Improved histograms of oriented gradientsfor Chinese RMB currency recognition

Hu Xuejuan，Ruan Shuangchen，Guo Chunyu，and Liu Chengxiang

Shenzhen Key Laboratory of Laser Engineering，College of Electronic Science and Technology，

Key Laboratory of Advanced Optical Precision Manufacturing Technology of Guangdong Higher Education Institutes，Shenzhen University，Shenzhen 518060，P.R.China

Improved histograms of oriented gradients
for Chinese RMB currency recognition

Hu Xuejuan，Ruan Shuangchen?，Guo Chunyu，and Liu Chengxiang

Shenzhen Key Laboratory of Laser Engineering，College of Electronic Science and Technology，

Key Laboratory of Advanced Optical Precision Manufacturing Technology of Guangdong Higher Education Institutes，Shenzhen University，Shenzhen 518060，P.R.China

This paper presents a method to improve the histograms of oriented gradient descriptors and support vector machine classifier for Chinese RMB currency recognition.The zebra-stripe pattern of the infrared images of RMB paper currency was used for real and counterfeit classification.The dimension of histograms of oriented gradient features is decreased by feature block selection based on the Fisher criterion.Several experiments on zebra-stripe pattern recognition were conducted，and the proposed method shows its robustness against background interference and noise.

infrared image;Chinese RMB currency recognition;histogram of oriented gradients;support vector machine;Fisher criterion;precision counterfeit detection;image feature extraction

Special inks that absorb infrared(IR)light are used in printing paper currency，which could be an important cue for counterfeit identification.Security ink that absorbs near-IR(NIR)light is an organic functional dye made up of one or several NIR absorption materials.This ink absorbs light waves with wavelengths ranging from 700 nm to 1 100 nm.When used as a localized portion of a printed product，this ink is invisible in daylight and can only be observed with a detection apparatus［1］.The NIR-absorbing material is synthesized under high temperature，which is a highly technical and costly process.Thus，NIR security ink is difficult to forge and effective for anti-counterfeit guarantee.

IR security inks have been widely used by many banknotes.For example，local IR security is used in the dollar，euro，and Portuguese banknotes.By imaging in NIR light，part of the pattern of several different banknotes is hidden selectively.For example，the pattern in Italian banknotes is almost entirely hidden except for the serial number.The IR security pattern of the 2005 edition of the renminbi(RMB)and the Comorian franc not only disappears but also shows another pattern.

Through IR transmission imaging，a zebra-stripe anticounterfeit pattern invisible in sunlight is presented in the security line area of the 2005 edition of the 10，20，50 and 100 RMB notes.Counterfeit paper currency has been reported to show a realistic watermark，an optical variable ink，an invisible denomination，magnetic and ultraviolet characteristics［2］，but no forged IR zebra stripes.Thus，the special characteristics of the IR anti-counterfeit method bring unique advantages for paper currency discrimination.Despite that some works have addressed the problem of money recognition，to the best of our knowledge，there are only a few works dealing with the problem of the authentication of the money.

In Ref.［3］，light transmittance and an instance-based classifier by the Euclidean distance metric are used to classify the value of banknote.Feature extraction using wavelet Transform and the minimum Euclidean distance matching is described in Ref.［4］for Korean Won bill classification，where image is acquired in the visible light spectra.In Ref.［5-6］，Neural network and genetic algorithm have been exploited to address the problem of banknote recognition.In Ref.［7］，US banknote recognition has been proposed by sped up robust features.However，these approaches in the above references do not take into account the problem of banknote counterfeit detection，which is the main issue addressed in this paper.

Ref.［8］addresses the problem of Sterling banknote validation through a cascade of segmentation and classification procedures.But the applicability is not straightforward in the context of the RMB，because this currency encodes different strategies to avoid forgeries.In Ref.［9］，a method based on multiple-kernel support vector machines is proposed to detect counterfeit Taiwanese currency.Banknotes are firstly divided into partitions，and the luminance of histograms of the partitions is taken as the input of the system.In Ref.［10］，the color domain has been considered for US banknote validation.In Ref.［11］，the euro banknote image is acquired in the visible light spectrum and two types of neural networks are used for classification.While all of the approaches in Ref.［9-11］work in the visible spectrum，they are actually not robust as most of the tampered banknotes visually look like the genuine one.In Ref.［12］，a NIR camera is used to acquire the Euro banknotes images.The average gray value feature and simple thresholding strategy were used for authentication.However，simple average gray value feature descriptors are not robust for geometric and photometric deformation of image.And histograms of oriented gradients(HOG)features are local and robust feature descriptors，which have a disadvantage of higher feature dimensions.

In this paper，the NIR images of RMB currency are acquired for counterfeit detection.To represent the discriminative zebra-stripe anti-counterfeit pattern，improved histograms of oriented gradients are proposed for feature extraction.Support vector machines(SVM)are used for classification.A database with 540 images captured from 500 real notes and 40 counterfeit notes are used for training and testing and as high as 99.03%accuracy has been achieved.

The remainder of the paper is organized as follows:section 1 describes the preprocessing of NIR image of the 100 RMB paper currency and summarizes the proposed algorithms for HOG feature extraction and feature block selection.In section 2，the designed counterfeit detection method is described，whereas experimental results are presented.Finally，conclusions are given.

1 HOG feature extraction and selection

In this paper，the detected samples are the 2005 edition of 100 RMB paper currencies.An IR image acquisition system as described in Ref.［13］is used to capture the IR transmission image of the paper currencies，so we can distinguish the real money from the counterfeit by the recorded zebra-stripe anticounterfeit pattern of the IR imaging，including a set of alternating bright and dark rectangular blocks.Fig.1(a)shows an example of the detected pattern，which consists of a group of alternating bright and dark blocks with a cycle of 2×H，2 times of the width of the bright or dark blocks，and a black line crossing normally the zebra-stripe pattern.In our image preprocessing，if no solid security line appears in the image，the cur-rency is directly recognized as the counterfeit.Otherwise，we locate the horizontal ordinate of the region of interest(ROI)center by the security line，thus two 16-pixel wide rectangle regions were segmented from the left and right sides of the security line to produce the zebra-stripe pattern of interest.Following that，a region with size 5H × 32 can be extracted as ROI for feature extraction shown in Fig.1(b).

Fig.1 (Color online)IR image of the security line region and region of interest圖1 安全線區(qū)域和感興趣區(qū)域的紅外圖像

HOG was introduced by Dalal and Triggs in 2005［14］and has been successfully used in pedestrian detection.The main principle of HOG is that shape characteristics can be properly described by the density distribution of the gradient or edge direction.To extract HOG feature，the ROI region(32×128)extracted was divided into a number of blocks consisting of 2×2 cells，where each cell is composed of 8 ×8 pixels.For each cell，gradient direction and magnitude were calculated using the gradient operator［-1，0，1］shown by

where I(x，y)is the pixel value at position(x，y)in the image，α(x，y)indicates the gradient direction of the pixel，and G(x，y)indicates the gradient amplitude.An HOG can then be calculated for each cell by weighted voting of every pixel.In this paper，Gaussian-weighted gradient amplitude and tri-linear interpolation are used to obtain the weight.The histogram vectors over the block were then normalized through L2-norm normalization:

where υ indicates a normalized histogram vector over the block，indicates k-norm calculation，k equals 1 or 2，and ε is a minimal constant that prevents yielding infinite values.A perblock normalization scheme is intended to compensate for variations of lighting over the input image.All normalized histogram vectors were combined as a full feature vector with size n×m，where n indicates the dimension of the histogram vector over the block，and m indicates the number of blocks in the detection windows(the region of interest).In this paper，m is 45，and n is 36.The combined vectors were then fed to a SVM for object/non-object classification.

However，feature vectors based on HOG are high dimensional.For example，when the bin number was set as 9 and the overlap rate of block set as 0.5，the dimension of the feature vector was 45×4×9=1 620.High dimensional feature brings about the complex and large calculation on feature extraction，training，and classification.As the edge directions of the Zebra stripes are mainly vertical and horizontal，we propose to use the Fisher criterion to remove redundant HOG features.According to the criterion，the feature with the better ability of discrimination shall show larger similarity within a group than that among groups.Through feature ranking，better feature blocks can be selected.

Let ωRbe the category of the real currency and ωCbe that of the counterfeit，and NRand NCbe the number of samples belong to categories ωRand ωCrespectively.The within-class scatter Sifor ith class，the whole within-class scatter Swand between-class Sbcan be calculated as below:

where X denotes the HOG feature extracted from a block，midenotes the mean feature for class ωRand ωC.The bigger the value of Sb/Sw，the better the discrimination capacity of the feature X.

The HOG feature blocks that have more discrimination information can thus be identified.Given a number of N blocks for HOG feature extraction，the feature block selection process can be described as follows:

a.Calculate the HOG feature Xifor each block.

b.Calculate Fisher score Si(i=1，2，...，N)for each feature Xi.

c.Sort Fisher score Si(i=1，2，...，N)in descending order.

d.Select the maximum of Si(i=1，2，...，N)as feature to input SVM classifier and calculate classification accuracy R.

e.Given preset classification accuracy Rtwhich meet system requirement，if R ＞ Rt，we stopped adding Fisher score from the rest of Si.Otherwise select a next maximum from the rest of Si(i=1，2，...，N)to input SVM classifier until the new classification accuracy R is bigger than Rt.

f.Output the selected M HOG feature blocks.

2 Paper currency authentication and experimental results

Once the ROI region around the security line was located，the HOG feature was extracted and input to SVM for real and counterfeit currency identification.SVM theory mainly focuses on binary class pattern recognition problems［15］.Let the training set be{(x1，y1)，(x2，y2)，...，(xn，yn)}，where xi∈Rnand yi∈ {-1，1}represent the HOG feature vectors and the class label，respectively.If the training set can be partitioned by a hyperplane，the hyperplane is expressed as W·X+b=0，where W and b determine the position of the hyperplane.The problem could then be transformed into one on solving the optimal hyperplane to obtain the optimal partition of the training set.Thus，an optimization model function was established:

where W indicates the coefficient vector of the separating hyperplane in the feature space，and b indicates the classification threshold.The relaxation factor ξiwas introduced given the classification error.C indicates the penalty term of wrongly classified samples，and n the number of training samples.

A decision function was then derived:

The NIR images of the 2005 edition of the 100 yuan RMB banknote were acquired using the NIR light with wavelength of around 850 nm for testing.Our dataset consists of 540 images captured from 500 real notes and 40 counterfeit notes.The position，width and height of the ROI were determined in the preprocessing stage.The sizes of the IR image and ROI are 640×480 and 32 × 128 pixels，respectively.All the algorithms in this paper were implemented with MATLAB R2011b and they were practical and applicable to similar security features of banknote identification systems.

In this experiment，the positive samples number is 500 and the negative samples number is 40.We randomly split the positive and negative samples into training and testing sets，50%as training and 50%as testing.While 250 positive and 20 negative samples were used to select HOG features and train SVM，another set of 250 positive and 20 negative samples were used for testing.We repeated the experiment 10 times，and each time used a different 50%of the sample as training and testing.

The accuracy，miss rate，and false positive rate(FPR)were then calculated according to formulas(9)to(11)，and compared with those of Ref.［16］.

where TP is the number of true positive instances;FN is the number of false negative instances;FP is the number of false positive instances，and TN is the number of true negative instances.

We first select the most discriminative features using the algorithm presented in section 2.The selection process stopped when 20 HOG features were selected and 99.03%accuracy was achieved.Fig.2 shows the variations of classification accuracy with the number of image blocks selected for feature ex-traction.One can observe from the figure that the accuracy increase significantly at the beginning，and become stable when the number of block exceeds 20.In the region of interest，these important selected blocks were located at the area of bright and dark edge.

Fig.2 Relation of selected block number with classification accuracy rate圖2 特征塊選取數(shù)與分類準確率的關系

Grid search algorithm was used to determine the optimum parameters(C，γ)of C-SVM by cross-validation.Grid search required less time and had higher cross-validation accuracy.The result of the parameter selection was in Fig.3.

Fig.3 (Color online)Results of parameter selection through grid search圖3 利用網(wǎng)格法選擇參數(shù)結(jié)果

Table 1 shows the performance of the proposed method in terms of accuracy，miss rate，F(xiàn)PR and efficiency，together with that of approach developed in Ref.［16］.An infrared feature extraction algorithm based on convolution and experience threshold classification method was proposed in Ref.［16］.By using horizontal projection and selecting appropriate convolution kernels，better paper currency identification accuracy is achieved in Ref.［16］.Three methods in table 1 obtain accuracy more than 99%，miss rate no more than 1%，and FPR 0%.However，the method proposed in this paper has higher efficiency.The average detection times for each image for these three methods are 0.85，0.56 and 0.25 s，respectively.Obviously，the average detection time is greatly shortened when improved HOG descriptors were used.In conclusion，the method in this paper improves efficiency of paper currency identification and achieved better accuracy.

Table 1 Comparison of statistical results表1 統(tǒng)計結(jié)果的比較

Conclusions

The IR zebra-stripe anti-counterfeiting pattern is difficult to forge，so recognition of the IR zebra-stripe contributes to RMB banknotes authentication in practical application.In addition，the HOG feature has a better description of shape characteristics of object and is robust for geometric and photometric deformation of image.HOG is selected as feature descriptors in this paper.In order to reduce its dimensionality and improve identification efficiency，an optimized HOG feature was extracted and input to C-SVM for classification，which is used in new application fields.Compared to the state-of-the-art algorithms，the proposed method makes use of infrared imaging and recognizes the forgeries rather than the value.The experiments performed on real notes and counterfeit notes provided by the Chinese bank demonstrate good performance on accuracy and efficiency.Furthermore，this method is robust to low contrast and background noise.Future work will be devoted to add other security features(e.g.the great hall of the people，watermark，etc)validation to further improve the recognition accuracy.In addition to the Chinese RMB，the extension of current method to other currencies such as US Dollars and HK Dollars will also be considered.

［1］［s.n.］.IR Security Inks Application on the Paper Currency ［EB/OL］.［2011-12-30］.http://blog.jibi.net/group.asp?cmd=show＆gid=4＆pid=242.(in Chinese)

佚 名.紅外防偽油墨在紙幣上的應用［EB/OL］.［2011-12-30］.http://blog.jibi.net/group.asp?cmd=show＆gid=4＆pid=242.

［2］Liang Youjie.Security technology of RMB and identification［M］.Beijing:China Financial Publishing House，2005:226-272.(in Chinese)

梁友杰.人民幣防偽技術及真?zhèn)舞b別［M］.北京:中國金融出版社，2005:226-272.

［3］Hinwood A，Preston P，Suaning G，et al.Bank note recognition for the vision impaired ［J］.Australasion Physical and Engineering Science in Medicine，2006，29(2):229-233.

［4］Choi E，Lee J，Yoon J.Feature extraction for bank note classification using wavelet transform ［C］//The 18th International Conference on Pattern Recognition.Hong Kong(China):IEEE Press，2006，2:934-937.

［5］Takeda F，Omatu S.Bank note recognition system using neural network with random masks［C］//Proceeding of the World Congress on NeuralNetworks.Portland(USA):International Neural Network Society，1993:I-241-I-244.

［6］Takeda F，Nishikage T，Matsumoto Y.Characteristic extraction of paper currency using symmetrical masks optimized by GA and neuro-recognition of multi-national paper currency［C］//International Conference on Neural Networks.Alaska(USA):IEEE Press，1998，1:634-639.

［7］ Hasanuzzaman F M，Yang X，Tian Y.Robust and effective component-based banknote recognition for the blind ［J］.IEEE Transactions on Systems，Man，and Cybernetics，Part C:Applications and Reviews，2012，42(6):1021-1030.

［8］He C，Girolami M，Ross G.Employing optimized combinations of one-class classifiers for automated currency validation ［J］.Pattern Recognition，2004，37(6):1085-1096.

［9］He C，Girolami M，Ross G.Employing optimized combinations of one-class classifiers for automated currency validation ［J］.Pattern Recognition，2004，37(6):1085-1096.

［10］Ionescu M，Ralescu A.Fuzzy hamming distance based banknote validator［C］//The 14th IEEE International Conference on the Fuzzy Systems.Vancouver(Canada):IEEE Press，2005:300-305.

［11］Masato A，Tetsuo K，Yoshiyasu T.Euro banknote recognition system using a three-layered perceptron and rbf networks［J］.IPSJ Transactions on Mathematical Modeling and Its Applications，2003，44:99-109.

［12］Bruna A，F(xiàn)arinella G M，Guarnera G C，et al.Forgery detection and value identification of Euro banknotes ［J］.Sensors，2013，13(2):2515-2529.

［13］Hu Xuejuan，Ruan Shuangchen，Yang Jinhui，et al.An I-dentification Device for Paper Currency or Notes:China，201120235245.4 ［P］.2012-02-08.

［14］Dalal N，Triggs B.Histograms of oriented gradients for human detection［C］//International Conference on Computer Vision and Pattern Recognition.San Diego(USA):IEEE Press，2005，1:886-893

［15］ Vapnik V N.The nature of statistical learning theory［M］.New York(USA):Springer-Verlag，1995.

［16］Hu Xuejuan，Liu Chengxiang，Yang Jinhui，et al.Convolution approach for zebra stripe feature extraction of infrared paper currency image［J］.Laser＆ Infrared，2012，42(10):1196-1201.(in Chinese)

胡學娟，劉承香，楊錦輝，等.基于卷積運算的紙幣紅外圖像斑馬線特征提取 ［J］.激光與紅外，2012，42(10):1196-1201.

基于改進梯度方向直方圖的人民幣識別

胡學娟，阮雙琛，郭春雨，劉承香

深圳市激光工程重點實驗室，深圳大學電子科學與技術學院，廣東省高校先進光學精密制造技術重點實驗室，深圳518060

提出一種基于改進梯度方向直方圖和支持向量機分類器的人民幣識別方法.利用人民幣紅外圖像中斑馬線特征進行真?zhèn)巫R別，通過Fisher準則進行特征塊選擇實現(xiàn)梯度方向直方圖特征的降維.針對斑馬線防偽圖案進行實驗.結(jié)果表明，該方法能克服紅外圖像中的背景干擾和噪聲，得到較好鑒偽結(jié)果.

紅外圖像;人民幣紙幣識別;梯度方向直方圖;支持向量機;Fisher準則;精密鑒偽;圖像特征提取

國家自然科學基金資助項目 (61308049);廣東省自然科學基金博士啟動資助項目 (S2013040012496)

胡學娟 (1981—)，女 (漢族)，湖北省安陸市人，深圳大學助理研究員、博士.E-mail:xjhu@szu.edu.cn

/References:

O 439;TP 391

A

10.3724/SP.J.1249.2014.05487

2014-04-01;

2014-08-05

Foundation:National Natural Science Foundation of China(61308049);PhD Start-up Fund of Natural Science Foundation of Guangdong Province(S2013040012496)

?

Professor Ruan Shuangchen.E-mail:scruan@szu.edu.cn

:Hu Xuejuan，Ruan Shuangchen，Guo Chunyu，et al.Improved histograms of oriented gradients for Chinese RMB currency recognition ［J］.Journal of Shenzhen University Science and Engineering，2014，31(5):487-492.

引 文:胡學娟，阮雙琛，郭春雨，等.基于改進梯度方向直方圖的人民幣識別［J］.深圳大學學報理工版，2014，31(5):487-492.(英文版)

【中文責編:方 圓;英文責編:海 潮】