KR20150059213A - Method and apparatus for processing palm print image - Google Patents

Abstract

Disclosed are a method and an apparatus for processing a palm print image comprising: a step of displaying hand shape guide information; a step of determining whether or not a hand is located on the guide information based on a signal pattern in a predetermined area of the guide information when an image is inputted; and a step of capturing the inputted image according to the determination result.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing method,

The present invention relates to a long image processing method and a terminal for the same, and more particularly, to a long image processing method for acquiring and processing a long image using guide information and a terminal for the same.

Generally, a long-range recognition system requires a high-resolution long-range image in order to obtain a high recognition rate. Therefore, in the conventional long-range recognition system, in order to obtain a consistent high-resolution long-range image, a method of inserting a finger between the fixed rod-shaped columns and scanning the finger or using a method of printing ink on the palm of the hand .

However, in the conventional long-range recognition system, it is difficult to acquire a long-range image in real time from a portable terminal such as a mobile device by using a method of scanning a long-range or inking. In addition, a long-range image using a camera built in a mobile device is obtained in a non-contact manner with a distance from the mobile phone without a separate fixing device. Therefore, the conventional long-range recognition system can acquire different images from the same hand according to the distance and angle between the camera and the hand when the user takes the hand posture or the image, And this leads to a decrease in the performance of the mobile long-distance recognition.

An object of the present invention is to provide a long-range image processing method for acquiring and processing a long-range image using a palm-shaped guide screen and a terminal for the same.

According to another aspect of the present invention, there is provided a long-distance image processing method including displaying hand-shaped guide information, Determining whether a hand is positioned on the guide information based on a signal pattern in a predetermined area of the guide information when an image is input; And capturing an input image according to the determination result.

The step of determining whether a hand is positioned on the guide information includes the steps of: setting an area from which the video signal is extracted from the guide information; Analyzing a signal pattern in the set region; And determining whether the hand is positioned on the guide information based on the analyzed signal pattern.

The setting of the area may be performed by setting a line segment of a finger image or a region of interest of the finger image in the guide information.

The step of setting a line segment of the finger image is characterized in that a line segment is set in upper and lower parts of a point of a predetermined finger and a line segment is set symmetrically with respect to the right and left hands.

Wherein the step of analyzing the signal pattern compares the video signal pattern of the first area of the guide information with the video signal pattern of the second area of the guide information.

Wherein the step of analyzing the signal pattern calculates a difference between an average value of all YCbCr of the first area and a YCbCr value of a pixel corresponding to the second area of the guide information.

Wherein the step of determining whether the hand is positioned on the guide information comprises comparing the video signal pattern of the first area of the guide information with the video signal pattern of the second area of the guide information, And the like.

Wherein the step of determining whether the hand is positioned on the guide information includes analyzing a signal pattern of the input image after the focus of the camera is adjusted.

And checking whether the hand exists in the input image based on the color information of the predetermined area of the guide information.

Wherein the step of verifying whether a hand is present in the input image comprises: Setting a region of interest in the guide information; Determining whether an average pixel value in the ROI is included in a preset primary boundary; Obtaining a ratio of pixels included in a predetermined second boundary among all the pixels within the set region of interest; And determining whether a hand exists in the input image based on the pixel ratio.

  According to another aspect of the present invention, there is provided a long-range image processing method including displaying hand-shaped guide information, Confirming whether a hand exists in the input image based on color information in a predetermined area of the guide information; Determining whether a hand is positioned on the guide information based on a pattern of a video signal in a predetermined area of the guide information according to the check result; And capturing an input image according to the determination result.

According to an aspect of the present invention, there is provided a long-range image processing apparatus including a guide information generator for generating hand-shaped guide information; A color analyzer for determining whether a hand is included in an input image based on color information in a predetermined area of the guide information; A signal pattern analyzer for determining whether or not a hand is positioned on the guide information based on a pattern of a video signal in a predetermined area of the guide information; And a video capturing unit capturing an input video signal according to a determination result of the color analyzer and the signal pattern analyzer.

According to an aspect of the present invention, there is provided a terminal comprising: a camera unit for capturing an image; An image processor for displaying hand guide information and analyzing a video signal in a predetermined area of the guide information when an image is input from the camera unit to determine whether a hand is positioned on the guide information; And a display unit for displaying the guide information and the image photographed by the camera unit.

Wherein the image processing unit comprises: a guide information generating unit for generating hand guide information; An image input unit for inputting an image photographed by a camera; A color analyzer for determining whether the input image is included in a hand based on color information in a predetermined area of the guide information; A signal pattern analyzer for determining whether or not a hand is positioned on the guide information based on a pattern of a video signal in a predetermined area of the guide information; And an image capturing unit capturing an input image signal according to a determination result of the color analyzer and the signal pattern analyzer.

1 is a block diagram of a terminal according to an embodiment of the present invention.
2 is a detailed block diagram of the image processing unit of FIG.
3 is a flowchart for explaining a long-range image processing method according to an embodiment of the present invention.
4 is a flowchart illustrating a method of processing a long image according to another embodiment of the present invention.
5A and 5B show left and right hand guide information according to an embodiment of the present invention.
6 is a flowchart illustrating color signal analysis in a setting area of guide information according to an embodiment of the present invention.
7 is a flowchart illustrating signal pattern analysis according to an embodiment of the present invention.
FIG. 8 shows an example of setting a region of interest for color signal analysis according to an embodiment of the present invention.
FIG. 9 shows an example of setting right-hand lines for verifying suitability of a long-length image according to an embodiment of the present invention.
FIG. 10 illustrates an example of setting a skin color distribution in a YCbCr color space used for determining whether a hand exists in a guide image according to an embodiment of the present invention.
11 is a diagram illustrating an example of a signal pattern of a line segment located at the uppermost point of a mark for verifying a long image according to an embodiment of the present invention.
12 shows an example of a signal pattern of a line segment located at the lower end of a point of the longbow for confirming a long image according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The present invention is capable of various modifications and various embodiments, and specific embodiments are illustrated in the drawings and described in detail in the detailed description. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by terms. Terms are used only for the purpose of distinguishing one component from another.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the invention. Also, in certain cases, there may be a term selected arbitrarily by the applicant, in which case the meaning thereof will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term, not on the name of a simple term, but on the entire contents of the present invention.

The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

1 is a block diagram of a terminal according to an embodiment of the present invention.

1 includes a camera unit 110, an image processing unit 120, a control unit 130, a display unit 140, a memory 150, a communication interface unit 160, a key input unit 170, an audio processing unit 180, .

The camera unit 110 captures an image, and can obtain an image frame such as a still image or a moving image through the image sensor in a video communication mode or a photographing mode. At this time, the image captured through the image sensor can be processed as a desired signal through the image processing unit 120. [

The image frame processed by the camera unit 120 may be stored in the memory 150 or may be transmitted to the outside through the communication interface unit 160.

When the long text recognition function is started, the image processing unit 120 displays guide information in the form of a hand floor on the display unit 140. When the captured image is input in the camera unit 120, the image processing unit 120 analyzes And verifies that the input image is suitable for long-range recognition.

The control unit 130 controls each block, and in particular, controls the focus of the lens of the camera unit 110 or inputs a video signal of a new frame according to focus adjustment to the image processing unit 120. [

The display unit 140 displays a frame image or various information processed by the image processing unit 120 on a screen and displays user data output from the control unit 130. [ In particular, the display unit 140 displays the guide information and the image photographed by the camera unit 110.

The memory 150 stores instructions executed by the control unit 130 or temporarily stores various information data. The memory 150 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), a RAM (Random Access Memory) SRAM (Static Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) , An optical disc, and the like.

The communication interface unit 160 transmits and receives a radio signal to at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signal may include various types of data depending on a voice call signal, a video call signal, or a text / multimedia message transmission / reception.

The key input unit 170 receives a control command from a user through a touch screen or an input key.

The audio processor 180 reproduces the audio signal generated by the controller 130 through a speaker or inputs an audio signal generated from the microphone to the controller 130.

2 is a detailed block diagram of the image processing unit 120 of FIG.

2 includes a guide information generating unit 210, an image input unit 220, a color analyzing unit 220, a signal pattern analyzing unit 240, and an image capturing unit 250.

The guide information generating unit 210 generates guide information in the form of a hand bottom for acquiring a long image on the screen

The image input unit 220 inputs images photographed by the camera unit 110.

The color analyzer 230 analyzes whether the hand is included in the input image based on the color information in the predetermined area of the guide information.

The signal pattern analyzing unit 240 analyzes whether or not the hand is positioned on the guide information based on the pattern of the video signal in the predetermined area of the guide information.

       The image capturing unit 250 captures an input image signal according to an analysis result of the color analyzing unit 230 and the signal pattern analyzing unit 240.

3 is a flowchart for explaining a long-range image processing method according to an embodiment of the present invention.

The method begins at step 310.

In step 320, when the long-range recognition function is started, the terminal displays guide information in the form of a hand bottom for acquiring a long-distance image on the screen.

In one embodiment, the terminal provides a hand floor-shaped guide screen on the screen so that the user can conveniently input the hand-held long-distance image while maintaining a relatively same hand posture and a distance to the camera. The terminal displays the guide information in the shape of the hand so that the long-range area used for recognition can be maximized within the range where the camera is in focus. At this time, the guide information of the bottom of the hand is displayed in a clockwise direction in the case of the left hand in the counterclockwise direction as shown in FIG. The long field area is extracted from the lower part parallel to the point between the index finger and the stop point and the point between the finger and the finger. Therefore, in order to guide the hands to be aligned at the positions of the two score points, the terminal points 502a and 502b between the index finger and the stop, the score points 503a and 503b between the stop and the finger, the score points 504a and 504b With a solid line. In addition, the terminal draws the palm boundary 501a, 501b and the lower palm boundary 505a, 505b between the thumb and index finger in a dotted line so that the user's hand is naturally guided based on the three points mentioned above. In the case of representing a hand shaped guide, the inclined oblique guide information including the above two point marks is an important factor for not only ensuring a high level of long-range recognition performance but also enhancing the convenience of the user by making it possible to acquire a certain long- do.

In step 330, the terminal inputs an image photographed by the camera.

 In operation 340, when the image is input, the terminal analyzes the signal pattern of the predetermined area or line segment in the predetermined area of the guide information, for example, the finger image to determine whether the hand is located in the guide information. If it is determined that the hand is positioned on the guide information, the terminal PASSes to the next step 350, otherwise performs step 330 (NON-PASS).

If it is determined in step 350 that the hand is positioned on the guide information, the terminal determines that the input image is an image suitable for recognition and captures the input image.

The method ends at step 360.

As a result, the terminal uses the captured image which is confirmed to be suitable for authentication to recognize the long text.

4 is a flowchart illustrating a method of processing a long image according to another embodiment of the present invention.

The method starts at step 405.

In step 410, when the terminal starts the long text recognition function, the terminal displays guide information in the form of a hand bottom for capturing a long text image on the screen.

In step 415, the terminal inputs the image photographed by the camera.

In step 420, the terminal checks whether the focus is being adjusted from the camera. If it is checked that the focus adjustment is being performed, the terminal continuously inputs an image of a new frame.

If it is determined in step 425 that the focus adjustment is not being performed, the terminal analyzes the color information of a predetermined area of the guide information, for example, the finger image of the guide information, and confirms whether or not the hand is included in the input image. If it is determined that the hand is included in the input image, the terminal PASSes to the next step 430, otherwise, it performs step 415 (NON-PASS).

Whether or not the hand is included in the input image is not limited to the method of analyzing the above-mentioned color information. The model of the hand such as the active appearance model (AAM) and the active shape model (ASM) Or a separate sensor that senses the temperature of the body, such as a body temperature sensor, may be used.

In step 430, if it is not confirmed that a hand exists in the input image, the terminal receives the new image and processes the image again in step 415. However, if it is determined that a hand is present in the input image, the terminal analyzes the signal pattern of the predetermined area or line segment in the predetermined area of the guide information, e.g., the finger image, to determine whether the hand is located in the guide information. If it is determined that the hand is positioned on the guide information, the terminal PASSes to the next step 435. Otherwise, the terminal determines that it is not a hand image suitable for recognizing the long pass (NON-PASS). In step 415, Receive.

If it is determined in step 435 that the hand is located in the guide information, the terminal determines that the hand image is suitable for recognition and checks whether the focus adjustment is completed.

If it is checked in step 440 that the focus adjustment is not completed, the terminal starts focus adjustment and inputs an image of the frame in step 415.

If it is checked in step 445 that the focus adjustment is completed, the terminal determines that the input image is suitable for recognition and captures it.

The method ends at step 450.

6 is a flowchart for explaining the color signal analysis in the setting area of the guide information of FIG.

 The method begins at step 610.

In step 620, the terminal sets the center of interest area in the guide information for color signal analysis.

As shown in FIG. 8, the center of interest (ROI) for color analysis is divided into a line segment 801 connecting between a point of intersection 801 between the detection and the stop and a point of intersection 802 between the fingerprint and the ground, ) Is defined as a region 804 which is appropriately separated from this. In one example, the central region of interest is a rectangular region 804 with a horizontal length L and a vertical length of 0.3L that is vertically separated by 0.3L.

In step 630, the terminal determines whether the average pixel value in the central region of interest is included in the preset primary boundary. In one embodiment, the terminal measures the average Cb and Cr values in a rectangular area and determines whether the values are contained in a first boundary corresponding to the range of Cb and Cr that the skin color may have. The range of Cb and Cr corresponding to the color information used at this time is set to be large enough to accommodate most hand images through learning data of various races and ages.

In step 640, the terminal determines the ratio of pixels included in the predetermined secondary boundary among all the pixels within the central region of interest. In one embodiment, the terminal sets a secondary boundary corresponding to a range of maximum Cb and Cr that a hand image can have through learning data, and sets a secondary boundary corresponding to a range of pixels included in the secondary boundary among all pixels in the central region of interest The ratio is measured to determine the presence of a hand in the image. 10, the x-coordinate is in the Cr range, the y-axis is in the Cb range, 101 is the first-order boundary, 102 is the second-order boundary, and 103 is the distribution of each pixel in the central region of interest.

In step 650, the terminal determines whether a hand exists in the input image based on the determined pixel ratio.

The method ends at step 660.

 FIG. 7 is a flowchart illustrating the signal pattern analysis of FIGS. 3 and 4. FIG.

The method begins at step 710.

In step 720, the terminal sets an area of a finger or a segment of a finger to extract a video signal from the guide information. In one embodiment, the area or line segment of the finger is set so that each point of the hand actually photographed can appropriately come in the vicinity of each point of the above-mentioned guide. That is, the positions of the line segments for extracting the image signal are determined by the points 502a and 502b between the detection and the stop of the guide and the positions of the points 504a and 504b between the ring finger and the finger as shown in FIGS. 5A and 5B , Below. 9, when the length of the line segment 903 connecting the point of intersection 901 between the detection and the stop and the point of intersection 902 between the fingerprint and the substrate is L, For example, the position of a line segment with a length of 0.44L is set at 904 and 905 around a point 901 between a detection and a stop, and a point 906 And 907, respectively. In the case of the left hand, the positions of the line segments for signal extraction are set symmetrically to the positions shown in FIG. 5A.

Referring to FIG. 9, if a hand image is acquired according to a guide shape, a one-dimensional image signal will show a hand-> background-> hand pattern at the set line segments 904 and 906 above the set point, All of the line segments 905 and 907 will show the pattern of the hand.

In step 730, the terminal analyzes the video signal pattern in a predetermined segment or region of the finger. The terminal analyzes signal patterns of the pair of two line segments around the finger and the finger point side to thereby verify whether or not a long image suitable for recognition is acquired. In one embodiment, in order to grasp a signal pattern in a line segment, the terminal uses a pattern information difference at a point located in a line segment and a central region of interest, which is a skin color region of a hand. The signal pattern value at a point on the line segment is obtained by the difference between the average value of the YCbCr of the central ROI region and the YCbCr value of the pixel corresponding to the center ROI region using Equation (1).

Here, Y _ROI, Cb _ROI, Cr _ROI is YCbCr average value of the center ROI areas, and Y _iN, Cb _iN, Cr _iN is a YCbCr value in a point on the line segment, WI is a Y value weight, Dist is a signal pattern Represents the difference value.

When the hand image is acquired in conformity with the guide shape, the pattern values of the line segments located at the above-mentioned punctum marks 904 and 906 can be represented by a signal waveform as shown in FIG. Referring to FIG. 11, the center has a large distance corresponding to the background, and the ends of the line segment have a small distance corresponding to the foreground of the skin (1101). In this case, the x-axis in FIG. 11 is a line segment length (L), the y-axis is a signal pattern difference value, 1103 corresponds to a punctual point, and 1102 corresponds to a reference value. The signal waveform shown in FIG. 11 indicates that the line segment is divided into a hand region, a background region, and a hand region. On the other hand, as shown in FIG. 12, the line segment located at the lower end points 905 and 907 of FIG. 9 has a small value 1201 below the reference value 1202 because the line segment pattern signal corresponds to the hand region.

In step 740, the terminal determines whether the hand is positioned on the guide information based on the analyzed video signal pattern. As shown in FIG. 11, if the number of intersections with the threshold value and the number of intersections with the threshold value at the positions of the intersection points with the threshold value and the threshold value at the position of the bottom point of the goal point satisfy both 2 and 0 conditions, It is determined that the image is input.

In the above embodiment, the line segment in the finger is analyzed to determine whether the hand image is acquired according to the guide shape, but the pixels corresponding to the predetermined region of interest in the finger can be analyzed without being limited to the line segment.

The long-range image processing method according to an embodiment of the present invention can perform long-range recognition only in a necessary portion of a guide screen using a camera mounted on a mobile device without using a separate dedicated sensor, It can bring a lot of advantages to the user, and it can also automatically improve the convenience of the user by acquiring a long image by automatically evaluating the quality of the image.

One or more programs including instructions for performing a method of implementing a long image processing method according to embodiments of the present invention may be recorded in a computer readable code on a computer readable recording medium. A computer-readable recording medium includes all kinds of storage devices in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. The computer readable recording medium may also be distributed over a networked computer system and stored and executed as computer readable code in a distributed manner.

The present invention has been described with reference to the preferred embodiments. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

Claims (15)

Displaying hand-shaped guide information;
Determining whether a hand is positioned on the guide information based on a signal pattern in a predetermined area of the guide information when an image is input; And
And capturing an input image according to the determination result. 2. The method of claim 1, wherein the step of determining whether a hand is positioned on the guide information comprises:
Setting an area to extract a video signal from the guide information;
Analyzing a signal pattern in the set region; And
And determining whether a hand is positioned on the guide information based on the analyzed signal pattern. 3. The method as claimed in claim 2, wherein the setting of the area comprises setting a line segment of a finger image or a region of interest of the finger image in the guide information. 4. The method according to claim 3, wherein the step of setting a line segment of the finger image sets a line segment in upper and lower portions of a point of a predetermined finger, and sets a line segment symmetrically with respect to the right and left hands, Processing method. 3. The method of claim 2, wherein analyzing the signal pattern comprises:
The video signal pattern of the first area of the guide information is compared with the video signal pattern of the second area of the guide information. 3. The method of claim 2, wherein analyzing the signal pattern comprises:
Calculating a difference between an average value of all YCbCr of the first area and a YCbCr value of a pixel corresponding to the second area of the guide information. 3. The method according to claim 2, wherein the step of determining whether the hand is positioned on the guide information comprises comparing the video signal pattern of the first area of the guide information with the video signal pattern of the second area of the guide information, Or whether the background is not a hand or a background. 3. The method as claimed in claim 2, wherein the step of determining whether the hand is positioned on the guide information comprises analyzing a signal pattern of the input image after the focus of the camera is adjusted. The long image processing method according to claim 1, further comprising checking whether a hand exists in an input image based on color information of a predetermined area of the guide information. 10. The method of claim 9, wherein the step of determining whether a hand is present in the input image comprises:
Setting a region of interest in the guide information;
Determining whether an average pixel value in the ROI is included in a preset primary boundary;
Obtaining a ratio of pixels included in a predetermined second boundary among all the pixels within the set region of interest; And
And determining whether a hand exists in the input image based on the pixel ratio. Displaying hand-shaped guide information;
Confirming whether a hand exists in the input image based on color information in a predetermined area of the guide information;
Determining whether a hand is positioned on the guide information based on a pattern of a video signal in a predetermined area of the guide information according to the check result; And
And capturing an input image according to the determination result. A guide information generator for generating hand guide information;
A color analyzer for determining whether a hand is included in an input image based on color information in a predetermined area of the guide information;
A signal pattern analyzer for determining whether or not a hand is positioned on the guide information based on a pattern of a video signal in a predetermined area of the guide information; And
And an image capturing unit capturing an input image signal according to a determination result of the color analysis unit and the signal pattern analysis unit. A camera unit for capturing an image;
An image processor for displaying hand guide information and analyzing a video signal in a predetermined area of the guide information when an image is input from the camera unit to determine whether a hand is positioned on the guide information; And
And a display unit for displaying the guide information and the image photographed by the camera unit. 14. The apparatus of claim 13, wherein the image processing unit
A guide information generator for generating hand guide information;
An image input unit for inputting an image photographed by a camera;
A color analyzer for determining whether the input image is included in a hand based on color information in a predetermined area of the guide information;
A signal pattern analyzer for determining whether or not a hand is positioned on the guide information based on a pattern of a video signal in a predetermined area of the guide information; And
And an image capturing unit capturing an input image signal according to a determination result of the color analysis unit and the signal pattern analysis unit. 12. A computer-readable recording medium on which a program for implementing the method of any one of claims 1 to 11 is recorded.

Images