CN111476253A

CN111476253A - Clothing image classification method, clothing image classification device, clothing image classification method, clothing image classification device and clothing image classification equipment

Info

Publication number: CN111476253A
Application number: CN201910063759.7A
Authority: CN
Inventors: 赵永飞; 龙一民; 袁炜; 徐博文; 吴剑; 胡露露; 张民英; 神克乐; 刘志敏; 陈新; 尹宁
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-01-23
Filing date: 2019-01-23
Publication date: 2020-07-31
Anticipated expiration: 2039-01-23
Also published as: TW202109356A; WO2020151529A1; CN111476253B

Abstract

The embodiment of the application provides a clothing image classification method, an image classification device and equipment, wherein the clothing image classification method comprises the steps of obtaining a plurality of clothing images; for any clothing image, dividing the clothing image into a plurality of area images; respectively extracting color histogram features of the plurality of region images; weighting the color histogram features of the multiple area images to obtain the image features of the clothing image; clustering the clothing images based on the image characteristics of the clothing images to obtain a plurality of image sets; determining the number of images of the plurality of image sets respectively corresponding to at least one clothing image. The technical scheme provided by the embodiment of the application improves the classification precision of the clothes.

Description

Clothing image classification method, clothing image classification device, clothing image classification method, clothing image classification device and clothing image classification equipment

Technical Field

The embodiment of the application relates to the technical field of computer application, in particular to a clothing image classification method, a clothing image classification device, a clothing image classification method, a clothing image classification device and clothing image classification equipment.

Background

At present, in order to facilitate management and improve work efficiency, a production unit is used for processing only one fixed work in the prior clothing processing factory so as to realize the production process of clothing in batches, namely the production line work mode in the common sense.

Since the garment manufacturer may process different garments at the same time, in order to obtain the number of different garments processed, it is necessary to count the number of different garments processed. Generally, a camera is used for acquiring images of the clothes, the sift feature points, textures, edge contours and other features of the images are extracted as image features, then the images can be clustered based on the image features to obtain images of different types, and then the processing condition of the clothes corresponding to one type of image is confirmed.

However, since the types of garments are diversified, the acquired garment images may include garment images with rich textures, for example, images acquired for garments including rich patterns, or garment images with simple textures, for example, images acquired for pure-color garments, where features such as textures and outlines of the garment images are too complex or too simple, and when the garment images are classified using the features such as textures of the garment images, the result is inaccurate, and a classification error is generated.

Disclosure of Invention

The embodiment of the application provides clothing image classification and image classification methods, devices and equipment, and aims to solve the technical problem that in the prior art, a plurality of image classification results are not accurate enough.

In a first aspect, an embodiment of the present application provides a clothing image classification method, including:

acquiring a plurality of garment images;

for any clothing image, dividing the clothing image into a plurality of area images;

respectively extracting color histogram features of the plurality of region images;

weighting the color histogram features of the multiple area images to obtain the image features of the clothing image;

clustering the clothing images based on the image characteristics of the clothing images to obtain a plurality of image sets;

determining the number of images of the plurality of image sets respectively corresponding to at least one clothing image

In a second aspect, an embodiment of the present application provides an image classification method, including:

acquiring a plurality of images to be processed;

for any image to be processed, dividing the image to be processed into a plurality of area images;

weighting the color histogram features of the multiple regional images to obtain the image features of the image to be processed;

classifying the images to be processed based on the image characteristics of the images to be processed to obtain a plurality of image sets;

determining the image types of at least one image to be processed corresponding to the plurality of image sets respectively;

and determining the image quantity of at least one image to be processed corresponding to each image category.

In a third aspect, an embodiment of the present application provides a clothing image classification device, including:

the first acquisition module is used for acquiring a plurality of clothing images;

the first dividing module is used for dividing the clothing image into a plurality of area images aiming at any clothing image;

the first extraction module is used for respectively extracting the color histogram features of the multiple regional images;

the first weighting module is used for weighting the color histogram characteristics of the multiple area images to obtain the image characteristics of the clothing image;

the first clustering module is used for clustering the clothing images based on the image characteristics of the clothing images to obtain a plurality of image sets;

the first determining module is used for determining the number of the images of the plurality of image sets corresponding to at least one clothing image respectively.

In a fourth aspect, an embodiment of the present application provides an image classification apparatus, including:

the second acquisition module is used for acquiring a plurality of images to be processed;

the second dividing module is used for dividing the image to be processed into a plurality of area images aiming at any image to be processed;

the second extraction module is used for respectively extracting the color histogram features of the plurality of regional images;

the second weighting module is used for weighting the color histogram characteristics of the multiple regional images to obtain the image characteristics of the image to be processed;

the second classification module is used for classifying the images to be processed based on the image characteristics of the images to be processed to obtain a plurality of image sets;

a second determining module, configured to determine an image type to which at least one to-be-processed image corresponding to each of the plurality of image sets belongs;

and the third determining module is used for determining the image quantity of at least one image to be processed corresponding to each image category.

In a fifth aspect, an embodiment of the present application provides a clothing image classification device, including: the storage component stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component;

the processing component is to:

acquiring a plurality of garment images; for any clothing image, dividing the clothing image into a plurality of area images; respectively extracting color histogram features of the plurality of region images; weighting the color histogram features of the multiple area images to obtain the image features of the clothing image; clustering the clothing images based on the image characteristics of the clothing images to obtain a plurality of image sets; determining the number of images of the plurality of image sets respectively corresponding to at least one clothing image.

In a sixth aspect, an embodiment of the present application provides an image classification apparatus, including: the storage component stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component;

the processing component is to:

acquiring a plurality of images to be processed; for any image to be processed, dividing the image to be processed into a plurality of area images; respectively extracting color histogram features of the plurality of region images; weighting the color histogram features of the multiple regional images to obtain the image features of the image to be processed; classifying the images to be processed based on the image characteristics of the images to be processed to obtain a plurality of image sets; determining the image types of at least one image to be processed corresponding to the plurality of image sets respectively; and determining the image quantity of at least one image to be processed corresponding to each image category.

In the embodiment of the application, after a plurality of clothing images are extracted, the clothing images can be divided into a plurality of area images for any clothing image, then, the color histogram feature of each area image can be respectively extracted, and the color histogram feature of each area image can embody the local color feature of the clothing image in the area; weighting the color histograms of the multiple area images to generate image characteristics of the clothing image, wherein the obtained image characteristics can realize attention to the overall color characteristics of the product image; in addition, because the texture of the image is actually generated by pixel value change, and the histogram feature of each regional image is actually obtained by counting the color histogram of each pixel point, the image feature obtained by weighting the color histograms of the multiple regional images can also characterize the characteristics of the image on the texture. And then based on the image characteristics of the plurality of clothing images, when the plurality of clothing images are clustered, an accurate classification result can be obtained. The image characteristics of each garment image can represent the color and texture characteristics of the garment image locally and integrally, so that the obtained image sets have small classification errors, the number of the images of the plurality of image sets corresponding to at least one garment image respectively can be accurately determined, and the garment production process can be accurately monitored through the number of the images of the garment images.

These and other aspects of the present application will be more readily apparent from the following description of the embodiments.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a flow chart illustrating an embodiment of a clothing image classification method provided by the present application;

FIG. 2 is a flow chart illustrating a further embodiment of a garment image classification method provided by the present application;

FIG. 3 is a flow chart illustrating an embodiment of a method for classifying pictures provided by the present application;

FIG. 4 is a schematic structural diagram illustrating an embodiment of a garment image classification device provided by the present application;

FIG. 5 is a schematic structural diagram of an embodiment of a garment image classification device provided by the present application;

FIG. 6 is a schematic structural diagram illustrating an embodiment of an image classification apparatus provided in the present application;

fig. 7 shows a schematic structural diagram of an embodiment of a picture classification device provided by the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

In some of the flows described in the specification and claims of this application and in the above-described figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, the number of operations, e.g., 101, 102, etc., merely being used to distinguish between various operations, and the number itself does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

The embodiment of the invention can be applied to digital factory management, and the production progress of the clothes can be acquired at any time by intelligently monitoring the production process of the clothes, so that the production efficiency is improved.

In the prior art, a camera can be used for acquiring images of clothes, extracting image features such as textures and contours of the images, classifying the acquired images based on the image features, obtaining images belonging to different types, and determining the production progress of the clothes corresponding to the images of different types. However, when an image is characterized by features such as texture and contour, the result of image classification is not accurate enough, and a classification error is easily generated. The inventor finds that when the image features such as textures and contours of an image are extracted, the obtained image features cannot well represent local features because the whole image is directly extracted, and the features extracted in the mode are easily influenced by factors such as shapes, colors and patterns of clothes and factors such as illumination and exposure, so that the extracted features are not accurate enough, and classification errors are caused.

Accordingly, the inventor proposes a technical solution of the present application, and in an embodiment of the present invention, after a plurality of clothing images are extracted, the clothing images may be divided into a plurality of region images for any clothing image, then, color histogram features of each region image may be extracted, and the color histogram features of the plurality of region images may be subjected to weighting processing to obtain image features of the clothing images. Dividing the clothing image into a plurality of regional images, extracting the color histogram of each regional image to extract the local features of the clothing image, and performing weighting processing on the color histogram features of the regional images to realize attention to the overall features of the clothing image, so that the obtained image features of the clothing image can be represented relatively comprehensively from a spatial angle; in addition, the histogram feature can characterize the image characteristics in terms of color and texture, and is not susceptible to the clothing itself and the image acquisition environment. Furthermore, the color histogram weighting processing of the plurality of area images is used for generating the image characteristics of the clothing images, and when the plurality of clothing images are clustered, accurate classification results can be obtained. The obtained image sets have small classification errors, the number of the images of the image sets corresponding to at least one garment image can be accurately determined, and the garment production process can be accurately monitored through the number of the images of the garment images.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

As shown in fig. 1, a flowchart of an embodiment of a clothing image classification method according to an embodiment of the present invention is provided, where the method may include the following steps:

101: a plurality of garment images are acquired.

Each garment image can correspond to one garment, and the garments corresponding to each image are different.

Optionally, in order to obtain an accurate garment production quantity for performing production scheduling of different types of garments, the acquisition of garment images may be performed for garments that are produced and in the quality inspection procedure.

In practical application, since one factory may include a plurality of production lines, images acquired by different cameras may have different sizes, and in order to perform classification processing on the same pair of images, a plurality of images acquired by different cameras may be normalized to obtain a plurality of garment images. When the plurality of images are normalized, the aspect ratio of the original image can be kept, and a plurality of clothing images with unchanged aspect ratio and normalized sizes can be obtained.

102: for any one garment image, dividing the garment image into a plurality of region images.

Any one of the garment images may be selected from the plurality of garment images, and the selected garment image may be divided into a plurality of region images.

In some embodiments, in order to obtain a balanced division result, for any one of the garment images, the garment image may be divided into a plurality of region images according to a preset region position and a preset region size.

The region position can refer to the central position of the region image, the region size can refer to the image size of the region image, and specifically can refer to the number of horizontal pixel points and the number of vertical pixel points of the region image.

In one possible implementation manner, in order to divide the clothing image uniformly, the color features at different positions are collected, and any clothing image can be divided into a plurality of area images according to the number of N × M. N may be equal to M, and the number of horizontal and vertical divisions of the clothing image is the same, and thus, the area size of each area image is the same. Wherein N is more than 1 and less than the number of the clothing image pixel points. In practical application, N may be 3, that is, the clothing image may be uniformly divided into 9 area images with the same size.

103: and respectively extracting the color histogram features of the plurality of regional images.

The clothing image is partitioned to obtain the color histogram feature of each area image respectively, so that the local feature of the clothing image is extracted, and the local feature of the clothing image is focused.

In order to improve the statistical efficiency, in practical application, histogram statistics can be directly performed on a plurality of pixel points of the regional image, so as to obtain the color histogram characteristics of the regional image. And respectively extracting the color histogram features of the plurality of regional images to obtain the color histogram features respectively corresponding to the plurality of regional images. 104: and performing weighting processing on the color histogram characteristics of the plurality of area images to obtain the image characteristics of the clothing image.

Wherein, the color histogram feature of each region image can be represented in the form of a color feature matrix.

As a possible implementation manner, the color histogram features of the multiple area images may be weighted according to a predetermined weighting rule to obtain the image features of the clothing image. The predetermined weighting rule may actually refer to performing weighting processing on the color histogram feature of each region image according to the feature weight and the weighting position corresponding to each region image to obtain the image feature of the clothing image.

In some embodiments, in order to balance the feature of each region on the image feature of the clothing image, so that the obtained image feature is more accurate, the weight of the color histogram feature of each region image may be set to 1. When the color histogram feature of each region image is the color feature matrix, the weighting the color histogram features of the plurality of region images to obtain the image feature of the clothing image may include: determining the weighting sequence of the color histogram features of each region image according to the position of each region image in the clothing image; and performing matrix transverse or longitudinal splicing on the plurality of color characteristic matrixes according to the corresponding weighting sequences, wherein the obtained characteristic matrixes are the image characteristics of the clothing image.

In practical applications, in order to ensure that the color histogram features of each region image have the same local influence on the image features of the clothing image, and generate accurate image features, the feature weights of each region image may be set to be the same, for example, all the region images are set to be 1, and at this time, the color histogram features corresponding to the plurality of region images may be directly subjected to feature concatenation, so as to obtain the image features of the clothing image. For example, assuming that the color histogram features corresponding to the 3 adjacent region images a1, a2, A3 are B1, B2, B3, respectively, the features of the clothing images corresponding to the region images a1, a2, A3 may be B1B2B 3.

105: and clustering the clothing images based on the image characteristics of the clothing images to obtain a plurality of image sets.

Each clothing image can represent a piece of clothing, the image characteristics of each clothing image can represent the characteristics of the clothing, and if the clothing images are the same, the clothing corresponding to the clothing images is the same. The image characteristics of the garment image are the same for the same type of garment. The clustering of the plurality of clothing images based on the respective image features of the plurality of clothing images to obtain the plurality of image sets may specifically be to divide the clothing images with higher feature similarity into the same type of images to obtain the plurality of image sets.

And clustering the plurality of clothing images by using a clustering algorithm based on the respective image characteristics of the plurality of clothing images to obtain a plurality of image sets.

In some embodiments, a clustering algorithm may be used to perform feature clustering on image features of each of the plurality of clothing images, and then, the clothing images corresponding to feature classes with the same image features are used as an image set to obtain a plurality of image sets.

At least one garment image can correspond to each image set, and the garments corresponding to the at least one garment image are the same garment.

106: determining the number of images of the plurality of image sets respectively corresponding to at least one clothing image.

Each image set may correspond to at least one clothing image, and the number of the at least one clothing image may be counted to obtain the number of images, that is, the number of images corresponding to each image set is obtained.

In some embodiments, after determining the number of images of the plurality of image sets corresponding to the at least one garment image, the plurality of image sets and the number of images corresponding to each image set may be further output for convenient viewing by a user.

In the embodiment of the invention, after a plurality of clothing images are extracted, the clothing images can be divided into a plurality of area images aiming at any clothing image, then, the color histogram feature of each area image can be respectively extracted, and the color histogram feature of each area image can embody the local color feature of the clothing image in the area; the color histograms of the multiple area images are subjected to weighting processing to generate image features of the clothing image, and the obtained image features can realize attention to the overall color features of the product image.

In addition, because the texture of the image is actually generated by pixel value change, and the histogram feature of each regional image is actually obtained by counting the color histogram of each pixel point, the image feature obtained by weighting the color histograms of the multiple regional images can also characterize the characteristics of the image on the texture. And then based on the image characteristics of the plurality of clothing images, when the plurality of clothing images are clustered, an accurate classification result can be obtained. The image characteristics of each garment image can represent the color and texture characteristics of the garment image locally and integrally, so that the obtained image sets have small classification errors, the number of the images of the plurality of image sets corresponding to at least one garment image respectively can be accurately determined, and the garment production process can be accurately monitored through the number of the images of the garment images.

In practical applications, the color histogram feature may include a color feature matrix, that is, the color histogram feature expresses the characteristics of the image in the form of the color feature matrix.

The weighting the color histogram features of the multiple region images to obtain the image features of the clothing image may include:

and carrying out transverse or longitudinal matrix splicing processing on the color characteristic matrixes of the plurality of area images to obtain the image characteristics of the clothing image.

The transverse splicing processing of any two color feature matrices may specifically refer to splicing any row of the first color feature matrix with a row corresponding to the second color feature matrix to obtain a transverse splicing matrix of the two color feature matrices. For example, assume that the first color feature matrix is [ 101; 100], the second color feature matrix being [ 202; 200], performing transverse splicing on the two color characteristic matrixes to obtain a transverse splicing matrix [ 101202; 100200].

The vertical splicing processing of any two color feature matrices may specifically refer to vertically splicing the first color feature matrix and the second color feature matrix based on the last row of the first color feature matrix and the first row of the second color feature matrix to obtain a vertical splicing matrix of the two color feature matrices. For example, assume that the first color feature matrix is [ 101; 100], the second color feature matrix being [ 202; 200], the longitudinal splicing matrix obtained by longitudinally splicing the two color feature matrixes can be [ 101; 100, respectively; 202; 200].

As shown in fig. 2, a flowchart of a further embodiment of a clothing image classification method provided for the embodiment of the invention is different from the embodiment shown in fig. 1 in that, after determining the number of images of the plurality of image sets corresponding to at least one clothing image respectively in step 106, the method may further include:

201: and determining the clothing type of at least one clothing image corresponding to the plurality of image sets respectively.

Each image set can correspond to at least one garment image, and garment images belonging to the same image belong to the same garment type, so that at least one garment image corresponding to each image set belongs to the same garment type, and the garment type where at least one garment image corresponding to each of the image sets is located can be determined.

As an embodiment, the determining a garment type where at least one garment image respectively corresponding to the plurality of image sets is located may include:

determining at least one training image and image features of each training image; wherein each training image corresponds to a garment type;

determining a training image matched with each image set based on the image characteristics of at least one clothing image respectively corresponding to the image sets;

the clothing types of the training images respectively corresponding to the image sets are used as the clothing types of at least one clothing image respectively corresponding to the image sets.

In order to make the feature expression ways of the images identical, so as to realize the feature matching of different images, the image features of the training images are acquired in the same way as the feature acquisition ways of the embodiments shown in fig. 1 to 2.

Thus, the image features of each training image may be obtained by:

for any training image, dividing the training image into a plurality of training area images;

respectively extracting color histogram features of the multiple training area images;

and performing weighting processing on the color histogram features of the images in the plurality of training areas to obtain the image features of the plurality of training images.

The area positions of each area image are different, and in order to make the representation modes of the image features of different clothing images the same, the color histogram features of the area images can be weighted according to the area positions to obtain the image features of the clothing images. As another embodiment, the step 104: performing weighting processing on the color histogram features of the multiple region images to obtain the image features of the clothing image may include:

and performing weighting processing on the color histogram characteristics of the plurality of area images according to the area positions of the plurality of area images to obtain the image characteristics of the clothing image.

Specifically, the weighting processing according to the area positions of the multiple area images may refer to determining the weighting positions of the area images according to the area positions of any area image, and performing feature splicing on the corresponding color histogram features of the area images according to the corresponding weighting positions, so as to obtain the image features of the clothing image when the feature splicing of the color histogram features of the multiple area images is completed. When the color histogram feature is a color feature matrix, performing feature splicing on the color histogram feature may refer to performing matrix splicing on the color histogram matrix.

Since the color overall characteristics of different pixel points can be represented by using a pure statistical manner of the pixel value of each pixel point, but the characteristics of different pixel points in different color spaces cannot be displayed, as another embodiment, the step 103 of extracting the color histogram characteristics of the multiple region images respectively may include:

and respectively extracting the color histogram features of the plurality of area images in a plurality of color channels.

The color histogram features of each region image at a plurality of color channels can be extracted in turn. Color histogram features of the plurality of region images may be extracted based on the plurality of color channels, respectively.

Each color channel can represent different color characteristics, and the characteristics of different pixel points in different color spaces can be obtained by converting the characteristics into corresponding color channels.

In order to obtain accurate color histogram features, as yet another embodiment, the extracting color histogram features of the plurality of region images at a plurality of color channels, respectively, may include:

extracting channel histogram features corresponding to the area images in a plurality of color channels respectively aiming at any one of the area images;

and weighting the channel histogram features respectively corresponding to the plurality of color channels to obtain the color histogram features of the regional image.

The channel histogram feature may refer to a channel feature matrix. Performing weighting processing on the channel histogram features corresponding to the multiple color channels, and obtaining the color histogram features of the area image may include: and performing transverse or longitudinal matrix splicing processing on the channel characteristic matrixes to obtain the color histogram characteristics of the area image. The weighting sequence of each color channel can be determined according to the channel sequence of the color channels, and the characteristic matrix obtained by transversely or longitudinally splicing the channel characteristic matrixes according to the weighting sequence of each color channel is the color histogram characteristic of the regional image.

The color histogram features of the area image are obtained by extracting the channel histogram features of the area image corresponding to the color histogram channels respectively and weighting the channel histogram features. In practical applications, for the weighting processing of the channel histogram features corresponding to the plurality of color channels, the weighting processing may be performed on each channel histogram feature to generate the color histogram of the area image.

In some embodiments, the extracting, for any one of the region images, channel histogram features corresponding to the region image in a plurality of color channels respectively includes:

aiming at any one of the regional images, respectively corresponding channel values of each pixel point of the regional image in the plurality of color channels;

dividing each color channel into a plurality of histogram statistical intervals;

for any color channel, counting channel values of a plurality of pixel points of the regional image in the color channel, and respectively corresponding distribution quantity in a plurality of histogram statistical intervals corresponding to the color channel;

and determining the channel histogram characteristics of the region image in the color channel based on the distribution quantity of the histogram statistical intervals.

In some embodiments, the clothing image classification method described above may further include: and determining a plurality of color channels formed by three color channels respectively corresponding to the at least one color space model.

The at least one color space module can be preset, a plurality of color channels can be obtained through the three color channels corresponding to the at least one color space model respectively, and the plurality of color channels can be specifically determined to be a plurality of color channels formed by the three color channels corresponding to the at least one preset color space model respectively, so that the processing efficiency is improved.

For any regional image, channel histograms corresponding to the regional image in the multiple color channels can be extracted, the respective pixel values of the multiple pixel points of the regional image can be converted into the multiple color channels, the channel value of each pixel point corresponding to the multiple color channels is obtained, the channel value of each regional image corresponding to the multiple pixel points in the channel can be obtained for each color channel, and then channel histogram statistics can be performed for any color channel.

Due to the fact that the number of the channels is large, if data corresponding to each channel are counted one by one, an increment calculation process is needed, and the data dimension of the obtained channel histogram feature is also very high. Therefore, each color channel can be subjected to histogram statistical interval division, so that different color channels can be counted according to the histogram statistical intervals.

In some possible designs, the at least one color space includes an RGB color space, an HSV color space, and a YcbCr color space;

the RGB color space corresponds to an R color channel, a G color channel and a B color channel, the HSV color space corresponds to an H color channel, an S color channel and a V color channel, and the YcbCr color space corresponds to a Y color channel, a Cb color channel and a Cv color channel.

For different color channels, each color channel can be divided into a plurality of histogram statistic intervals according to the dividing times by aiming at the channel characteristics of each color channel.

As a possible implementation manner, the R color channel may be divided into 24 histogram statistic intervals, the G color channel may be divided into 24 histogram statistic intervals, and the B color channel may be divided into 24 histogram statistic intervals, the HSV color space may be divided into 32 histogram statistic intervals corresponding to the H color channel, the S color channel may be divided into 32 histogram statistic intervals, and the V color channel may be divided into 8 histogram statistic intervals, the YcbCr color space may be divided into 24 histogram statistic intervals corresponding to the Y color channel, the Cb color channel may be divided into 16 histogram statistic intervals, and the Cv color channel may be divided into 16 statistic intervals.

And then, the occurrence times of the channel values of the plurality of pixel points respectively corresponding to the plurality of color channels in each statistical interval can be counted, and the histogram feature value corresponding to each statistical interval is obtained.

Taking the above G color channel as an example, after the G color channel is divided into 24 histogram statistical intervals, channel values corresponding to a plurality of pixel points in the G color channel may be counted, and the occurrence times of each statistical interval are respectively obtained, so as to obtain the distribution number of the G color channel corresponding to each of the 24 statistical intervals, and obtain the channel histogram feature of the G color channel, where the feature is 1 × 24 dimensional data. Histogram features corresponding to color channels of R, B, H, S, V, Y, Cb, Cr, etc. can be obtained, and the dimensions of the features are 1 × 24, 1 × 32, 1 × 8, 1 × 24, 1 × 16, respectively.

Then, weighting processing may be performed on the channel histogram features corresponding to the plurality of color channels, respectively, to obtain the color histogram features of the region image, and feature weighting processing may be performed in this manner, for example, weighting processing may be directly performed on the channel histogram features corresponding to each channel, to obtain a1 × 200-dimensional color feature histogram. If each clothing channel is averagely divided into 9 area images, the color histogram features respectively corresponding to the area images are subjected to feature weighting processing, for example, simple feature splicing, and the image features of the clothing image with 1 × 1800 dimensions can be obtained.

After the plurality of clothing images are clustered through the image characteristics and based on the image characteristics, clustering results of the plurality of clothing images can be output, so that a user can conveniently check the clothing images. As another embodiment, after determining the number of images of the plurality of image sets respectively corresponding to at least one clothing image, the method further includes:

sorting the number of images to determine an output order of each image set;

and sequentially outputting at least one clothing image corresponding to each of the plurality of image sets according to the respective output sequence of the plurality of image sets.

Alternatively, sorting the number of images to determine the output order of each image set may specifically refer to sorting the number of images in ascending or descending order according to the size of the number to determine the output order of each image set.

As shown in fig. 3, a flowchart of another embodiment of an image classification method according to an embodiment of the present invention is provided, where the method may include the following steps:

301: a plurality of images to be processed are acquired.

302: for any image to be processed, dividing the image to be processed into a plurality of area images.

303: and respectively extracting the color histogram features of the plurality of regional images.

304: and performing weighting processing on the color histogram characteristics of the multiple regional images to obtain the image characteristics of the image to be processed.

305: classifying the images to be processed based on the image characteristics of the images to be processed to obtain a plurality of image sets.

306: and determining the image type of at least one to-be-processed image respectively corresponding to the plurality of image sets.

307: and determining the image quantity of at least one image to be processed corresponding to each image category.

The image classification method provided in the embodiment of the present invention is the same as the image processing method used in the clothing image classification method shown in fig. 1 to 2, and is not described herein again.

In the embodiment of the present invention, after a plurality of images to be processed are extracted, the images to be processed may be divided into a plurality of region images for any one of the images to be processed, and then, the color histogram features of each region image may be respectively extracted, and the color histogram features of the plurality of region images are subjected to weighting processing, so as to obtain the image features of the images to be processed. The color histogram features of the regional images can reflect local features of the images to be processed, and the attention to the overall features of the images to be processed can be realized by weighting the color histogram features of the regional images; in addition, the histogram feature can characterize the image characteristics in terms of color and texture, and is not susceptible to the clothing itself and the image acquisition environment. And then, generating the image characteristics of the images to be processed by using the color histogram weighting processing of the images of the plurality of areas, and obtaining an accurate classification result when clustering the images to be processed. The obtained image sets have small classification errors, the number of the images of the image sets corresponding to at least one image to be processed respectively can be accurately determined, and the garment production process can be accurately monitored through the number of the images of the image to be processed.

As shown in fig. 4, a schematic structural diagram of a further embodiment of a clothing image classification device provided in an embodiment of the present invention may include the following modules:

a first obtaining module 401, configured to obtain a plurality of garment images;

a first dividing module 402, configured to divide the clothing image into a plurality of area images for any clothing image;

a first extraction module 403, configured to extract color histogram features of the multiple region images respectively;

a first weighting module 404, configured to perform weighting processing on the color histogram features of the multiple region images to obtain image features of the clothing image;

a first clustering module 405, configured to cluster the clothing images based on image features of the clothing images to obtain a plurality of image sets;

a first determining module 406, configured to determine a number of images of the plurality of image sets respectively corresponding to at least one clothing image.

In the embodiment of the application, the color histogram features of the area images can embody the local features of the clothing images, and the attention to the overall features of the clothing images can be realized by performing weighting processing on the color histogram features of the area images; in addition, the histogram feature can characterize the image characteristics in terms of color and texture, and is not susceptible to the clothing itself and the image acquisition environment. Furthermore, the color histogram weighting processing of the plurality of area images is used for generating the image characteristics of the clothing images, and when the plurality of clothing images are clustered, accurate classification results can be obtained. The obtained image sets have small classification errors, the number of the images of the image sets corresponding to at least one garment image can be accurately determined, and the garment production process can be accurately monitored through the number of the images of the garment images.

As an embodiment, the apparatus shown in fig. 4 may further include:

and the fourth determining module is used for determining the clothing type of at least one clothing image corresponding to the plurality of image sets respectively.

As still another embodiment, the apparatus shown in fig. 4 may further include:

a sorting module for sorting the number of images to determine an output order of each image set; and the output module is used for sequentially outputting the plurality of image sets according to the respective output sequence and at least one clothing image corresponding to each image set.

In order to make the representation modes of the image features of different clothing images the same, the color histogram features of the area images may be weighted according to the area positions thereof to obtain the image features of the clothing images, and as a further embodiment, the first weighting module includes:

and the first weighting unit is used for carrying out weighting processing on the color histogram characteristics of the plurality of area images according to the area positions of the plurality of area images to obtain the image characteristics of the clothing image.

Since the color overall characteristics of different pixel points can be expressed by using a mode of simply counting the pixel value of each pixel point, but the characteristics of different pixel points in different color spaces cannot be displayed, as another embodiment, the first extraction module includes:

and the first extraction unit is used for respectively extracting the color histogram features of the area images in a plurality of color channels.

In order to obtain accurate color histogram features, as still another embodiment, the first extraction unit includes:

a first extraction subunit, configured to extract, for any one of the plurality of region images, channel histogram features corresponding to the region image in each of a plurality of color channels;

and the first weighting subunit is used for weighting the channel histogram features respectively corresponding to the plurality of color channels to obtain the color histogram features of the area image.

In some embodiments, the first extraction subunit may specifically be configured to include:

In certain embodiments, further comprising:

and the channel determining module is used for determining a plurality of color channels formed by three color channels respectively corresponding to the at least one color space model.

As one embodiment, the color histogram feature comprises a color feature matrix;

the first weighting module may include:

and the second weighting module is used for carrying out transverse or longitudinal matrix splicing processing on the color characteristic matrixes of the plurality of area images to obtain the image characteristics of the clothing image.

The apparatus shown in fig. 4 can execute the clothing image classification method described in the embodiments shown in fig. 1 to fig. 2, and the implementation principle and technical effect thereof are not repeated. The specific manner in which each module and unit of the clothing image classification device in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the method for classifying clothing images according to the embodiment shown in fig. 1 to 2 may be implemented.

As shown in fig. 5, a schematic structural diagram of another embodiment of a garment image classification apparatus according to an embodiment of the present invention is provided, where the apparatus may include: the storage component 501 stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component 502;

the processing component 502 can be configured to:

As an embodiment, the processing component 501 may be further configured to:

and determining the clothing type of at least one clothing image corresponding to the plurality of image sets respectively.

As yet another embodiment, the processing component 501 may be further configured to:

sorting the number of images to determine an output order of each image set;

As the mode of simply counting the pixel value of each pixel point is used, the color overall characteristics of different pixel points can be represented, but the characteristics of different pixel points in different color spaces cannot be displayed, as another embodiment, the processing component performs weighting processing on the color histogram characteristics of the multiple area images, and the image characteristics of the clothing image can be obtained specifically as follows:

In order to obtain accurate color histogram features, as another embodiment, the step of extracting the color histogram features of the plurality of region images by the processing component may specifically be:

In some embodiments, the specific steps of the processing component extracting the color histogram features of the plurality of region images in the plurality of color channels respectively may be: extracting channel histogram features corresponding to the area images in a plurality of color channels respectively aiming at any one of the area images;

In some embodiments, for any region image in the plurality of region images, the extracting, by the processing component, the channel histogram features of the region image corresponding to the plurality of color channels may specifically be:

In some embodiments, the processing component 501 may also be configured to:

and determining a plurality of color channels formed by three color channels respectively corresponding to the at least one color space model.

In some possible designs, the at least one color space determined by the processing component includes an RGB color space, an HSV color space, and a YcbCr color space;

The device shown in fig. 5 may execute the clothing image classification method described in the embodiment shown in fig. 1 to fig. 2, and the implementation principle and the technical effect are not repeated. The detailed description of the processing components of the clothing image classification device in the above embodiments has been described in detail in the embodiments related to the method, and will not be elaborated herein.

As shown in fig. 6, a schematic structural diagram of another embodiment of an image classification apparatus according to an embodiment of the present invention is provided, where the apparatus may include the following modules:

a second obtaining module 601, configured to obtain a plurality of images to be processed;

a second dividing module 602, configured to divide any image to be processed into a plurality of region images;

a second extracting module 603, configured to extract color histogram features of the multiple region images, respectively;

a second weighting module 604, configured to perform weighting processing on the color histogram features of the multiple region images to obtain image features of the image to be processed;

a second classification module 605, configured to classify the multiple images to be processed based on image features of the multiple images to be processed, so as to obtain multiple image sets;

a second determining module 606, configured to determine an image type to which at least one to-be-processed image corresponding to each of the plurality of image sets belongs;

a third determining module 607, configured to determine the image quantity of the at least one to-be-processed image corresponding to each image category.

In the embodiment of the invention, the color histogram features of the regional images can embody the local features of the images to be processed, and the attention to the overall features of the images to be processed can be realized by weighting the color histogram features of the regional images; in addition, the histogram feature can characterize the image characteristics in terms of color and texture, and is not susceptible to the clothing itself and the image acquisition environment. And then, generating the image characteristics of the images to be processed by using the color histogram weighting processing of the images of the plurality of areas, and obtaining an accurate classification result when clustering the images to be processed. The obtained image sets have small classification errors, the number of the images of the image sets corresponding to at least one image to be processed respectively can be accurately determined, and the garment production process can be accurately monitored through the number of the images of the image to be processed.

The apparatus shown in fig. 6 can execute the image classification method shown in the embodiment shown in fig. 3, and the implementation principle and the technical effect are not repeated. The specific manner in which each module and unit of the image classification apparatus in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the image classification method of the embodiment shown in fig. 3 may be implemented.

As shown in fig. 7, a schematic structural diagram of another embodiment of an image classification apparatus according to an embodiment of the present invention is provided, where the apparatus may include: the storage component 701 stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component 702;

the processing component 702 is configured to:

The device shown in fig. 7 may perform the image classification method described in the embodiment shown in fig. 3, and the implementation principle and the technical effect are not repeated. The detailed description of the image classification device in the above embodiments regarding the processing components has been described in detail in the embodiments related to the method, and will not be set forth herein in detail.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A clothing image classification method is characterized by comprising the following steps:

acquiring a plurality of garment images;

determining the number of images of the plurality of image sets respectively corresponding to at least one clothing image.

2. The method of claim 1, further comprising:

3. The method of claim 1, wherein after determining the number of images of the plurality of image sets corresponding to at least one garment image, respectively, further comprising:

sorting the number of images to determine an output order of each image set;

4. The method according to claim 1, wherein the weighting the color histogram features of the plurality of region images to obtain the image features of the clothing image comprises:

5. The method according to claim 1, wherein the extracting color histogram features of the plurality of region images respectively comprises:

6. The method according to claim 5, wherein the extracting color histogram features of the plurality of region images at a plurality of color channels respectively comprises:

7. The method according to claim 6, wherein the extracting, for any one of the region images, channel histogram features corresponding to the region image in a plurality of color channels respectively comprises:

8. The method of claim 7, further comprising:

9. The method of claim 8, wherein the at least one color space comprises an RGB color space, an HSV color space, and a YcbCr color space;

10. The method of claim 1, wherein the color histogram feature comprises a color feature matrix;

the weighting processing of the color histogram features of the multiple area images to obtain the image features of the clothing image comprises:

11. An image classification method, comprising:

acquiring a plurality of images to be processed;

12. An apparatus for classifying a garment image, comprising:

13. An image classification apparatus, comprising:

14. An apparatus for classifying a garment image, comprising: the storage component stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component;

the processing component is to:

15. An image classification apparatus characterized by comprising: the storage component stores one or more computer instructions, and the one or more computer instructions are called and executed by the processing component;

the processing component is to: