CN106778919B - Euro coin country identification method based on local binary pattern - Google Patents

Euro coin country identification method based on local binary pattern Download PDF

Info

Publication number
CN106778919B
CN106778919B CN201710059329.9A CN201710059329A CN106778919B CN 106778919 B CN106778919 B CN 106778919B CN 201710059329 A CN201710059329 A CN 201710059329A CN 106778919 B CN106778919 B CN 106778919B
Authority
CN
China
Prior art keywords
euro
image
coin
value
area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710059329.9A
Other languages
Chinese (zh)
Other versions
CN106778919A (en
Inventor
张东波
文登伟
陈红磊
张莹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiangtan University
Original Assignee
Xiangtan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xiangtan University filed Critical Xiangtan University
Priority to CN201710059329.9A priority Critical patent/CN106778919B/en
Publication of CN106778919A publication Critical patent/CN106778919A/en
Application granted granted Critical
Publication of CN106778919B publication Critical patent/CN106778919B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
    • G06V10/507—Summing image-intensity values; Histogram projection analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)
  • Testing Of Coins (AREA)

Abstract

The invention discloses a local binary pattern-based Euro coin country identification method, which comprises the following steps of: the method comprises the following steps: acquiring a gray image of the coin, extracting a target area to be detected from the acquired coin image, and performing size normalization processing; step two: performing annular space decomposition on the target area; step three: extracting a uniform rotation invariant local binary pattern of each annular region, counting histogram distribution characteristics of the annular region, and assembling according to the sequence from an inner ring to an outer ring to obtain final coin image description characteristics; step four: and designing a classifier by using a support vector machine, and designing a plurality of classifiers according to different currency values respectively to detect and identify the Euro coins with different currency values. The method adopts the area as the characteristic to determine the currency value of the euro coin, and then selects different classifiers for identification according to the currency value, thereby decomposing the recognition problem of the euro coin country, reducing the problem difficulty and ensuring the accuracy of the subsequent country recognition.

Description

Euro coin country identification method based on local binary pattern
Technical Field
The invention relates to a Euro coin country identification method, in particular to an image-based Euro coin country identification method.
Background
There are 17 countries in the 28 member countries of the european union that use euro, of which 12 countries france, germany, spain, portugal, the netherlands, irish, finland, greece, italy, lucenburg, belgium, austria, etc. have high traffic. Coin market traffic is small in 5 countries of slovennia, cypress, malta, slovak, and estonia. The currency value of the euro coins on the market is 8, namely 2 ohm, 1 ohm, 50 ohm, 20 ohm, 10 ohm, 5 ohm, 2 ohm and 1 ohm, wherein, the currency value of 5 ohm, 2 ohm and 1 ohm is less circulated. The euro coins of all countries have the same positive patterns, and the negative patterns are designed by each country. Therefore, the country identification of the euro coins can be realized by using the back pattern, thereby being beneficial to sorting the coins.
The key technology for identifying the Euro coin country to be solved is characterized by feature extraction and expression, and the factors to be considered are as follows: firstly, rotation resistance is achieved; secondly, resisting disturbance (scratches, stains, abrasion and the like); and illumination change resistance (the reflection difference of new and old coins to light is large). The conventional methods are mainly divided into two main methods based on global feature description and local feature description:
1) the method based on global feature description mainly adopts template matching and extracts statistical information of features such as texture, edge, shape and the like to realize appearance modeling of the target. The method is easily influenced by image transformation, noise and illumination change, and the description of local information of the image is not fine enough, so that the identification performance is poor;
2) the method based on local feature description focuses on the description of key points or key areas of the image. The method has the characteristics of good positioning, high identification, good robustness, interference resistance, strong shielding resistance and the like, and therefore, the method becomes a mainstream technology for detecting and identifying the image target. But it needs to heavily consider the anti-rotation, anti-illumination and anti-noise capabilities of the image characterization during the design construction process.
The identification problem of the euro coin image is rarely reported in the past literature, the performance of a related method lacks a comparison basis and a reference, according to market research, a designed algorithm should enable the identification error rate to reach below 0.5%, and how to solve the technical problem is a problem to be explored and researched.
Disclosure of Invention
In order to solve the technical problems, the invention provides the image-based Euro coin country identification method which is simple in calculation and high in accurate identification rate.
The technical scheme for solving the problems is as follows: a local binary pattern-based Euro coin country identification method comprises the following steps:
the method comprises the following steps: acquiring a gray image of the coin, extracting a target area to be detected from the acquired coin image, and performing size normalization processing;
step two: performing annular space decomposition on the target area;
step three: extracting a uniform rotation invariant local binary pattern of each annular region, counting histogram distribution characteristics of the annular region, and assembling according to the sequence from an inner ring to an outer ring to obtain final coin image description characteristics;
step four: and designing a classifier by using a support vector machine, and designing a plurality of classifiers according to different currency values respectively to detect and identify the Euro coins with different currency values.
The euro coin country identification method based on the local binary pattern specifically comprises the following step
1-1: acquiring a gray level image I of the euro coin by adopting a coaxial light illumination scheme;
1-2: determining a threshold th according to the background gray value
Figure BDA0001218130310000031
Wherein IBWFor the segmented image, I (x, y) is the coordinate in I: (x，y) A pixel value of (a);
1-3: the binary image IBWPerforming filtering calculation by using an average filter with the size of 10 multiplied by 10 pixels, and then using a hole filling operation;
filling process formula
Where X denotes all holes filled, ends when iteration k times,
Figure BDA0001218130310000033
representing a swelling operation, B being a corresponding structural element, ACThe negation of the hole area is shown;
1-4: carrying out corrosion operation on the filtered binary image by using a circular structural element with the radius of 10 pixels to obtain a mask image M, and calculating the area S, the center O and the radius R of a target region through the mask image M; the calculation formula is as follows:
Figure BDA0001218130310000034
Figure BDA0001218130310000035
Figure BDA0001218130310000036
where M, n are the side length of M, Ox，OyIs the coordinate of the oxygen (O),
Figure BDA0001218130310000037
x and y coordinate values representing a value of M (x, y) of 1;
1-5: performing mask calculation on the mask image M and the original image I to obtain a target area image I*Is shown as I*I · M, wherein · is a point multiplier;
1-6: in I*Taking O as the center and 2R as the side length to extract a square area, and normalizing the square area to an image I with the size of 200 multiplied by 200 pixelsROI。
The second step of the euro coin country identification method based on the local binary pattern includes the following specific steps: in a 200 × 200 region, a 24-area circular ring template Ψ is generated with a point (100 ) as a center, overlapping each otheriWherein the radius range of the ith ring is
Figure BDA0001218130310000041
Wherein
Figure BDA0001218130310000042
The euro coin country identification method based on the local binary pattern comprises the following three specific steps:
3-1: connecting each circular ring template psiiMasking with the original image I to obtain an annular image area Ii，Ii＝I.*Ψi；
3-2: in IiGray value g of P neighborhoods of each pixel pointpWith the gray value g of the pointcComparing the two values to obtain the sum gpValue S corresponding to neighborhood pointpThe calculation is as follows:
Figure BDA0001218130310000043
3-3: selecting a certain neighborhood point as a starting point, and forming texture description T ═ S of the current pixel point in the clockwise direction1S2S3S4S5S6S7S8]Then, the value of U is calculated by the following formula, and the value of U is the change times of the texture T in one shift period
Figure BDA0001218130310000044
3-4: will U>2 is divided into a mode value P +1, and a uniform rotation invariant mode is calculated for points with U less than or equal to 2
Figure BDA0001218130310000045
The calculation formula is as follows,
Figure BDA0001218130310000046
3-5: histogram statistics of i-th annular space mode value HiAssembling the coin images in sequence from the inner ring to the outer ring to obtain the final coin image description characteristic F ═ H1H2H3，...，H24]。
The euro coin country identification method based on the local binary pattern comprises the following four specific steps:
4-1: designing a classifier by using a support vector machine, wherein a kernel function of the support vector machine is a linear kernel function;
4-2: the area S is used as a characteristic to distinguish 5 Euro coins with different currency values, namely 2 Euro, 1 Euro, 50 Euro, 20 Euro and 10 Euro;
4-3: respectively selecting enough training samples for Euro coins with different currency values to learn by adopting the finally extracted image description characteristics F to obtain 5 support vector machine classifiers;
4-4: and detecting and identifying the images of the euro coins to be detected by using the trained support vector machine classifier.
The invention has the beneficial effects that:
1. the coin value of the euro coin is determined by taking the area as the characteristic, and the shape and the appearance characteristics of the euro coin are considered, for example, the coin is a circular pattern, the coins with different coin values are different in size, the back patterns of the coins with different countries are different, and the back patterns of the coins with the same country are similar in style. Therefore, the currency value can be determined according to the area of the image target area, and different classifiers are selected for identification according to the currency value, so that problems are decomposed, the problem difficulty is reduced, and the accuracy of subsequent country identification is guaranteed.
2. The invention selects a uniform rotation invariant binary pattern
Figure BDA0001218130310000051
As the local area description features, the feature extraction mode has the anti-rotation transformation capability and inherits the advantage that the local binary pattern LBP is insensitive to monotone illumination change, so that the robustness of the extracted features is ensured.
3. When the method is used for spatial pooling operation, the characteristic that the euro coins are circular patterns is fully utilized, and meanwhile, an annular spatial pooling operation strategy with rotation invariance is adopted, so that the rotation invariance of the whole pattern description is ensured.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a block flow diagram of the present invention.
FIG. 3 is a schematic diagram of the ring template division according to the present invention.
Fig. 4 is a schematic diagram of the LBP calculation process of the present invention.
FIG. 5 is a graph of the accuracy test results of the present invention.
Detailed Description
The invention is further described below with reference to the figures and examples.
As shown in fig. 1 and fig. 2, a euro coin country identification method based on a local binary pattern includes the following steps:
the method comprises the following steps: and acquiring a gray image of the coin, extracting a target area to be detected from the acquired coin image, and performing size normalization processing. The method comprises the following specific steps:
1-1: in order to inhibit the reflection of the metal surface as much as possible, a coaxial light illumination scheme is adopted, and a CCD camera is used for shooting an image and then converting the image into a gray image, so that a gray image I of the euro coin is obtained;
1-2: determining a threshold th according to the background gray value, wherein the threshold th is usually slightly larger than the maximum pixel value of the background area, so that
Figure BDA0001218130310000061
Wherein IBWFor the segmented image, I (x, y) is the coordinate in I: (x，y) A pixel value of (a);
1-3: the binary image IBWPerforming filtering calculation by using an average filter with the size of 10 multiplied by 10 pixels, and then using a hole filling operation;
filling process formula
Figure BDA0001218130310000062
Where X denotes all holes filled, ends when iteration k times,
Figure BDA0001218130310000063
representing a swelling operation, B being a corresponding structural element, ACThe negation of the hole area is shown;
1-4: carrying out corrosion operation on the filtered binary image by using a circular structural element with the radius of 10 pixels to obtain a mask image M, and calculating the area S, the center O and the radius R of a target region through the mask image M; the calculation formula is as follows:
Figure BDA0001218130310000071
Figure BDA0001218130310000072
Figure BDA0001218130310000073
where M, n are the side length of M, Ox，OyIs the coordinate of the oxygen (O),
Figure BDA0001218130310000074
x and y coordinate values representing a value of M (x, y) of 1;
1-5: performing mask calculation on the mask image M and the original image I to obtain a target area image I*Is shown as I*I · M, wherein · is a point multiplier;
1-6: in I*Taking O as the center and 2R as the side length to extract a square area, and normalizing the square area to an image I with the size of 200 multiplied by 200 pixelsROI。
Step two: and performing annular space decomposition on the target region. The method comprises the following specific steps: in a 200 × 200 region, a 24-area circular ring template Ψ is generated with a point (100 ) as a center, overlapping each otheriWherein the radius range of the ith ring is
Figure BDA0001218130310000075
Wherein
Step three: and extracting the uniform rotation invariant local binary pattern of each annular region, counting the histogram distribution characteristics of the annular region, and assembling according to the sequence from the inner ring to the outer ring to obtain the final coin image description characteristics.
The method comprises the following specific steps: each circular ring templateΨiMasking with the original image I to obtain an annular image area Ii，Ii＝I.*Ψi；
3-2: in IiTaking each pixel point as a center, selecting P neighborhoods at the position with the radius r being 1, and aligning the gray value g of the center pixelcGray value g of adjacent pixel pointpComparing, and performing binarization processing according to the magnitude relation to obtain a sum gpValue S corresponding to neighborhood pointpThe calculation is as follows:
Figure BDA0001218130310000081
fig. 4 gives an example of the calculation.
3-3: selecting a certain neighborhood point as a starting point, and forming texture description T ═ S of the current pixel point in the clockwise direction1S2S3S4S5S6S7S8]Then, the value of U is calculated by the following formula, and the value of U is the change times of the texture T in one shift period
Figure BDA0001218130310000082
3-4: will U>2 is divided into a mode value P +1, and a uniform rotation invariant mode is calculated for points with U less than or equal to 2The calculation formula is as follows,
Figure BDA0001218130310000084
3-5: histogram statistics of i-th annular space mode value HiAssembling the coin images in sequence from the inner ring to the outer ring to obtain the final coin image description characteristic F ═ H1H2H3，...，H24]。
Step four: a classifier is designed by utilizing a Support Vector Machine (SVM), and a plurality of classifiers are respectively designed according to different currency values to detect and identify the Euro coins with different currency values. The method comprises the following specific steps:
4-1: designing a classifier by using a support vector machine, wherein a kernel function of the support vector machine is a linear kernel function;
4-2: due to the large difference in the size of euro coins of different denominations, the denomination recognition accuracy based on area can reach 100%. The area S is used as a characteristic to distinguish 5 Euro coins with different currency values, namely 2 Euro, 1 Euro, 50 Euro, 20 Euro and 10 Euro;
4-3: and (3) respectively designing support vector machine classifiers for the Euro coins of 5 different currency values by adopting the finally extracted image description characteristics F, respectively taking 8 pictures on the back surface of each currency coin of 12 countries, taking 96 pictures on the front surface as training samples to learn to obtain 5 SVM classifiers, and taking 8547 pictures as a test set. Selecting enough training samples to learn to obtain 5 support vector machine classifiers;
4-4: the trained support vector machine classifier is used for detecting and identifying the images of the euro coins to be detected, the final statistical accuracy reaches 99.871% (see fig. 5), the error rate is below 0.2%, and the actual application index requirements can be met.

Claims (5)

1. A local binary pattern-based Euro coin country identification method comprises the following steps:
the method comprises the following steps: acquiring a gray image of the coin, extracting a target area to be detected from the acquired coin image, and performing size normalization processing;
step two: performing annular space decomposition on the target area;
step three: extracting a uniform rotation invariant local binary pattern of each annular region, counting histogram distribution characteristics of the annular region, and assembling according to the sequence from an inner ring to an outer ring to obtain final coin image description characteristics;
step four: and designing a classifier by using a support vector machine, and designing a plurality of classifiers according to different currency values respectively to detect and identify the Euro coins with different currency values.
2. The local binary pattern-based euro coin country identification method according to claim 1, wherein: the step one comprises the following specific steps
1-1: acquiring a gray level image I of the euro coin by adopting a coaxial light illumination scheme;
1-2: determining a threshold th according to the background gray value
Wherein IBWFor the segmented image, I (x, y) is the pixel value of the coordinate (x, y) in I;
1-3: the binary image IBWPerforming filtering calculation by using an average filter with the size of 10 multiplied by 10 pixels, and then using a hole filling operation;
filling process formula
Figure FDA0002247625660000012
Where X denotes all holes filled, ends when iteration k times,
Figure FDA0002247625660000013
representing a swelling operation, B being a corresponding structural element, ACThe negation of the hole area is shown;
1-4: carrying out corrosion operation on the filtered binary image by using a circular structural element with the radius of 10 pixels to obtain a mask image M, and calculating the area S, the center O and the radius R of a target region through the mask image M; the calculation formula is as follows:
Figure FDA0002247625660000021
Figure FDA0002247625660000023
where M, n are the side length of M, Ox，OyIs the coordinate of the oxygen (O),
Figure FDA0002247625660000024
x and y coordinate values representing a value of M (x, y) of 1;
1-5: performing mask calculation on the mask image M and the original image I to obtain a target area image I*Is shown as I*I · M, wherein · is a point multiplier;
1-6: in I*Taking O as the center and 2R as the side length to extract a square area, and normalizing the square area to an image I with the size of 200 multiplied by 200 pixelsROI。
3. The local binary pattern-based euro coin country identification method according to claim 2, characterized in that: the second step comprises the following specific steps: in a 200 × 200 region, a 24-area circular ring template Ψ is generated with a point (100 ) as a center, overlapping each otheriWherein the radius range of the ith ring is
Figure FDA0002247625660000025
Wherein
Figure FDA0002247625660000026
4. The Euro coin country identification method based on local binary pattern according to claim 3, characterized in that: the third step comprises the following specific steps:
3-1: connecting each circular ring template psiiMasking with the original image I to obtain an annular image area Ii，Ii＝I.*Ψi；
3-2: in IiSelecting P neighborhoods at radius r by taking each pixel point as a center, and performing gray value g on the P neighborhoodspWith the gray value g of the pointcComparing, and performing binarization processing to obtain angpValue S corresponding to neighborhood pointpThe calculation is as follows:
Figure FDA0002247625660000031
3-3: selecting a certain neighborhood point as a starting point, and forming texture description T ═ S of the current pixel point in the clockwise direction1 S2S3 S4 S5 S6 S7 S8]Then, the value of U is calculated by the following formula, and the value of U is the change times of the texture T in one shift period
3-4: will U>2 is divided into a mode value P +1, and a uniform rotation invariant mode is calculated for points with U less than or equal to 2
Figure FDA0002247625660000034
The calculation formula is as follows,
3-5: histogram statistics of i-th annular space mode value HiAssembling the coin images in sequence from the inner ring to the outer ring to obtain the final coin image description characteristic F ═ H1 H2 H3，...，H24]。
5. The Euro coin country identification method based on local binary pattern according to claim 4, characterized in that: the fourth concrete step is as follows:
4-1: designing a classifier by using a support vector machine, wherein a kernel function of the support vector machine is a linear kernel function;
4-2: the area S is used as a characteristic to distinguish 5 Euro coins with different currency values, namely 2 Euro, 1 Euro, 50 Euro, 20 Euro and 10 Euro;
4-3: respectively selecting enough training samples for Euro coins with different currency values to learn by adopting the finally extracted image description characteristics F to obtain 5 support vector machine classifiers;
4-4: and detecting and identifying the images of the euro coins to be detected by using the trained support vector machine classifier.
CN201710059329.9A 2017-01-24 2017-01-24 Euro coin country identification method based on local binary pattern Active CN106778919B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710059329.9A CN106778919B (en) 2017-01-24 2017-01-24 Euro coin country identification method based on local binary pattern

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710059329.9A CN106778919B (en) 2017-01-24 2017-01-24 Euro coin country identification method based on local binary pattern

Publications (2)

Publication Number Publication Date
CN106778919A CN106778919A (en) 2017-05-31
CN106778919B true CN106778919B (en) 2020-01-07

Family

ID=58942163

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710059329.9A Active CN106778919B (en) 2017-01-24 2017-01-24 Euro coin country identification method based on local binary pattern

Country Status (1)

Country Link
CN (1) CN106778919B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107729902B (en) * 2017-07-28 2021-01-22 湘潭大学 Image microstructure mode feature extraction method for image recognition

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001175911A (en) * 1999-12-17 2001-06-29 Glory Ltd Method and device for discriminating true/false coin from picture image
CN103077528A (en) * 2013-02-25 2013-05-01 南京大学 Rapid image matching method based on DCCD (Digital Current Coupling)-Laplace and SIFT (Scale Invariant Feature Transform) descriptors
CN104036234A (en) * 2014-05-23 2014-09-10 中国科学院国家天文台 Image identification method for crater
CN105005781A (en) * 2015-06-29 2015-10-28 中国人民解放军国防科学技术大学 Robust extended local binary pattern texture feature extracting method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001175911A (en) * 1999-12-17 2001-06-29 Glory Ltd Method and device for discriminating true/false coin from picture image
CN103077528A (en) * 2013-02-25 2013-05-01 南京大学 Rapid image matching method based on DCCD (Digital Current Coupling)-Laplace and SIFT (Scale Invariant Feature Transform) descriptors
CN104036234A (en) * 2014-05-23 2014-09-10 中国科学院国家天文台 Image identification method for crater
CN105005781A (en) * 2015-06-29 2015-10-28 中国人民解放军国防科学技术大学 Robust extended local binary pattern texture feature extracting method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"CHoG: Compressed Histogram of Gradients";Vijay Chandrasekhar etal.;《IEEE》;20091231;第2504-2511页 *

Also Published As

Publication number Publication date
CN106778919A (en) 2017-05-31

Similar Documents

Publication Publication Date Title
CN109299720A (en) A kind of target identification method based on profile segment spatial relationship
CN101398894B (en) Automobile license plate automatic recognition method and implementing device thereof
CN110443128B (en) Finger vein identification method based on SURF feature point accurate matching
CN108596197B (en) Seal matching method and device
Bandeira et al. Detection of sub-kilometer craters in high resolution planetary images using shape and texture features
CN105046252B (en) A kind of RMB prefix code recognition methods
CN104809715B (en) Banknote image slant correction and method for extracting region
CN110472479B (en) Finger vein identification method based on SURF feature point extraction and local LBP coding
CN107967482A (en) Icon-based programming method and device
CN107748877A (en) A kind of Fingerprint recognition method based on minutiae point and textural characteristics
Raju et al. Copy-move forgery detection using binary discriminant features
Youn et al. Efficient multi-currency classification of CIS banknotes
CN104778701A (en) Local image describing method based on RGB-D sensor
CN104182973A (en) Image copying and pasting detection method based on circular description operator CSIFT (Colored scale invariant feature transform)
CN105405138B (en) Waterborne target tracking based on conspicuousness detection
Zeggeye et al. Automatic recognition and counterfeit detection of Ethiopian paper currency
KR101001691B1 (en) Recognizing the Denomination of a Note Using Wavelet transform
CN114596551A (en) Vehicle-mounted forward-looking image crack detection method
Zhang et al. Saliency-driven oil tank detection based on multidimensional feature vector clustering for SAR images
Pawade et al. Comparative study of different paper currency and coin currency recognition method
Sharan et al. Detection of counterfeit Indian currency note using image processing
Al-Hammadi et al. Improving SURF based copy-move forgery detection using super resolution
Bahrami et al. Splicing detection in out-of-focus blurred images
CN106778919B (en) Euro coin country identification method based on local binary pattern
CN105631860B (en) Image point extracting method of the same name based on partial ordering's direction histogram description

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Zhang Dongbo

Inventor after: Wen Dengwei

Inventor after: Chen Honglei

Inventor after: Zhang Ying

Inventor before: Wen Dengwei

Inventor before: Chen Honglei

Inventor before: Zhang Dongbo

Inventor before: Zhang Ying

GR01 Patent grant
GR01 Patent grant