization processing on the gray level map to remove pixels with brightness lower than first brightness and pixels with brightness higher than second brightness in the gray level map, so as to obtain a standard map;
and carrying out gradation processing on the standard graph to obtain a third image.
6. The method according to claim 1, wherein the step of dividing the third image into a plurality of pixel cells and comparing the combined vector obtained by combining the gradation data in the plurality of pixel cells with the feature vector of the feature image includes:
dividing the third image into a plurality of square pixel grids;
acquiring gray level data of a color level in each square pixel grid;
combining the gray level data of the color gradation in the square pixel grids to obtain a combined vector;
and comparing the combined vector with the characteristic vector of the characteristic image.
7. The method of claim 6, wherein combining the gray scale data of the gray scales in the square pixel cells to obtain the combination vector comprises:
counting the gradient histogram of each square pixel grid based on the gray level data of the color level of each square pixel grid to form a feature descriptor of each square pixel grid;
forming pixel blocks by square pixel grids with each preset number;
the feature descriptors of the preset number of square pixel grids in each pixel block are connected in series to obtain feature descriptors of each pixel block;
and (5) connecting the feature descriptors of all the pixel blocks in series to obtain a combined vector.
8. The method according to claim 1, wherein the method further comprises:
storing a plurality of characteristic images containing characteristics as an image library;
the image library is updated based on an update operation.
9. The method according to claim 1, wherein the method further comprises:
temporarily storing the image in the image refining process into a cache image library;
and deleting the temporarily stored images in the cache image library according to a preset period.
10. An image refinement processing apparatus, comprising:
the preprocessing module is used for carrying out size adjustment and rasterization processing on each target image in the image library to obtain a first image;
the integration module is used for screening out layers meeting preset characteristic conditions from all the layers of the first image, and integrating a plurality of layers to obtain a second image;
the processing module is used for carrying out graying, color space standardization and color gradation processing on the second image to obtain a third image;
the contrast module is used for dividing the third image into a plurality of pixel grids, and comparing the combined vector obtained by combining the tone gray data in the pixel grids with the feature vector of the feature image; the characteristic image is an image to be retrieved;
and the output module is used for outputting the target image if the combined vector is the same as the characteristic vector.
11. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating over the bus when the electronic device is running, the processor executing the machine-readable instructions to perform the steps of the method of any one of claims 1 to 9.
12. A computer-readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, performs the steps of the method according to any of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110827005.1A CN113554615B (en) | 2021-07-21 | 2021-07-21 | Image refinement processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110827005.1A CN113554615B (en) | 2021-07-21 | 2021-07-21 | Image refinement processing method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113554615A CN113554615A (en) | 2021-10-26 |
| CN113554615B true CN113554615B (en) | 2023-08-22 |
Family
ID=78132434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110827005.1A Active CN113554615B (en) | 2021-07-21 | 2021-07-21 | Image refinement processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554615B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766798A (en) * | 2017-09-28 | 2018-03-06 | 辽宁工程技术大学 | A kind of Remote Sensing Target detection method based on cloud computing storage and deep learning |
| CN109857897A (en) * | 2019-02-14 | 2019-06-07 | 厦门一品威客网络科技股份有限公司 | A kind of trademark image retrieval method, apparatus, computer equipment and storage medium |
| CN111143813A (en) * | 2019-12-27 | 2020-05-12 | 网易（杭州）网络有限公司 | Verification problem generation method, verification method and device |
| CN111667475A (en) * | 2020-06-09 | 2020-09-15 | 陕西科技大学 | Machine vision-based Chinese date grading detection method |
| CN112329888A (en) * | 2020-11-26 | 2021-02-05 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| CN113011326A (en) * | 2021-03-18 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, storage medium and computer equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477692B (en) * | 2009-02-13 | 2012-08-22 | 阿里巴巴集团控股有限公司 | Method and apparatus for image characteristic extraction |
| KR20180131621A (en) * | 2016-04-14 | 2018-12-10 | 아데르 빌기사야르 히즈메트레리 베 티카레트 에이.에스. | Content-based search and retrieval of brand images |
-
2021
- 2021-07-21 CN CN202110827005.1A patent/CN113554615B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766798A (en) * | 2017-09-28 | 2018-03-06 | 辽宁工程技术大学 | A kind of Remote Sensing Target detection method based on cloud computing storage and deep learning |
| CN109857897A (en) * | 2019-02-14 | 2019-06-07 | 厦门一品威客网络科技股份有限公司 | A kind of trademark image retrieval method, apparatus, computer equipment and storage medium |
| CN111143813A (en) * | 2019-12-27 | 2020-05-12 | 网易（杭州）网络有限公司 | Verification problem generation method, verification method and device |
| CN111667475A (en) * | 2020-06-09 | 2020-09-15 | 陕西科技大学 | Machine vision-based Chinese date grading detection method |
| CN112329888A (en) * | 2020-11-26 | 2021-02-05 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| CN113011326A (en) * | 2021-03-18 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, storage medium and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 彩色图像快速检索方法的改进研究与仿真;杨茜;;计算机仿真(第08期);443-447 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113554615A (en) | 2021-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107403421B (en) | Image defogging method, storage medium and terminal equipment | |
| CN111062892B (en) | Single image rain removing method based on composite residual error network and deep supervision | |
| EP4109393A1 (en) | Method and device for removing moiré patterns | |
| Srinivas et al. | Remote sensing image segmentation using OTSU algorithm | |
| CN113395415B (en) | Camera data processing method and system based on noise reduction technology | |
| CN113012059A (en) | Shadow elimination method and device for character image and electronic equipment | |
| CN111340077A (en) | Disparity map acquisition method and device based on attention mechanism | |
| CN112967207A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN114757854B (en) | Night vision image quality improving method, device and equipment based on multispectral analysis | |
| CN113963009B (en) | Local self-attention image processing method and system based on deformable block | |
| CN117152182B (en) | Ultralow-illumination network camera image processing method and device and electronic equipment | |
| CN112070682A (en) | Method and device for compensating image brightness | |
| CN113554615B (en) | Image refinement processing method and device, electronic equipment and storage medium | |
| CN116343051B (en) | Geological environment monitoring method and system based on remote sensing image | |
| CN111860287A (en) | Target detection method and device and storage medium | |
| CN112085652A (en) | Image processing method and device, computer storage medium and terminal | |
| CN115660991A (en) | Model training method, image exposure correction method, device, equipment and medium | |
| CN110580694B (en) | Secondary histogram equalization dynamic image method | |
| CN113469889B (en) | Image noise reduction method and device | |
| CN109242750B (en) | Picture signature method, picture matching method, device, equipment and storage medium | |
| CN112634166A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN112822343A (en) | Night video oriented sharpening method and storage medium | |
| CN112053300B (en) | Correction method, device and equipment for illumination non-uniform image | |
| CN110647898A (en) | Image processing method, image processing device, electronic equipment and computer storage medium | |
| CN113962907B (en) | Image denoising method, device and equipment |
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 |