KR20160109404A - Method and apparatus for appraising item - Google Patents

Abstract

The present invention relates to a method and an apparatus for appraising an item. For this, the method for appraising an item includes a step of loading the photographed image of the item; a step of extracting a comparison object image included in the photographed image, by analyzing the photographed image; and a step of determining whether the item is genuine based on a matching rate between a reference image to the item and the comparison object image.

Description

[0001] METHOD AND APPARATUS FOR APPARATUS [0002]

The present invention relates to a method and apparatus for appraising an article.

Recently, due to the prolonged recession and consumer rationality, transactions for used goods are gradually increasing. As IT technology develops, such transactions are gradually spreading in the form of electronic commerce using a user terminal such as a computer or a smart phone. However, in the case of such electronic commerce, the frequency of fraudulent transactions is gradually increasing due to the fact that the user can not directly confirm the goods and purchase them, and even if the user directly confirms the goods, it is difficult to accurately determine whether the goods are genuine or not It is true.

In other words, when the merchandise is traded for a low price, the amount of damage is small in the case of low-priced merchandise. However, since the amount of damage is high for expensive articles such as expensive bags, watches and wallets, .

In this regard, Korean Patent Laid-Open Publication No. 2014-0048813, titled " Used Commodity Transaction / Payment Mediation System and Intermediate Method ", exists.

It is an object of the present invention to provide a method and apparatus for an appraisal of an article that assists a customer in knowing whether the article is genuine or not, even if the customer does not know a specific emotional method for the article.

According to an aspect of the present invention, there is provided an emotion method for emulating an authenticity of an article of the present invention, the method comprising: loading an image of an article; Extracting a comparison object image included in the captured image by analyzing the captured image; And determining whether the article is genuine based on a matching rate between the comparison image and the reference image for the article.

Also, the comparison image includes a zipper image of the article contained in the shot image, the zipper image including an image of the front portion of the zipper exposed to the outside of the article and the back portion of the zipper present on the opposite side of the front portion of the zipper Wherein the step of determining whether the item is genuine or not comprises the steps of extracting a pattern of the product logo formed on at least one of the slide portion and the stopper of the zipper in the image of the back portion of the zipper, .

In addition, the step of determining whether the article is genuine may include extracting a pattern of at least one of a zipper, a slide, a handle, a band, and a stopper included in the zipper image, The pattern of the slide part may include a front part shape of the slide part, a shape of the back part, a shape of the side part, and a separation distance between the front part and the back part of the slide part.

Also, the comparison image includes an image for at least one of a trademark, a serial number, and a certificate included in the photographed image, and the step of determining whether the article is authentic includes determining the type and size of the trademark included in the photographed image, The number of the serial number, and the image of at least one of the font and the certificate against the reference image.

The method of the present invention may further include the step of calculating an appraised value of the article based on the emotion information including whether the article is authentic or not, according to the step of determining whether the article is genuine or not.

Further, the emotion information may further include at least one of a use period of the article, a model name, an appearance state, and demand information.

In addition, the first estimation value is calculated based on the authenticity of the goods, model name, and demand information, and the final estimation value can be derived based on the use period and the appearance state of the goods at the first estimation value.

In addition, the step of extracting the comparison object image included in the photographed image may further include extracting an entire pattern of the photographed image, wherein the appearance state includes a number and a size of the scratches and stains detected through the analysis of the entire pattern, The grades can be determined based on the weights that are variably set according to the location of the scratches and smudges.

The computer-readable storage medium of the present invention for solving the above-mentioned problems may include a program for implementing the above-described method.

In order to solve the above problems, an emotion device for judging whether an article of the present invention is genuine or not has a function of extracting a comparative image included in a photographed image by loading a photographed image of the article and analyzing the photographed image, And a controller for determining whether the article is genuine based on the agreement rate between the image and the reference image for the article.

Also, the comparison image includes a zipper image of the article contained in the shot image, the zipper image including an image of the front portion of the zipper exposed to the outside of the article and the back portion of the zipper present on the opposite side of the front portion of the zipper And the control unit can extract a pattern of the product logo formed on at least one of the slide portion and the stopper of the zipper and compare the reference image with the pattern of the product logo in the image of the back portion of the zipper.

The control unit may extract at least one pattern of the zipper, the slide unit, the handle, the band, and the stopper included in the zipper image. The control unit may extract at least one pattern of the zipper, the slide unit, the handle, the band, And the reference image may be further compared. The pattern of the slide part may include a front part shape, a back part shape, a side part shape, and a separation distance between a front part and a back part of the slide part.

Also, the comparison image includes an image for at least one of a trademark, a serial number and a certificate included in the photographed image, and the control unit displays the shape and size of the trademark included in the photographed image, the number of the serial number, And the reference image.

Further, the control unit may further calculate the estimated value of the article based on the feeling information including whether the article is authentic, and the feeling information may include at least one of the use period of the article, the model name, the appearance state, and the demand information .

Further, the control unit further extracts the entire pattern of the photographed image, and the appearance state is determined based on the number and size of scratches and smudges detected through the analysis of the entire pattern, and the weights variably set according to the positions of the scratches and smudges The grade can be determined.

According to the emotional method and apparatus of the present invention, even if a customer does not know a specific emotional method for an article, it is possible to grasp whether the article is authentic or not, thereby improving the soundness of the market at the time of article transaction.

In addition, the present invention can be applied to various fields such as importation, brokerage, and sale of goods, as well as a feeling of a new product as well as a used transaction.

1 is a conceptual diagram of an emotional apparatus according to an embodiment of the present invention.
2 is a block diagram of an emotional apparatus according to an embodiment of the present invention.
3 is a diagram showing an example of an article to be inspected.
4 is a flowchart of an emotion method according to an embodiment of the present invention.
5 is a flowchart of steps for determining whether the article of the present invention is genuine or not.
6 is a block diagram of an example in which the emotional apparatus of the present invention can be applied.

The present invention will now be described in detail with reference to the accompanying drawings. Hereinafter, a repeated description, a known function that may obscure the gist of the present invention, and a detailed description of the configuration will be omitted. Embodiments of the present invention are provided to more fully describe the present invention to those skilled in the art. Accordingly, the shape and size of the elements in the drawings and the like can be exaggerated for clarity.

Hereinafter, the emotional apparatus 100 according to the embodiment of the present invention will be described with reference to FIG. 1 and FIG. 1 is a conceptual diagram of an emotion apparatus 100 according to an embodiment of the present invention. The emotional apparatus 100 according to an embodiment of the present invention may determine whether the article 30 is genuine or not based on a photographed image of the article 30 photographed by the user terminal 10 Function. A conceptual description of the emotion apparatus 100 according to an embodiment of the present invention is as follows.

First, the user 20 takes an image of the article 30 through the user terminal 10. Here, the captured image of the article may correspond not only to the image photographed through the user terminal 10 but also to the image through the other photographing apparatus possessed by the user 20. The user terminal 100 may include various terminals such as a laptop computer and a computer, as well as a mobile terminal including a camera function (e.g., a smart phone, a mobile phone, and a tablet pc). The photographed image is transmitted to the emotional apparatus 100 of the present invention via the network 40.

Thereafter, the emotion apparatus 100 of the present invention compares the photographed image transmitted from the user terminal 10 with the emotion reference stored in the emotion reference storage unit 50, that is, the reference image, I can feel it. Here, a specific emotion method through the emotion apparatus 100 according to an embodiment of the present invention will be described in detail below with reference to FIG.

2 is a block diagram of an emotion device 100 according to an embodiment of the present invention. As described above, the emotion apparatus 100 according to an exemplary embodiment of the present invention performs emotion for the article 30 by comparing the sensed image transmitted from the user terminal 10 with the reference image. For this purpose, the emotional apparatus 100 according to an embodiment of the present invention may include a communication unit 110 and a control unit 120. Hereinafter, an emotion apparatus 100 according to an embodiment of the present invention will be described.

The communication unit 110 performs communication between the user terminal 10 and the emotional apparatus 100 of the present invention via the network 40. [ That is, the communication unit 110 may perform a function of receiving a shot image from the user terminal 10 or transmitting an emotion result through the emotion device 100 to the user terminal 10. [ Also, as described below, the communication unit 110 can perform not only communication between the user terminals 10 but also communication with the intermediary server.

The control unit 120 analyzes the photographed image of the article 30 to determine whether the article 30 is authentic or not. Specifically, the control unit 120 extracts a comparison object image included in the captured image by loading the captured image, analyzing the captured image, and extracting the object (or the object) based on the matching ratio between the comparison object image and the reference image 30) can be determined. Here, the image to be compared may include an image of a trademark, a serial number, a zipper, and a certificate, for example, an emotion standard necessary for emotion of the article. And, the reference image represents an image including the genuine reference of the articles, which can be stored in the emotion reference storage 50 located inside or outside the emotion apparatus 100 of the present invention. In the above description, emotions can be made based on at least one of a trademark, serial number, zip and certificate, or a trademark, serial number, zip, and certificate.

The control unit 120 may include an extraction module 121, a determination module 122, and a valuation module 123 to perform the functions described above. Hereinafter, the configurations included in the control unit 120 will be described.

The extraction module 121 functions to extract a comparison object image included in the captured image by loading the captured image transmitted from the user terminal 10 and analyzing the captured image. Here, the method of analyzing the captured image and the method of extracting the image to be compared are not limited to a particular method. As mentioned above, the image to be compared may include an image of a trademark, serial number, zipper and certificate for the article 30.

Specifically, the extraction of the comparison object image with respect to the trademark is preferably performed so that the overall shape and size of the trademark can be grasped, and the number of the serial number itself, font, . For example, in the case of brands such as LOUIS VUITTON, brand-specific logos or letters, and product-specific serial numbers exist in the article. In this case, in the present invention, it is possible to adopt a method of extracting an image for the above-mentioned portion, that is, extracting a comparison object image and confirming whether or not the image is authentic based on the extracted image.

As shown in Fig. 3, each of the components included in the zipper includes a slide portion 61 of the zipper, a handle 62 connected to the slide portion 61, , The band (63), and the stopper (64). Here, the extraction of the comparison object image relative to the zipper is preferably performed on both the front portion and the back portion of the zipper, which may also form a logo that can be used for the genuine emotion of the article, It is because. Accordingly, the extraction module 121 of the present invention is capable of extracting the slide portion 61 of the zipper and the stopper 64 in the image of the back portion of the zipper, as well as the front portion of the zipper, Lt; RTI ID = 0.0 > of the product logo. ≪ / RTI >

In addition, there are many cases in which a logo of a brand that manufactures a zipper is engraved, rather than a brand of the product itself, on the slide portion of the zipper or the seal. Accordingly, in the present invention, the determination can be performed by considering both the logo of the brand of the product itself, as well as the logo of the brand that manufactures the zipper, through the determination module 122 mentioned below. Performs comparison between the comparison object image of the article extracted through the extraction module 121 and the emotion reference stored in the emotion reference storage unit 50, that is, the reference image. That is, the determination module 122 can determine whether the article is authentic based on the agreement rate between the comparison image and the reference image.

As described above, the image to be compared may include at least one of a trademark, a serial number, a zipper, and a certificate. That is, when judging whether or not the article is genuine based on the comparison object image with respect to the zipper, the judgment module 122 judges whether the article is genuine or not based on at least one of the slide portion 61 and the blocking 64 extracted from the image of the back portion of the zipper The determination as to whether or not the product is authentic can be performed by checking the agreement rate between the pattern and the reference image. Of course, it is also possible for the determination module 122 to perform the determination by comparing the reference image with a pattern for at least one of the zipper's teeth, the slide portion, the handle, the band and the closure in the image of the front portion of the zipper For example, the determination module 122 performs an image comparison based on the frontal portion of the slide portion, the shape of the back portion, the shape of the side portion, and the distance between the front portion and the back portion of the slide portion with respect to the entire pattern of the slide portion , And it is possible to perform the genuine emotion based on this.

Likewise, when determining whether a product is genuine based on a comparison image of a trademark, a logo form or size for the trademark itself may be used, and the serial number may be a number, a number form, have. A detailed description thereof has been given above, so that further explanation is omitted.

In the above description, emotion is described as being based on one of a trademark, a serial number, a zipper and a certificate, but this is merely an example, and the emotion may be sequential or parallel to both the trademark, serial number, . That is, since the emotion of an article is made not only for one criterion but also for all of the above criteria, the accuracy of confirming whether the product is authentic can be further increased.

The appraisal price calculating module 123 calculates the appraisal value of the article based on the judgment result through the judgment module 122, that is, the feeling information including whether the article is authentic or not. Here, the estimation value may be calculated by further including at least one of the use period of the article, the model name, the appearance state, and the acceptance information. The estimation method using the estimation module 123 calculates a first estimation value based on, for example, the authenticity of the article, the model name, and the demand information. Based on the use period and the appearance state of the article at the first estimation value, A method of deriving the final appraisal value by adjusting the first appraisal value can be used.

Here, the appearance state of the article may be graded based on the number and size of the speckles and scratches contained in the article. In addition, the grade of the appearance of the article can be graded by weighting the position of the stain and the scratch, and applying the weight. In this case, for example, a method in which the weight is higher when the position is noticeable to a person, and the weight is lower when the position is less noticeable can also be applied. For this purpose, the extraction module 121 can further perform a function of extracting an entire pattern for the article. The estimation module 123 analyzes the article based on the extracted whole pattern, and adjusts the estimation value Can be performed. Here, the method of detecting scratches or unevenness of an article is not limited to a particular method, and a general gray scale method, various methods, or the like can be applied.

The demand information of the goods can be calculated on the basis of the customers desiring to sell the commodity and the customers desiring to purchase the commodity. Here, the method of calculating the demand information of the article is not limited to a specific method, and a method of direct input by an administrator can also be used.

Hereinafter, an emotional method according to an embodiment of the present invention will be described with reference to FIG. 4 is a flowchart of an emotion method according to an embodiment of the present invention. The emotion method according to an embodiment of the present invention described below can be performed through the emotion apparatus described above, specifically through the communication unit and the control unit included in the emotion apparatus. In the following description, the elements overlapping with those described above are omitted.

First, after photographing the article (S110), a step S120 of transmitting a photographed image of the article from the user terminal 10 to the emotional apparatus 100 is performed. The photographing in the step S110 may be performed not only in the user terminal 10 but also in various apparatuses, and the user terminal 10 may be an apparatus capable of communicating with the emotional apparatus 100 of the present invention. Thus, when the transmission of the shot image is made, the image sensing apparatus 100 loads the shot image of the article.

Thereafter, a step S130 of extracting a comparison object image included in the shot image is performed by analyzing the shot image in the emotion apparatus 100. [ The extraction of the comparison image in step S130 may include an image for at least one of a trademark, a serial number, a zipper, and a certificate, which is a part used for emotion, as mentioned with reference to Figs. 1 and 2 . Here, the description of the specific parts used for emotion has been described in detail above, and a further explanation thereof will be omitted.

In addition, the step S130 may further perform a function of extracting the entire pattern for scratching or checking the unevenness of the article used in the step S150.

Thereafter, step S140 is performed to determine whether the article is authentic by comparing the comparison image extracted in step S130 with the reference image. In step S140, it is possible to determine whether the article is genuine based on the agreement rate between the comparison image and the reference image for the article.

Thereafter, step S 150 is performed to calculate the appraised value of the article based on the emotion information including whether or not the inspected article is authentic in step S 140. Here, the emotion information may further include at least one of the use period of the article, the model name, the appearance state, and the demand information. Here, the estimation value can be derived in such a manner that the first estimation value is calculated based on the authenticity of the article, the model name, and the demand information, and the final estimation value is derived based on the use period and the appearance state of the article at the first estimation value, The method of deriving the estimation value is not limited to the above-described manner and can be performed in various ways.

Thereafter, step S160 of transmitting the article information including the authenticity of the article derived from steps S140 and S150 to the user terminal 10 is performed.

Hereinafter, with reference to FIG. 5, step S140 of FIG. 4 will be described in more detail. 5 is a flowchart of steps for determining whether the article of the present invention is genuine or not.

First, a step S141 of comparing a comparison object image with a reference image is performed. Specifically, the step S 141 performs a function of comparing the comparison image with the reference image with respect to the trademark, the serial number, the zipper and the certificate of the article. Here, the comparison with the trademark is based on, for example, the overall shape of the trademark and the size of the letter or figure included in the trademark, and the comparison with the serial number is, for example, the serial number itself and the form of the serial number .

And the comparison to the zipper can be made centering on the comparison of the logo and the reference image formed on the slide part or the plug in the image of the back part of the zipper. Of course, comparisons to the zipper may also be made through comparison of the reference image with a pattern for at least one of the zipper's teeth, the slide portion, the handle, the strap, and the closure in the image of the front portion of the zipper. Since the comparison method mentioned in step S141 is described in detail with reference to FIGS. 1 and 2, a further explanation will be omitted.

Thereafter, step S142 is performed in which it is determined whether the coincidence rate between the comparison object image and the reference image is equal to or greater than a predetermined threshold value, that is, the true or not judgment value. As a result of the determination in step S142, if it is determined that the matching rate is equal to or larger than the true value determination value, control is passed to step S143, and the product is determined as the genuine product. Otherwise, control is passed to step S144, where the product is determined as an article. Thereafter, control is passed to step S150, where the evaluation value is calculated.

As described above, the emotional method and apparatus according to an embodiment of the present invention can grasp whether the customer is authentic or not, even if he / she does not know a specific method of feeling about the product. There is an advantage that it can be increased. Also, the emotional apparatus and method according to an embodiment of the present invention can be applied to various fields as well as emotions according to a request of a customer. For example, the emotional apparatus and method of the present invention can be applied to a web page or an application of an article transaction or a used goods transaction.

That is, as shown in FIG. 6, the present invention can be applied to an existence of an intermediary center or an intermediary server, and to determine whether an article is authentic in a transaction between customers or between a company and a customer. For example, when the seller sends an item to the mediating server 70 via the seller terminal 12, the mediating server 70 performs the verification of the goods with the emotion apparatus 100 of the present invention, The mediating server 70 can perform the transaction for the goods. Thus, the present invention is applied to various fields and has an advantage that the market can be improved in the market.

The method and apparatus for transforming an object according to the present invention can be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Includes all types of hardware devices that are specially configured to store and execute magneto-optical media and program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such a hardware device may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

The teachings of the principles of the present invention may be implemented as a combination of hardware and software. In addition, the software can be implemented as an application program that is actually implemented on the program storage unit. The application program can be uploaded to and executed by a machine that includes any suitable architecture. Advantageously, the machine may be implemented on a computer platform having hardware such as one or more central processing units (CPUs), a computer processor, a random access memory (RAM), and input / output (I / . In addition, the computer platform may include an operating system and microinstruction code. The various processes and functions described herein may be part of microcommand codes or a portion of an application program, or any combination thereof, and they may be executed by various processing devices including a CPU. In addition, various other peripheral devices such as additional data storage and printers may be connected to the computer platform.

It is to be understood that the actual connections between system components or process functional blocks may vary depending on how the principles of the present invention are programmed, as some of the constituent system components and methods illustrated in the accompanying drawings are preferably implemented in software It should be further understood. Given the teachings herein, those skilled in the relevant art (s) will be able to contemplate these and similar implementations or configurations of the principles of the invention.

100: emotional apparatus 110: communication unit
120: control unit 121: extraction module
122: determination module 123: estimation module

Claims (15)

As an emotion method for judging whether an article is authentic,
Loading a photographed image of the article;
Extracting a comparison object image included in the captured image by analyzing the captured image; And
And determining whether the article is authentic based on a match rate between the comparison image and the reference image for the article. The method according to claim 1,
Wherein the comparison image includes a zipper image of the article included in the shot image and the zipper image includes a front portion of a zipper exposed to the outside of the article and a back portion of a zipper that is opposite to the front portion of the zipper ≪ / RTI >
The step of determining whether the article is authentic includes:
Extracting a pattern of a product logo formed on at least one of a slide portion of the zipper and a stopper in an image of the back portion of the zipper and comparing the pattern of the product logo with the reference image, . 3. The method of claim 2,
The step of determining whether the article is authentic includes:
Wherein at least one of a zipper, a slide, a handle, a band, and a clogging of a zipper included in the zipper image is extracted, and a pattern of at least one of the zipper, the slide, the handle, the belt, The images are further compared,
Wherein the pattern of the slide portion includes a front portion shape, a back portion shape, a side portion shape, and a separation distance between a front portion and a back portion of the slide portion. The method according to claim 1,
Wherein the comparison image includes an image for at least one of a trademark, a serial number, and a certificate included in the photographed image,
The step of determining whether the article is authentic includes:
And comparing the reference image with an image of at least one of a shape and size of a trademark included in the shot image, a serial number, and a font and a certificate. The method according to claim 1,
Further comprising the step of calculating the estimated value of the article based on the feeling information including whether or not the article is genuine according to the step of determining whether the article is genuine or not. 6. The method of claim 5,
Wherein the emotion information further includes at least one of a use period of the article, a model name, an appearance state, and demand information. The method according to claim 6,
Wherein the first estimation value is calculated based on the authenticity of the article, the model name, and the demand information, and the final estimation value is derived based on the use period and the appearance state of the article in the first estimation value . The method according to claim 6,
Wherein the step of extracting the comparison target image included in the captured image comprises:
Wherein the appearance state is variably set according to the number and size of scratches and smudges detected through analysis of the entire pattern and the positions of the scratches and smudges And a rating is determined based on the weight. An emotion device for judging whether an article is genuine or not,
Extracting a comparison image included in the captured image by loading the captured image of the article and analyzing the captured image and comparing the comparison image with the reference image for the article, And a control unit for determining whether or not the user is a user. 10. The method of claim 9,
Wherein the comparison image includes a zipper image of the article included in the shot image and the zipper image includes a front portion of a zipper exposed to the outside of the article and a back portion of a zipper that is opposite to the front portion of the zipper ≪ / RTI >
Wherein the controller extracts a pattern of the product logo formed on at least one of the slide portion of the zipper and the plug in the image of the back portion of the zipper and compares the reference image with a pattern of the product logo. Appraiser. 11. The method of claim 10,
Wherein the controller extracts a pattern of at least one of a zipper, a slide, a handle, a band, and a clogging of a zipper included in the zipper image, and detects at least one of the zipper, the slide, the handle, And the reference image,
Wherein the pattern of the slide part includes a shape of a front part of the slide part, a shape of a back part, a shape of a side part, and a separation distance between a front part and a back part of the slide part. 10. The method of claim 9,
Wherein the comparison image includes an image for at least one of a trademark, a serial number, and a certificate included in the photographed image,
Wherein the control unit compares the reference image with an image of at least one of a type and size of a trademark included in the photographed image, a serial number, and a font and a certificate. 10. The method of claim 9,
Wherein,
And further calculates the estimated value of the article based on the emotion information including whether the article is authentic or not. 14. The method of claim 13,
Wherein the emotion information includes at least one of a use period, model name, appearance state, and demand information of the article. 15. The method of claim 14,
The control unit further extracts an entire pattern of the photographed image, and the appearance state includes a number and a size of scratches and smudges detected through analysis of the entire pattern, and a weight that is variably set according to the positions of the scratches and smudges, And the rating is determined based on the rating.

Images