WO2019096174A1 - 人物图像服装颜色识别方法、装置及电子设备 - Google Patents

人物图像服装颜色识别方法、装置及电子设备 Download PDF

Info

Publication number
WO2019096174A1
WO2019096174A1 PCT/CN2018/115488 CN2018115488W WO2019096174A1 WO 2019096174 A1 WO2019096174 A1 WO 2019096174A1 CN 2018115488 W CN2018115488 W CN 2018115488W WO 2019096174 A1 WO2019096174 A1 WO 2019096174A1
Authority
WO
WIPO (PCT)
Prior art keywords
color
garment
target
effective area
recognition
Prior art date
Application number
PCT/CN2018/115488
Other languages
English (en)
French (fr)
Inventor
斯科特·马修·罗伯特
黄鼎隆
傅恺
张弛
Original Assignee
深圳码隆科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳码隆科技有限公司 filed Critical 深圳码隆科技有限公司
Publication of WO2019096174A1 publication Critical patent/WO2019096174A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0203—Market surveys; Market polls
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person

Definitions

  • the present application relates to the field of image recognition technologies, and in particular, to a method, device, and electronic device for recognizing a person image clothing color.
  • the purpose of the present application is to provide a method, device, and electronic device for recognizing a person's image clothing color, which can identify and predict the color of a person's image collected in various regions and seasons, and provide clothing manufacturers with A reliable reference.
  • an embodiment of the present application provides a color recognition method for a character image clothing, including:
  • a popular color trend prediction map is generated based on a plurality of color scale maps.
  • the embodiment of the present application provides a first possible implementation manner of the first aspect, where the acquiring multiple target person images includes:
  • the plurality of character images of the preset area in the preset time period are collected by the camera; the preset time period includes: spring and summer, autumn and winter; and the preset area includes: any one of the garment exit areas;
  • a person image of a preset area in a plurality of preset time periods is taken as a target person image.
  • the embodiment of the present application provides a second possible implementation manner of the first aspect, wherein extracting the effective area of the garment from each target person image includes:
  • the effective area of the garment is determined.
  • the embodiment of the present application provides a third possible implementation manner of the first aspect, wherein the color analysis and recognition of the effective area of the garment is performed by using the preset depth learning model to generate a color ratio map, which specifically includes:
  • Color recognition of the effective area of the garment to determine a plurality of target colors contained in the effective area of the garment;
  • a color scale map is generated based on the proportional relationship between the plurality of target colors.
  • the embodiment of the present application provides a fourth possible implementation manner of the first aspect, wherein, according to the multiple color ratio maps, the trend graph of the popular color trend is generated, which specifically includes:
  • a plurality of scale change curves of the same color are drawn according to the scale, and a trend forecast map of the popular color is generated.
  • the embodiment of the present application provides a fifth possible implementation manner of the first aspect, wherein, after performing color recognition on the effective area of the garment to determine a plurality of target colors included in the effective area of the garment, the method further includes :
  • the embodiment of the present application provides a character image clothing color recognition device, including:
  • An image acquisition module configured to acquire images of a plurality of target characters
  • a region extraction module configured to extract a garment effective area from each character image
  • a color recognition module configured to perform color analysis and recognition on a plurality of garment effective regions by using a preset depth learning model to generate a color scale map
  • a chart generation module configured to generate a trend forecast map based on a plurality of color scale maps.
  • the embodiment of the present application provides a first possible implementation manner of the second aspect, where the color recognition module includes:
  • a color recognition unit configured to perform color recognition on the effective area of the garment to determine a plurality of target colors included in the effective area of the garment;
  • a quantization detecting unit configured to perform quantitative detection on each target color to determine a proportional relationship between the plurality of target colors
  • the scale map generation unit is configured to generate a color scale map according to a proportional relationship between the plurality of target colors.
  • an embodiment of the present application provides an electronic device, including a memory and a processor, where the computer stores a computer program executable on a processor, and when the processor executes the computer program, the method of the first aspect is implemented. step.
  • the embodiment of the present application further provides a computer readable medium having a processor-executable non-volatile program code, the program code causing a processor to perform the method as described in the first aspect.
  • a plurality of target person images are first acquired; a clothing effective area is extracted from each target person image; and a plurality of clothing effective areas are subjected to color analysis and recognition through deep learning, Generate a color scale map; generate a trend forecast map based on a plurality of color scale maps.
  • the method is based on deep learning, and can identify and detect the color of a large number of people's images collected in various time zones in various regions, thereby analyzing and predicting the color of clothing in various regions and seasons, providing reliable clothing manufacturers. Reference.
  • FIG. 1 is a flowchart of a color recognition method for a character image clothing according to an embodiment of the present application
  • FIG. 2 is a flowchart of another method for recognizing a character image clothing color according to an embodiment of the present application
  • FIG. 3 is a flowchart of another method for recognizing a color of a character image clothing according to an embodiment of the present application
  • FIG. 4 is a flowchart of another method for recognizing a character image clothing color according to an embodiment of the present application
  • FIG. 5 is a flowchart of another method for recognizing a character image clothing color according to an embodiment of the present application.
  • FIG. 6 is a flowchart of another method for recognizing a color of a character image clothing according to an embodiment of the present application
  • FIG. 7 is a schematic structural diagram of a character image clothing color recognition apparatus according to an embodiment of the present disclosure.
  • FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • the existing fashion color analysis and prediction requires manual classification and statistics of various clothing colors in the collected person images. This process requires a lot of manpower and material resources, and the efficiency is very low.
  • the image image clothing color recognition method, device and electronic device provided by the embodiments of the present invention can identify and predict the color of the clothing collected from various regions and seasons, and provide a reliable reference for the garment manufacturer. .
  • Embodiment 1 is a diagrammatic representation of Embodiment 1:
  • the embodiment of the present application provides a color recognition method for a character image clothing.
  • the method includes the following steps:
  • the specific image acquisition process includes the following steps, as shown in Figure 2:
  • S201 Collect, by the camera, a plurality of character images of a preset area within a preset time period.
  • the preset time period includes: spring and summer, autumn and winter
  • the preset area includes: any one of the clothing export areas, such as: South Asia, South Korea or Europe. It should be noted that the preset time period is not limited to the spring and summer and autumn and winter as described in the embodiments of the present application, and other time segmentation methods may be used, such as: spring, summer, autumn, and winter.
  • the camera can capture a large number of character images in a certain period of time in a certain area, and can directly capture the image of the characters in the fashion magazine, or go to various clothing stores to take pictures of the characters of the model, or other places.
  • Character image can also be divided into two categories, namely, men's and women's, and separately perform clothing color recognition and prediction on the two types of character images.
  • S202 The person image of the preset area in the plurality of preset time periods is used as the target person image.
  • a large number of person images in a certain time period in a certain region collected above are used as target person images to provide sample data for subsequent deep learning.
  • the specific process of determining the effective area of the garment includes the following steps, as shown in FIG. 3:
  • S301 Using a Sobel boundary detection filter to perform boundary detection on a target person image.
  • the GPU Image Sobel Edge Detection Filter filter is used to detect the effective area of the garment, and the gray value of the image to be processed is first calculated by the Sobel operator.
  • the Sobel operator is mainly used for edge detection. Technically, it is a discrete difference operator that is used to calculate the approximation of the gray level of the image brightness function. Using this operator at any point in the image will produce a corresponding gray vector or its normal vector.
  • the Sobel convolution factor is:
  • the operator consists of two sets of 3x3 matrices, which are horizontal and vertical, respectively, and are planarly convolved with the image to obtain lateral and longitudinal luminance difference approximations. If A represents the original image, Gx and Gy represent the gray value of the image detected by the lateral and longitudinal edges, respectively, and the formula is as follows:
  • Gx (-1)*f(x-1,y-1)+0*f(x,y-1)+1*f(x+1,y-1)
  • Gy 1*f(x-1,y-1)+2*f(x,y-1)+1*f(x+1,y-1)
  • f(a, b) represents the gray value of the image (a, b) point
  • the point (x, y) is considered to be an edge point.
  • the gradient direction can then be calculated using the following formula:
  • the exact edge direction can be obtained by calculating the gradient direction.
  • the Sobel operator detects the edge by the weighted difference between the upper and lower adjacent points of the pixel and the extreme value at the edge. It has a smoothing effect on noise and provides accurate edge direction information.
  • S302 Determine the effective area of the garment according to the detection result of the boundary detection.
  • the skin color detection criterion based on the RGB color mode is used to detect the skin color of the person image, and the effective area of the clothing is accurately obtained.
  • S103 Perform color analysis and recognition on a plurality of garment effective regions by using a preset depth learning model to generate a color scale map.
  • the specific color scale map generation process includes the following steps, as shown in Figure 4:
  • S401 Perform color recognition on the effective area of the garment to determine a plurality of target colors included in the effective area of the garment.
  • the colors contained in the effective area of the garment are detected as three target colors.
  • S402 Perform quantitative detection on each target color to determine a proportional relationship between the plurality of target colors.
  • S403 Generate a color scale map according to a proportional relationship between the plurality of target colors.
  • the effective area of the garment includes three target colors of red, blue, and yellow
  • quantitatively detecting the three target colors respectively detecting the color amount of each color, thereby determining the color of each target color.
  • the ratio of the amount to the total amount of color also gives the proportional relationship between the multiple target colors.
  • a color scale map is generated according to the proportional relationship between the plurality of target colors determined above.
  • S104 Generate a trend forecast map of the popular color based on the plurality of color scale maps.
  • the specific popular color trend prediction graph generation process includes the following steps, as shown in FIG. 5:
  • S501 Extract the proportion of the same color in each color scale map from a plurality of color scale maps.
  • S502 draw a plurality of scale change curves of the same color according to the ratio, and generate a trend forecast map of the popular color.
  • the plurality of color scale maps may be a color scale map of the men's clothing in a certain period of time, from which the proportion of the color of the same color in each color scale map is extracted, and then the proportion change is drawn according to the color amount ratio value. Curves to generate a trend forecast map of popular colors.
  • S601 Perform preset semantic matching on each target color to obtain a color semantic analysis result.
  • the semantics matching blue are pure, the semantics matching golden color is vitality, the semantics matching green are youth, the semantics matching red are enthusiasm, the semantics matching yellow are young, and the semantics matching purple are Mystery, etc., after determining the plurality of target colors contained in the effective area of the garment, matching the color and the semantics, and obtaining the semantic analysis result corresponding to the effective area of the clothing in each target image.
  • a plurality of target person images are first acquired; a clothing effective area is extracted from each target person image; and a plurality of clothing effective areas are subjected to color analysis and recognition through deep learning, Generate a color scale map; generate a trend forecast map based on a plurality of color scale maps.
  • the method is based on deep learning, and can identify and detect the color of a large number of people's images collected in various time zones in various regions, thereby analyzing and predicting the color of clothing in various regions and seasons, providing reliable clothing manufacturers. Reference.
  • Embodiment 2 is a diagrammatic representation of Embodiment 1:
  • the embodiment of the present application provides a character image clothing color recognition device.
  • the device includes:
  • the image obtaining module 71 is configured to acquire a plurality of target person images
  • the area extraction module 72 is configured to extract a garment effective area from each character image
  • the color recognition module 73 is configured to perform color analysis and recognition on a plurality of garment effective regions by using a preset depth learning model to generate a color scale map;
  • the graph generation module 74 is configured to generate a pop color trend prediction map based on the plurality of color scale maps.
  • the color recognition module 73 includes:
  • the color recognition unit 731 is configured to perform color recognition on the effective area of the garment, and determine a plurality of target colors included in the effective area of the garment;
  • the quantization detecting unit 732 is configured to perform quantitative detection on each target color to determine a proportional relationship between the plurality of target colors
  • the scale map generation unit 733 is configured to generate a color scale map based on a proportional relationship between the plurality of target colors.
  • the working process of each module has the same technical features as the character image clothing color recognizing method. Therefore, the above functions can also be implemented, and details are not described herein again.
  • Embodiment 3 is a diagrammatic representation of Embodiment 3
  • the embodiment of the present application further provides an electronic device.
  • the electronic device includes: a processor 80, a memory 81, a bus 82, and a communication interface 83.
  • the processor 80, the communication interface 83, and the memory 81 pass through the bus.
  • 82 is connected; the processor 80 is configured to execute an executable module, such as a computer program, stored in the memory 81.
  • the steps of the method as described in the method embodiments are implemented when the processor executes a computer program.
  • the memory 81 may include a high speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory.
  • RAM high speed random access memory
  • non-volatile memory such as at least one disk memory.
  • the communication connection between the system network element and at least one other network element is implemented by at least one communication interface 83 (which may be wired or wireless), and may use an Internet, a wide area network, a local network, a metropolitan area network, or the like.
  • the bus 82 can be an ISA bus, a PCI bus, or an EISA bus.
  • the bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one double-headed arrow is shown in Figure 8, but it does not mean that there is only one bus or one type of bus.
  • the memory 81 is configured to store a program, and the processor 80 executes the program after receiving the execution instruction, and the method executed by the device defined by the flow process disclosed in any of the foregoing embodiments of the present application may be applied to the processing.
  • the processor 80 or implemented by the processor 80.
  • Processor 80 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in the processor 80 or an instruction in the form of software.
  • the processor 80 may be a general-purpose processor, including a central processing unit (CPU) and a network processor (NP), and may also be a digital signal processor (DSP). ), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component.
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present application may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory 81, and the processor 80 reads the information in the memory 81 and performs the steps of the above method in combination with its hardware.
  • the computer program product of the method for locating a network device includes a computer readable storage medium storing non-volatile program code executable by a processor, the program code including instructions configurable to execute the front
  • a computer readable storage medium storing non-volatile program code executable by a processor, the program code including instructions configurable to execute the front
  • each block of the flowchart or block diagram can represent a module, a program segment, or a portion of code that comprises one or more of the Executable instructions.
  • the functions noted in the blocks may also occur in a different order than that illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or function. Or it can be implemented by a combination of dedicated hardware and computer instructions.
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some communication interface, device or unit, and may be electrical, mechanical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as separate products, may be stored in a non-transitory computer readable storage medium executable by a processor.
  • the technical solution of the present application which is essential or contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product, which is stored in a storage medium, including
  • the instructions are used to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Multimedia (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

一种人物图像服装颜色识别方法、装置及电子设备，涉及图像识别技术领域，其中，人物图像服装颜色识别方法包括：获取多个目标人物图像（S101）；从每个目标人物图像中提取出服装有效区域（S102）；通过预设深度学习模型对多个服装有效区域进行颜色分析识别，生成颜色比例图（S103）；基于多个颜色比例图，生成流行色趋势预测图（S104）。该人物图像服装颜色识别方法能够对采集于各个地区和各个季节的人物图像，进行服装颜色的识别及预测，为服装生产厂商提供参考。

Description

人物图像服装颜色识别方法、装置及电子设备
相关申请的交叉引用
本申请要求于2017年11月14日提交中国专利局的申请号为201711126273.0、名称为“人物图像服装颜色识别方法、装置及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及图像识别技术领域，尤其是涉及一种人物图像服装颜色识别方法、装置及电子设备。
背景技术
随着我国经济的持续快速发展，服装出口业务呈现大幅度上升趋势。对于服装出口数量的控制及预测，目前采用如下方式：
国家专业机构每年提供两次服装流行色分析及预测报告，为各大服装供应商提供参考。具体的过程为：通过拍照获取各个商店、杂志或者其它场所的人物图像，然后通过人工方式对人物图像中的各种服装颜色进行分类统计。此过程需要花费大量的人力物力，并且效率很低。
发明内容
有鉴于此，本申请的目的在于提供一种人物图像服装颜色识别方法、装置及电子设备，能够对采集于各个地区和各个季节的人物图像，进行服装颜色的识别及预测，为服装生产厂商提供可靠的参考。
第一方面，本申请实施例提供了一种人物图像服装颜色识别方法，包括：
获取多个目标人物图像；
从每个目标人物图像中提取出服装有效区域；
通过预设深度学习模型对多个服装有效区域进行颜色分析识别，生成颜色比例图；
基于多个颜色比例图，生成流行色趋势预测图。
结合第一方面，本申请实施例提供了第一方面的第一种可能的实施方式，其中，获取多个目标人物图像，具体包括：
通过摄像机采集在预设时间段内预设地区的多个人物图像；预设时间段包括：春夏季和秋冬季；预设地区包括：服装出口地区中的任一区域；
将多个预设时间段内预设地区的人物图像作为目标人物图像。
结合第一方面，本申请实施例提供了第一方面的第二种可能的实施方式，其中，从每个目标人物图像中提取出服装有效区域，具体包括：
采用Sobel边界检测滤镜，对目标人物图像进行边界检测；
根据边界检测的检测结果，确定服装有效区域。
结合第一方面，本申请实施例提供了第一方面的第三种可能的实施方式，其中，通过预设深度学习模型对服装有效区域进行颜色分析识别，生成颜色比例图，具体包括：
对服装有效区域进行颜色识别，确定服装有效区域内所包含的多个目标颜色；
对每个目标颜色进行量化检测，确定多个目标颜色之间的比例关系；
根据多个目标颜色之间的比例关系，生成颜色比例图。
结合第一方面，本申请实施例提供了第一方面的第四种可能的实施方式，其中，基于多个颜色比例图，生成流行色趋势预测图，具体包括：
从多个颜色比例图中提取出相同颜色在各个颜色比例图中所占的比例；
根据比例绘制出多个相同颜色的比例变化曲线，生成流行色趋势预测图。
结合第一方面，本申请实施例提供了第一方面的第五种可能的实施方式，其中，在对服装有效区域进行颜色识别，确定服装有效区域内所包含的多个目标颜色之后，还包括：
对每个目标颜色进行预设语义匹配，得到颜色语义分析结果。
第二方面，本申请实施例提供一种人物图像服装颜色识别装置，包括：
图像获取模块，配置成获取多个目标人物图像；
区域提取模块，配置成从每个人物图像中提取出服装有效区域；
颜色识别模块，配置成通过预设深度学习模型对多个服装有效区域进行颜色分析识别，生成颜色比例图；
图表生成模块，配置成基于多个颜色比例图，生成流行色趋势预测图。
结合第二方面，本申请实施例提供了第二方面的第一种可能的实施方式，其中，颜色识别模块包括：
颜色识别单元，配置成对服装有效区域进行颜色识别，确定服装有效区域内所包含的多个目标颜色；
量化检测单元，配置成对每个目标颜色进行量化检测，确定多个目标颜色之间的比例关系；
比例图生成单元，配置成根据多个目标颜色之间的比例关系，生成颜色比例图。
第三方面，本申请实施例提供一种电子设备，包括存储器和处理器，存储器上存储有可在处理器上运行的计算机程序，处理器执行计算机程序时实现上述第一方面所述的方法的步骤。
第四方面，本申请实施例还提供一种具有处理器可执行的非易失的程序代码的计算机可读介质，程序代码使处理器执行如第一方面所述的方法。
本申请实施例带来了以下有益效果：
在本申请实施例提供的人物图像服装颜色识别方法中，首先获取多个目标人物图像；从每个目标人物图像中提取出服装有效区域；通过深度学习对多个服装有效区域进行颜色分析识别，生成颜色比例图；基于多个颜色比例图，生成流行色趋势预测图。该方法基于深度学习，能够对采集于各个地区各个时间段内的大量的人物图像进行服装颜色的识别和检测，从而对各个地区和各个季节的服装颜色进行分析及预测，为服装生产厂商提供可靠的参考。
本申请的其他特征和优点将在随后的说明书中阐述，并且，部分地从说明书中变得显而易见，或者通过实施本申请而了解。本申请的目的和其他优点在说明书、权利要求书以及附图中所特别指出的结构来实现和获得。
为使本申请的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本申请具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种人物图像服装颜色识别方法的流程图；
图2为本申请实施例提供的另一种人物图像服装颜色识别方法的流程图；
图3为本申请实施例提供的另一种人物图像服装颜色识别方法的流程图；
图4为本申请实施例提供的另一种人物图像服装颜色识别方法的流程图；
图5为本申请实施例提供的另一种人物图像服装颜色识别方法的流程图；
图6为本申请实施例提供的另一种人物图像服装颜色识别方法的流程图；
图7为本申请实施例提供的一种人物图像服装颜色识别装置的结构示意图；
图8为本申请实施例提供的电子设备的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请的技术方案进行清楚和完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
目前现有的服装流行色分析及预测，需要通过人工方式对采集的人物图像中的各种服装颜色进行分类统计，此过程需要花费大量的人力物力，并且效率很低。基于此，本申请 实施例提供的人物图像服装颜色识别方法、装置及电子设备，能够对采集于各个地区和各个季节的人物图像，进行服装颜色的识别及预测，为服装生产厂商提供可靠的参考。
为便于对本实施例进行理解，首先对本申请实施例所公开的一种人物图像服装颜色识别方法进行详细介绍。
实施例一：
本申请实施例提供了一种人物图像服装颜色识别方法，参见图1所示，该方法包括以下步骤：
S101：获取多个目标人物图像。
具体的获取图像过程包括以下步骤，参见图2所示：
S201：通过摄像机采集在预设时间段内预设地区的多个人物图像。
在本实施例中，预设时间段包括：春夏季和秋冬季，预设地区包括：服装出口地区中的任一区域，比如：南亚地区、韩国或欧洲等。需要说明的是，预设时间段不仅限于本申请实施例所述的春夏季和秋冬季，还可以采用其它的时间分段方式，比如：春季、夏季、秋季和冬季。
在具体实现的时候，通过摄像机采集某一地区某一时间段内的大量的人物图像，可以直接拍摄时尚杂志中的人物图像，也可以去各种服装店中拍摄模特的人物图像，或者其它场所的人物图像。当然，还可以将人物图像分为男士和女士两类，对这两类人物图像分别进行服装颜色识别和预测。
S202：将多个预设时间段内预设地区的人物图像作为目标人物图像。
将上述采集到的某个地区某个时间段内的大量的人物图像作为目标人物图像，为后续深度学习提供样本数据。
S102：从每个目标人物图像中提取出服装有效区域。
具体的确定服装有效区域过程包括以下步骤，参见图3所示：
S301：采用Sobel边界检测滤镜，对目标人物图像进行边界检测。
具体地，采用GPU Image Sobel Edge Detection Filter滤镜来检测服装有效区域，首先通过Sobel算子计算待处理图像的灰度值。
索贝尔算子(Sobel operator)主要用作边缘检测，在技术上，它是一离散性差分算子，用来运算图像亮度函数的灰度之近似值。在图像的任何一点使用此算子，将会产生对应的灰度矢量或是其法矢量。
Sobel卷积因子为：
Figure PCTCN2018115488-appb-000001
该算子包含两组3x3的矩阵，分别为横向及纵向，将之与图像作平面卷积，即可分别得出横向及纵向的亮度差分近似值。如果以A代表原始图像，Gx及Gy分别代表经横向及纵向边缘检测的图像灰度值，其公式如下：
Figure PCTCN2018115488-appb-000002
Figure PCTCN2018115488-appb-000003
具体计算如下：
Gx＝(-1)*f(x-1,y-1)+0*f(x,y-1)+1*f(x+1,y-1)
+(-2)*f(x-1,y)+0*f(x,y)+2*f(x+1,y)
+(-1)*f(x-1,y+1)+0*f(x,y+1)+1*f(x+1,y+1)
＝[f(x+1,y-1)+2*f(x+1,y)+f(x+1,y+1)]-[f(x-1,y-1)+2*f(x-1,y)+f(x-1,y+1)]
Gy＝1*f(x-1,y-1)+2*f(x,y-1)+1*f(x+1,y-1)
+0*f(x-1,y)0*f(x,y)+0*f(x+1,y)
+(-1)*f(x-1,y+1)+(-2)*f(x,y+1)+(-1)*f(x+1,y+1)
＝[f(x-1,y-1)+2f(x,y-1)+f(x+1,y-1)]-[f(x-1,y+1)+2*f(x,y+1)+f(x+1,y+1)]
其中f(a,b),表示图像(a,b)点的灰度值；
图像的每一个像素的横向及纵向灰度值通过以下公式结合，来计算该点灰度的大小：
Figure PCTCN2018115488-appb-000004
通常，为了提高效率使用不开平方的近似值：
|G|＝|Gx|+|Gy|
如果梯度G大于某一阀值，则认为该点(x,y)为边缘点。
然后可用以下公式计算梯度方向：
Figure PCTCN2018115488-appb-000005
通过计算梯度方向可以得到精确的边缘方向。Sobel算子根据像素点上下和左右邻点灰度加权差，在边缘处达到极值这一现象检测边缘。对噪声具有平滑作用，提供精确的边缘方向信息。
S302：根据边界检测的检测结果，确定服装有效区域。
运用基于RGB色彩模式的阈值肤色识别准则，对人物图像进行肤色检测，精确地获取服装有效区域。
S103：通过预设深度学习模型对多个服装有效区域进行颜色分析识别，生成颜色比例图。
具体的颜色比例图生成过程包括以下步骤，参见图4所示：
S401：对服装有效区域进行颜色识别，确定服装有效区域内所包含的多个目标颜色。
在确定出服装有效区域后，检测服装有效区域内所包含的颜色，比如，红色、蓝色和黄色，为三种目标颜色。
S402：对每个目标颜色进行量化检测，确定多个目标颜色之间的比例关系。
S403：根据多个目标颜色之间的比例关系，生成颜色比例图。
比如，在确定出服装有效区域包含红色、蓝色和黄色三种目标颜色后，对这三种目标颜色进行量化检测，分别检测出每种颜色的颜色量，进而确定出每个目标颜色的颜色量占总颜色量的比值，也就得到多个目标颜色之间的比例关系。进一步地，根据上述确定出的多个目标颜色之间的比例关系，生成颜色比例图。
S104：基于多个颜色比例图，生成流行色趋势预测图。
具体的流行色趋势预测图生成过程包括以下步骤，参见图5所示：
S501：从多个颜色比例图中提取出相同颜色在各个颜色比例图中所占的比例。
S502：根据比例绘制出多个相同颜色的比例变化曲线，生成流行色趋势预测图。
具体地，多个颜色比例图可以是某一时间段内男士服装的颜色比例图，从中提取出相同颜色在各个颜色比例图中的颜色量占比，进而根据颜色量占比数值绘制出比例变化曲线，从而生成流行色趋势预测图。
此外，在对服装有效区域进行颜色识别，确定服装有效区域内所包含的多个目标颜色之后，还包括以下步骤，参见图6所示：
S601：对每个目标颜色进行预设语义匹配，得到颜色语义分析结果。
比如，与蓝色匹配的语义是纯净，与金黄色匹配的语义是活力，与绿色匹配的语义是青春，与红色匹配的语义是热情，与黄色匹配的语义是年轻，与紫色匹配的语义是神秘等，在确定出服装有效区域内所包含的多个目标颜色后，进行颜色和语义的匹配，得到每个目标人物图像中服装有效区域所对应的语义分析结果。
在本申请实施例提供的人物图像服装颜色识别方法中，首先获取多个目标人物图像；从每个目标人物图像中提取出服装有效区域；通过深度学习对多个服装有效区域进行颜色分析识别，生成颜色比例图；基于多个颜色比例图，生成流行色趋势预测图。该方法基于深度学习，能够对采集于各个地区各个时间段内的大量的人物图像进行服装颜色的识别和检测，从而对各个地区和各个季节的服装颜色进行分析及预测，为服装生产厂商提供可靠的参考。
实施例二：
本申请实施例提供一种人物图像服装颜色识别装置，参见图7所示，该装置包括：
图像获取模块71，配置成获取多个目标人物图像；
区域提取模块72，配置成从每个人物图像中提取出服装有效区域；
颜色识别模块73，配置成通过预设深度学习模型对多个服装有效区域进行颜色分析识别，生成颜色比例图；
图表生成模块74，配置成基于多个颜色比例图，生成流行色趋势预测图。
其中，颜色识别模块73包括：
颜色识别单元731，配置成对服装有效区域进行颜色识别，确定服装有效区域内所包含的多个目标颜色；
量化检测单元732，配置成对每个目标颜色进行量化检测，确定多个目标颜色之间的比例关系；
比例图生成单元733，配置成根据多个目标颜色之间的比例关系，生成颜色比例图。
本申请实施例所提供的人物图像服装颜色识别装置中，各个模块的工作过程与前述人物图像服装颜色识别方法具有相同的技术特征，因此，同样可以实现上述功能，在此不再赘述。
实施例三：
本申请实施例还提供一种电子设备，参见图8所示，该电子设备包括：处理器80，存储器81，总线82和通信接口83，所述处理器80、通信接口83和存储器81通过总线82连接；处理器80配置成执行存储器81中存储的可执行模块，例如计算机程序。处理器执行计算机程序时实现如方法实施例所述的方法的步骤。
其中，存储器81可能包含高速随机存取存储器(RAM，Random Access Memory)，也可能还包括非不稳定的存储器(non-volatile memory)，例如至少一个磁盘存储器。通过至少一个通信接口83(可以是有线或者无线)实现该系统网元与至少一个其他网元之间的通信连接，可以使用互联网，广域网，本地网，城域网等。
总线82可以是ISA总线、PCI总线或EISA总线等。所述总线可以分为地址总线、数据总线和控制总线等。为便于表示，图8中仅用一个双向箭头表示，但并不表示仅有一根总线或一种类型的总线。
其中，存储器81配置成存储程序，所述处理器80在接收到执行指令后，执行所述程序，前述本申请实施例任一实施例揭示的流过程定义的装置所执行的方法可以应用于处理器80中，或者由处理器80实现。
处理器80可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器80中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器80可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)和网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(Digital Signal Processing，简称DSP)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)、现场可编程门阵列(Field-Programmable Gate Array，简称FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器81，处理器80读取存储器81中的信息，结合其硬件完成上述方法的步骤。
本申请实施例所提供的网络设备的定位方法的计算机程序产品，包括存储了处理器可执行的非易失的程序代码的计算机可读存储介质，所述程序代码包括的指令可配置成执行前面方法实施例中所述的方法，具体实现可参见方法实施例，在此不再赘述。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的装置及电子设备的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
附图中的流程图和框图显示了根据本申请的多个实施例方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个配置成实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功 能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
在本申请的描述中，需要说明的是，术语“中心”、“上”、“下”、“左”、“右”、“竖直”、“水平”、“内”和“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位或者以特定的方位构造和操作，因此不能理解为对本申请的限制。此外，术语“第一”、“第二”和“第三”仅用于描述目的，而不能理解为指示或暗示相对重要性。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上所述实施例，仅为本申请的具体实施方式，用以说明本申请的技术方案，而非对其限制，本申请的保护范围并不局限于此，尽管参照前述实施例对本申请进行了详细地说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员 在本申请揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本申请实施例技术方案的精神和范围，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (10)

  1. 一种人物图像服装颜色识别方法，其特征在于，包括：
    获取多个目标人物图像；
    从每个所述目标人物图像中提取出服装有效区域；
    通过预设深度学习模型对多个所述服装有效区域进行颜色分析识别，生成颜色比例图；
    基于多个所述颜色比例图，生成流行色趋势预测图。
  2. 根据权利要求1所述的方法，其特征在于，所述获取多个目标人物图像，具体包括：
    通过摄像机采集在预设时间段内预设地区的多个人物图像；所述预设时间段包括：春夏季、秋冬季；所述预设地区包括：服装出口地区中的任一区域；
    将多个所述预设时间段内预设地区的人物图像作为所述目标人物图像。
  3. 根据权利要求1所述的方法，其特征在于，所述从每个所述目标人物图像中提取出服装有效区域，具体包括：
    采用Sobel边界检测滤镜，对所述目标人物图像进行边界检测；
    根据所述边界检测的检测结果，确定所述服装有效区域。
  4. 根据权利要求1所述的方法，其特征在于，所述通过预设深度学习模型对所述服装有效区域进行颜色分析识别，生成颜色比例图，具体包括：
    对所述服装有效区域进行颜色识别，确定所述服装有效区域内所包含的多个目标颜色；
    对每个所述目标颜色进行量化检测，确定多个所述目标颜色之间的比例关系；
    根据多个所述目标颜色之间的比例关系，生成颜色比例图。
  5. 根据权利要求1所述的方法，其特征在于，所述基于多个所述颜色比例图，生成流行色趋势预测图，具体包括：
    从多个所述颜色比例图中提取出相同颜色在各个所述颜色比例图中所占的比例；
    根据所述比例绘制出多个所述相同颜色的比例变化曲线，生成所述流行色趋势预测图。
  6. 根据权利要求4所述的方法，其特征在于，在所述对所述服装有效区域进行颜色识别，确定所述服装有效区域内所包含的多个目标颜色之后，还包括：
    对每个所述目标颜色进行预设语义匹配，得到颜色语义分析结果。
  7. 一种人物图像服装颜色识别装置，其特征在于，包括：
    图像获取模块，配置成获取多个目标人物图像；
    区域提取模块，配置成从每个所述目标人物图像中提取出服装有效区域；
    颜色识别模块，配置成通过预设深度学习模型对多个所述服装有效区域进行颜色分析识别，生成颜色比例图；
    图表生成模块，配置成基于多个所述颜色比例图，生成流行色趋势预测图。
  8. 根据权利要求7所述的装置，其特征在于，所述颜色识别模块包括：
    颜色识别单元，配置成对所述服装有效区域进行颜色识别，确定所述服装有效区域内所包含的多个目标颜色；
    量化检测单元，配置成对每个所述目标颜色进行量化检测，确定多个所述目标颜色之间的比例关系；
    比例图生成单元，配置成根据多个所述目标颜色之间的比例关系，生成颜色比例图。
  9. 一种电子设备，包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现上述权利要求1至6任一项所述的方法的步骤。
  10. 一种具有处理器可执行的非易失的程序代码的计算机可读介质，其特征在于，所述程序代码使所述处理器执行所述权利要求1至6任一项所述的方法。
PCT/CN2018/115488 2017-11-14 2018-11-14 人物图像服装颜色识别方法、装置及电子设备 WO2019096174A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711126273.0A CN107766861A (zh) 2017-11-14 2017-11-14 人物图像服装颜色识别方法、装置及电子设备
CN201711126273.0 2017-11-14

Publications (1)

Publication Number Publication Date
WO2019096174A1 true WO2019096174A1 (zh) 2019-05-23

Family

ID=61278783

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/115488 WO2019096174A1 (zh) 2017-11-14 2018-11-14 人物图像服装颜色识别方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN107766861A (zh)
WO (1) WO2019096174A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111680201A (zh) * 2019-12-31 2020-09-18 江苏工程职业技术学院 服装潮流趋势样品展示板的制作方法及其潮流趋势册
CN113159826A (zh) * 2020-12-28 2021-07-23 武汉纺织大学 基于深度学习的服装流行元素预测的系统及方法
CN113222971A (zh) * 2021-05-31 2021-08-06 深圳市蝶讯网科技股份有限公司 一种色彩和搭配浏览款式的方法、计算机设备及存储介质
CN113727072A (zh) * 2021-08-31 2021-11-30 浙江吉利控股集团有限公司 安全带的智能显示方法和系统
CN113763408A (zh) * 2021-09-29 2021-12-07 上海海事大学 一种无人船航行过程中的图像快速辨别水面下水草的方法
CN114120307A (zh) * 2021-12-02 2022-03-01 壹沓科技(上海)有限公司 显示内容的识别方法、装置、设备和存储介质

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107766861A (zh) * 2017-11-14 2018-03-06 深圳码隆科技有限公司 人物图像服装颜色识别方法、装置及电子设备
CN110503084B (zh) * 2018-05-18 2024-03-01 广州腾讯科技有限公司 一种图像中的文字区域识别方法和装置
CN110147854A (zh) * 2018-07-19 2019-08-20 深圳码隆科技有限公司 服装识别方法、计算机设备和存储介质
CN109034255A (zh) * 2018-08-02 2018-12-18 深圳码隆科技有限公司 服装销量的预测方法及装置
CN111079757B (zh) * 2018-10-19 2024-09-20 北京奇虎科技有限公司 服饰属性识别方法、装置及电子设备
JP6511204B1 (ja) * 2018-10-31 2019-05-15 ニューラルポケット株式会社 情報処理システム、情報処理装置、サーバ装置、プログラム、又は方法
JP6592755B1 (ja) * 2019-04-05 2019-10-23 ニューラルポケット株式会社 情報処理システム、情報処理装置、サーバ装置、プログラム、又は方法
CN112801681A (zh) * 2019-11-12 2021-05-14 杭州海康威视数字技术股份有限公司 产品流行趋势的分析方法、装置、电子设备及存储介质
CN111145242A (zh) * 2019-12-26 2020-05-12 赛维时代科技股份有限公司 预测流行趋势的方法、智能设备和计算机可读存储介质
CN111325806A (zh) * 2020-02-18 2020-06-23 苏州科达科技股份有限公司 基于语义分割的服装颜色识别方法、装置和系统
CN112990012A (zh) * 2021-03-15 2021-06-18 深圳喜为智慧科技有限公司 一种遮挡条件下的工装颜色识别方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104484450A (zh) * 2014-12-25 2015-04-01 广东欧珀移动通信有限公司 基于图像的服饰搭配推荐方法和服饰搭配推荐装置
CN105069466A (zh) * 2015-07-24 2015-11-18 成都市高博汇科信息科技有限公司 基于数字图像处理的行人服饰颜色识别方法
CN106033547A (zh) * 2015-03-12 2016-10-19 阿里巴巴集团控股有限公司 颜色搭配评价方法、服饰搭配推荐方法及装置
CN107067011A (zh) * 2017-03-20 2017-08-18 北京邮电大学 一种基于深度学习的车辆颜色识别方法与装置
CN107766861A (zh) * 2017-11-14 2018-03-06 深圳码隆科技有限公司 人物图像服装颜色识别方法、装置及电子设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9953217B2 (en) * 2015-11-30 2018-04-24 International Business Machines Corporation System and method for pose-aware feature learning
CN107080435A (zh) * 2017-05-27 2017-08-22 文曙东 虚拟衣橱管理系统和方法以及基于该系统的服饰销售方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104484450A (zh) * 2014-12-25 2015-04-01 广东欧珀移动通信有限公司 基于图像的服饰搭配推荐方法和服饰搭配推荐装置
CN106033547A (zh) * 2015-03-12 2016-10-19 阿里巴巴集团控股有限公司 颜色搭配评价方法、服饰搭配推荐方法及装置
CN105069466A (zh) * 2015-07-24 2015-11-18 成都市高博汇科信息科技有限公司 基于数字图像处理的行人服饰颜色识别方法
CN107067011A (zh) * 2017-03-20 2017-08-18 北京邮电大学 一种基于深度学习的车辆颜色识别方法与装置
CN107766861A (zh) * 2017-11-14 2018-03-06 深圳码隆科技有限公司 人物图像服装颜色识别方法、装置及电子设备

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111680201A (zh) * 2019-12-31 2020-09-18 江苏工程职业技术学院 服装潮流趋势样品展示板的制作方法及其潮流趋势册
CN111680201B (zh) * 2019-12-31 2023-12-22 江苏工程职业技术学院 服装潮流趋势样品展示板的制作方法及其潮流趋势册
CN113159826A (zh) * 2020-12-28 2021-07-23 武汉纺织大学 基于深度学习的服装流行元素预测的系统及方法
CN113222971A (zh) * 2021-05-31 2021-08-06 深圳市蝶讯网科技股份有限公司 一种色彩和搭配浏览款式的方法、计算机设备及存储介质
CN113727072A (zh) * 2021-08-31 2021-11-30 浙江吉利控股集团有限公司 安全带的智能显示方法和系统
CN113763408A (zh) * 2021-09-29 2021-12-07 上海海事大学 一种无人船航行过程中的图像快速辨别水面下水草的方法
CN114120307A (zh) * 2021-12-02 2022-03-01 壹沓科技(上海)有限公司 显示内容的识别方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN107766861A (zh) 2018-03-06

Similar Documents

Publication Publication Date Title
WO2019096174A1 (zh) 人物图像服装颜色识别方法、装置及电子设备
JP6336117B2 (ja) 建物高さの計算方法、装置及び記憶媒体
EP3806064A1 (en) Method and apparatus for detecting parking space usage condition, electronic device, and storage medium
WO2017092431A1 (zh) 基于肤色的人手检测方法及装置
WO2019114036A1 (zh) 人脸检测方法及装置、计算机装置和计算机可读存储介质
CN109154978A (zh) 用于检测植物疾病的系统和方法
EP2811423A1 (en) Method and apparatus for detecting target
CN110210448B (zh) 一种智能人脸皮肤老化程度的识别与评估方法
US20150016687A1 (en) Method, system and computer storage medium for face detection
CN101599175B (zh) 确定拍摄背景发生改变的检测方法及图像处理设备
WO2020253508A1 (zh) 异常细胞检测方法、装置及计算机可读存储介质
CN106991421A (zh) 一种身份证信息提取系统
WO2019119515A1 (zh) 人脸分析、过滤方法、装置、嵌入式设备、介质和集成电路
WO2019096177A1 (zh) 图像识别方法、系统以及电子设备
CN104636759A (zh) 一种获取图片推荐滤镜信息的方法及图片滤镜信息推荐系统
CN110991452A (zh) 一种车位框检测方法、装置、设备及可读存储介质
CN108229473A (zh) 车辆年检标签检测方法及装置
CN112784835A (zh) 圆形印章的真实性识别方法、装置、电子设备及存储介质
JP6819445B2 (ja) 情報処理装置、制御方法、及びプログラム
CN111582278B (zh) 人像分割方法、装置及电子设备
CN113947730A (zh) 遥感数据识别方法、装置、电子设备及可读存储介质
JP6463095B2 (ja) 画像検索装置及び方法
JP2014016710A (ja) 対象物検出装置及びプログラム
CN116363076A (zh) 一种实验电路的电流流向判断方法和装置
KR102416714B1 (ko) 3차원 이미지 및 딥러닝을 활용한 도시 규모 나무 지도 작성 시스템 및 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18877617

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18877617

Country of ref document: EP

Kind code of ref document: A1