KR20140124087A - System and method for recommending hair based on face and style recognition - Google Patents

Abstract

The present invention relates to a system and a method for recommending a personal style by using a user terminal, and a recording medium storing a program code for executing the method with a computer and, more particularly, a system and a method for recommending a personal style by using a user terminal, and a recording medium storing a program code for executing the method with a computer, which can analyze a face brightness image transmitted through a camera in addition to basic information such as the body size of a user, can automatically select the tone of clothing according to face colors, and can provide clothing styles in which the size and color of the clothing are combined with each other, thereby progressing an optimal clothing co-ordination for the user and providing a clothing seller with a customized clothing service such that the clothing seller can obtain the maximum profit.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a personal style recommendation system and method using a user terminal, and a recording medium storing program codes for causing a computer to execute the method.

The present invention relates to a personal style recommendation system and method using a user terminal, and a recording medium storing a program code for causing a computer to execute the method. More particularly, the present invention relates to a personal style recommendation system using a user terminal, By analyzing the image, the clothing tone of the clothing is automatically selected according to the face color, and the clothing style combining the clothing and size of the corresponding color is provided. Thus, the clothing coordination is optimized for the user, and the clothing company provides the custom clothing service The present invention relates to a personal style recommendation system and method using a user terminal, and a recording medium storing program codes for causing the computer to execute the method.

2. Description of the Related Art Recent mobile communication terminals all have a large screen having color display characteristics of tens of thousands of colors or more and a camera or the like is built in to capture a megapixel image or a screen shot through the screen having a high resolution have.

Therefore, various functions that can utilize the performance of the mobile communication terminal are being developed continuously. One of them is the coordination function. From the function of simply providing the user with additional information of the weather and the coordination information of the recommended costume, it is possible to coordinate the costumes in a desired style by using the costume data prepared in advance after accessing the special Internet server, There are also services available to make purchases.

For example, in Korean Patent Application No. 2001-17399 (coordination information providing service system and method of operating this system), after accessing a specific Internet site by using a mobile communication terminal, And Korean Patent Application No. 2001-22149 (Apparel sales system and method using image synthesis and editing technology through a communication network) suggests a system and method for obtaining advice on whether to select a product, Apparel sales that use image synthesis and editing technology through a communication network that enables users to select clothing to purchase after accessing a specific web site using a wireless communication network, and to tailor, process, and purchase the product according to the taste, preference, System and method.

Most of the conventional costume coordination information is obtained by accessing a web server or a network server that provides information using a communication network or the Internet, and then receiving information necessary for coordination on-line, or performing image synthesis and editing It is a way to make purchasing clothes suitable for oneself using technology.

However, until now, the coordination system is limited to the user's body size, so that the costume information is not given. Appropriate color clothing information according to the user's face color is not given.

As a result, there is a limitation in grasping and applying the most suitable color information to oneself.

For example, if the face tone is black, the color of the overly bright tones should be avoided because the contrast is emphasized and the face looks darker.

However, since the coordination information according to the image up to the present has provided the service considering only the size of the body regardless of the face tone, there was a problem in choosing the clothes which best suits the user himself.

The present invention solves the above-mentioned problems. When a face is shot with a cell phone image at the same time as the body size information of the user, the user can automatically select and send clothes suitable for a face tone, I have a purpose to help you.

As means for solving the above problem,

The present invention relates to an image processing apparatus, including a video device 110 for capturing a face image of a user, a memory 120 storing an image of a user photographed through the video device and a user's body size, A user terminal (100) having a communication device (130); And a garment selection device (200) for inputting and processing a body size of the user including the face image of the user from the user terminal (100) The clothing selection apparatus 200 includes a face detection unit 210 for receiving an image input through the imaging apparatus through a communication system and detecting a face region in the image; A skin region detection unit 220 for detecting a skin region in the image; A face region extracting unit 230 for detecting a face image from a common image by matching the face detecting unit, the skin region detecting unit, and the face region detecting unit; A face pigment function determiner 240 for comparing the face image detected by the face region extracting unit with a reference image image to determine the overall face brightness; A color database 250 for preparing colors in advance to match clothing colors suitable for a face image discriminated by the face coloring matter function discriminator; A matching unit 260 for matching the face image discriminated by the face coloring matter function discriminator and the clothing color according to the face color stored in advance in the database; An apparel database 270 for preparing clothing corresponding to the color and the body dimensions of the user determined by the matching unit; And a garment selector 280 for selecting garments stored in the clothing database and wearing clothing on a virtual human image, and transmitting the clothing to a user terminal through a communication system.

The user terminal 100 may be a device for processing a digital image such as a digital camera or a digital camcorder, or a TV, a DVD player, a computer, a PDA, a mobile phone, or a PMP.

(A) receiving a user's body information such as a key or a weight from a user terminal and receiving an image of the user's upper body at the same time; (b) detecting a skin region in the input image; (c) detecting a face region in the input image; (d) determining a face image of a user based on a common region between the skin region and the face region, and extracting a user's face color using a face pigment function discriminator; (e) determining a face color of the user based on color information previously stored in the database with reference to a skin color present in the face determined in the step (d); (f) selecting clothes suitable for the user's basic body dimensions and the user's face color by referring to the clothing database, and wearing the clothes on the virtual human image and transmitting the clothes to the user terminal.

The step of detecting the face region may include detecting a face using the AdaBoost method.

A program code for receiving physical information such as a user's key and / or weight from a user terminal and receiving an image of a user's upper body taken at the same time; A program code for detecting a skin region in an input image; A program code for detecting a face region in the input image; A program code for determining a common area between the skin area and the face area as a face; A program code for determining a user's face color based on color information stored in advance in a database with reference to a skin color present in a face; And a program code for referring to the clothing database and selecting clothes suitable for the basic body dimensions of the user and the face color of the user, wearing the clothes on the virtual human image, and transmitting the clothes to the user terminal.

As described above, according to the present invention, when a face is shot with a cell phone image simultaneously with the body size information of the user, the user can automatically select clothes suitable for the face tone, do.

1 is a block diagram of a personal style recommendation system according to the present invention;
FIG. 2 is a diagram illustrating an example of inputting an image and a body dimension through a user terminal in the present invention. FIG.
FIG. 3 is an exemplary view showing a virtual image matching a face color displayed on a user terminal in the present invention. FIG.
FIG. 4 is an exemplary view showing a virtual clothing image matching a face color on a user terminal in the present invention. FIG.
5 is an operational flowchart for implementing the personal style recommendation method of the present invention;

The operation principle of the preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings and description. It should be understood, however, that the drawings and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the invention, and are not to be construed as limiting the present invention.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The terms used below are defined in consideration of the functions of the present invention, which may vary depending on the user, intention or custom of the operator. Therefore, the definition should be based on the contents throughout the present invention.

It is to be understood that both the foregoing general description and the following detailed description of the present invention are exemplary and explanatory and are intended to provide further explanation of the invention as claimed. The configuration is omitted as much as possible, and a functional configuration that should be additionally provided for the present invention is mainly described.

Those skilled in the art will readily understand the functions of the components that have been used in the prior art among the functional configurations that are not shown in the following description, The relationship between the elements and the components added for the present invention will also be clearly understood.

In order to efficiently explain the essential technical features of the present invention, the following embodiments properly modify the terms so that those skilled in the art can clearly understand the present invention, It is by no means limited.

As a result, the technical idea of the present invention is determined by the claims, and the following embodiments are merely illustrative of the technical idea of the present invention in order to efficiently explain the technical idea of the present invention to a person having ordinary skill in the art to which the present invention belongs. .

1 is a block diagram of a personal style recommendation system according to the present invention;

FIG. 2 is a diagram illustrating an example of inputting an image and a body dimension through a user terminal in the present invention. FIG.

FIG. 3 is an exemplary view showing a virtual image matching a face color displayed on a user terminal in the present invention. FIG.

FIG. 4 is an exemplary view showing a virtual clothing image matching a face color on a user terminal in the present invention. FIG.

5 is an operational flowchart for executing the personal style recommendation method of the present invention,

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a preferred embodiment of the present invention will be described with reference to the block diagrams or process flowcharts for explaining a method and an apparatus for performing preferential color conversion of skin by applying face detection and skin area detection. . At this point, it will be appreciated that the combinations of blocks and flowchart illustrations in the process flow diagrams may be performed by computer program instructions. These computer program instructions may be stored in a general purpose computer, special purpose computer, or other programmable data processing

The instructions that are executed through the processor of the computer or other programmable data processing equipment will create a means for performing the functions described in the flowchart block (s). These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory The instructions stored in the block diagram (s) are also capable of producing manufacturing items containing instruction means for performing the functions described in the flowchart block (s). The computer program instructions may be loaded onto a computer or other programmable data processing equipment so that a series of operating steps may be performed on the computer or other programmable data processing equipment to create a computer- It is also possible for the instructions to perform the processing equipment to provide steps for executing the functions described in the flowchart block (s).

In addition, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative implementations, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may actually be executed substantially concurrently, or the blocks may sometimes be performed in reverse order according to the corresponding function.

The term " module " or " table " used in the present embodiment includes a hardware component , And the module performs certain functions. However, a module is not limited to software or hardware. A module may be configured to reside on an addressable storage medium and configured to play back one or more processors. Thus, by way of example, a module may include components such as software components, object-oriented software components, class components and task components, and processes, functions, attributes, procedures, subroutines , Segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and modules may be combined into a smaller number of components and modules or further separated into additional components and modules. In addition, components and modules may be implemented to play one or more CPUs in the device.

The components of the present invention mainly include a video device 110 for capturing a face image of a user, a memory 120 for storing an image of a user photographed through the video device and a user's body size, A user terminal (100) having a communication device (130) for communicating with the outside; And a clothes selection device 200 for receiving and processing the user's body dimensions including the user's face image from the user terminal 100.

The clothing selection device 200 includes a face detection unit 210 for receiving an image input through the imaging device through a communication system and detecting a face region in the image, A face region extracting unit 230 for detecting a face image from a common image by matching the face detecting unit with the skin region detecting unit and the face region detecting unit; A face coloring function determiner 240 for determining the overall face brightness in comparison with an image, a color database 250 for preparing colors in advance to match clothes colors suitable for the face image discriminated by the face coloring function discriminator, ; A matching unit 260 for matching the face image discriminated by the face coloring matter function discriminator and the clothing color according to the face color stored in advance in the database; An apparel database 270 for preparing clothing corresponding to the color determined by the matching unit; And a clothes selector 280 for selecting clothing stored in the clothing database and wearing clothes on a virtual human image and transmitting the clothing to a user terminal through a communication system.

The user terminal 100 may be a TV or a DVD player as well as a device for processing a digital image such as a digital camera or a digital camcorder. Also, the user terminal 100 may be a video playback device such as a computer, PDA, The invention particularly focuses on imaging devices using mobile phones.

In addition, basic user information such as a user's height or weight age is inputted through the input unit and stored in a memory through the user terminal 100. In addition, contents stored in the memory are transmitted through a communication device, Transfer it with the image.

The face detecting unit 210 detects a face from an input image. In the image, spatial position information of the face region is output. Various methods can be applied to detect the face. In one embodiment, the AdaBoost method, the neural network based method, and the statistical method exist. AdaBoost is a structure in which several stages composed of Weak classifiers are connected in a cascade form. Therefore, if the detection fails at the present stage, the subwindow is determined as a non-face image, that is, a non-face. Then, only the sub window succeeding the detection at the present stage is inputted to the next stage, and if the detection succeeds to the last stage, it is determined as 'face'. It is possible to learn the classifier by using a facial appearance that is inclined in the X, Y, and Z axes, respectively, in order to discriminate a face that is not a front face, or a face that is turned or tilted. In order to detect faces of various sizes, it is possible to apply a case in which the size of a sub-window parallel to the XY-axis is changed rather than a face is detected with a single window.

In the neural network based detection method, the network connected to the neural network examines the small windows of the image and determines whether each window contains a face. Also, it can provide higher performance than adjusting one network by adjusting multiple networks.

A neural network circuit can be trained by using a case where a negative example is extracted and a face is identified.

Statistical methods can also be applied. Statistical methods can recognize objects by applying a classifier based on the statistics of localized parts. The classifier calculates the result of matching each part and the image and obtains the probability according to the condition of the classification. And we decide about things that are recognized through likelihood ratio test. It also suggests increasing the steps from low resolution to high resolution to find the image.

The skin region detection unit 220 extracts pixels corresponding to the skin color from the input image using a standard skin color model unit defined in the color space.

The result extracted at this time is not limited to the skin area. This is because a pixel having an error within a certain range of skin color is extracted, so that a background having a color similar to a skin color or a pixel of another image can be extracted.

On the other hand, in order to improve the speed of processing, the skin region detecting unit extracts a skin region from a portion detected as a face, rather than a whole image, and examines the degree of skin color in a region detected as a face, Can be extracted.

The face region extracting unit 230 compares the face determined by the face detecting unit and the region in which the skin color extracted by the skin region detecting unit is present, and determines a region that is commonly overlapped as a face region. And if the common area exists, verifying that the corresponding area is a face area. That is, it may include a process of determining whether the face corresponds to an actual face based on the ratio of the pixels corresponding to the skin color in the face area, the size of the face area, and the like. As a result of the determination, if the input image is not a face region, the input image can be output without conversion. The skin color existing in the facial region judged by the facial region extracting unit may be referred to as the skin color used in the image.

The face coloring matter function determiner 240 converts the RGB system of the detected thermal region image into the HSV system. Then, the facial color belonging function for the color value and the saturation value of each pixel is calculated using the facial color belonging function for each color stored in the storage unit, and a facial color filter image is obtained by performing a threshold operation on the result. Next, the facial color filter image and the brightness value monochrome image are cumulatively calculated to calculate the facial color filter accumulation image, the monochrome cumulative image and the monochrome cumulative sum, and the calculated facial color filter cumulative image, Store the squares in the storage. Then, the color matching unit 260 and the color database 250, which prepare clothes colors suitable for the face image discriminated by the face coloring matter function determiner 240, are used to determine clothing colors most suitable for the user.

The clothing data base 270 prepares clothing corresponding to the color judged by the matching unit 260. The clothing selector 280 selects clothes stored in the clothing data base 270 and transmits the clothes to the communication system To the user terminal so that the user can grasp the clothes suitable for him / her.

Hereinafter, the operation procedure of the present invention will be described.

When a user's upper body image is input through the user terminal, the face region is detected. At this time, a Gentle AdaBoost (Gentle AdaBoost) based face detection method, a neural network method, and a statistical method can be applied to detect a face region. In particular, it is necessary to ensure fast execution speed and low false rejection rate (FRR) so that it can be applied to image acquisition or output devices.

A face skin color region is detected. Based on the information on the skin color defined by the standard skin color region, pixels corresponding to the skin color are detected from the pixels. If the skin color of the region having the outline of the face is high, the skin color model can be set by distributing the skin color of the face region on the color space, considering the color of the face region as the skin color. In one embodiment, the image reference skin color model can be set in 2D elliptical form. Then, an actual facial skin area is detected based on the skin color model.

When the face area is detected, the face color of the user is determined based on the color stored in the color database.

When the face color of the user is determined, the clothing selector selects clothing suitable for the user through the clothing database and transmits the selected clothing to the user terminal.

100: User terminal
110: Imaging device
120: Memory
130: Communication device
200: Apparel selection device
210:
220: skin area detection unit
230: Face area extracting unit
240: Facial pigment function discriminator
250: Color database
260:
270: Clothing database
280: Clothing selector

Claims (5)

A memory 120 for storing an image of a user photographed through the image device and a user's body size, a communication device for communicating contents stored in the memory with the external device, A user terminal (100) having a device (130); And a garment selection device (200) for inputting and processing a body size of the user including the face image of the user from the user terminal (100)
The garment selecting apparatus (200)
A face detection unit 210 receiving an image input through the image device through a communication system and detecting a face region in the image; A skin region detection unit 220 for detecting a skin region in the image; A face region extracting unit 230 for detecting a face image from a common image by matching the face detecting unit, the skin region detecting unit, and the face region detecting unit; A face pigment function determiner 240 for comparing the face image detected by the face region extracting unit with a reference image image to determine the overall face brightness; A color database 250 for preparing colors in advance to match clothing colors suitable for a face image discriminated by the face coloring matter function discriminator; A matching unit 260 for matching the face image discriminated by the face coloring matter function discriminator and the clothing color according to the face color stored in advance in the database; An apparel database 270 for preparing clothing corresponding to the color and the body dimensions of the user determined by the matching unit; And a clothes selector (280) for selecting clothing stored in the clothing database and wearing clothes on a virtual human image and transmitting the clothing to a user terminal through a communication system. . The method according to claim 1,
The user terminal 100 may be a device for processing a digital image such as a digital camera or a digital camcorder, or a TV, a DVD player, a computer, a PDA, a mobile phone, or a PMP. Recommended system. (a) receiving physical information such as a user's key or weight from a user terminal and receiving an image of a user's upper body at the same time;
(b) detecting a skin region in the input image;
(c) detecting a face region in the input image;
(d) determining a face image of a user based on a common region between the skin region and the face region, and extracting a user's face color using a face pigment function discriminator;
(e) determining a face color of the user based on the color information stored in advance in the database with reference to the skin color existing in the face determined in the step (d);
(f) selecting clothes suitable for the user's basic body dimensions and the user's face color by referring to the clothing database, and wearing the clothes on the virtual human image, and transmitting the clothes to the user terminal Personal style recommendation method used. The method of claim 3,
The step of detecting the face region comprises:
And detecting a face by using the AdaBoost method. A program code for inputting physical information such as a user's key and / or weight from a user terminal and receiving an image of a user's upper body taken at the same time;
A program code for detecting a skin region in an input image;
A program code for detecting a face region in the input image;
A program code for determining a common area between the skin area and the face area as a face;
A program code for determining a user's face color based on color information stored in advance in a database with reference to a skin color present in a face;
And a program code for referring to the clothing database and selecting clothing suitable for the basic body dimensions of the user and the face color of the user, and wearing the clothes on the virtual human image and transmitting the clothes to the user terminal. A recording medium storing a program code which recommends a personal style.

Images