In the processing of our project they had added and remaved noise, does anyone know why this was done?

1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 | 978-1-4577-0697-4/12/$26.00 ©2012 IEEE Image Recognition and Processing Using Artificial Neural Network Md. Iqbal Quraishi, J Pal Choudhury Dept. of Information Technology Kalyani Govt Engineering College, Kalyani, Nadia, India [e-mail], [e-mail] Mallika De Dept. of Engg and Tech Studies University of Kalyani, Kalyani, Nadia, India [e-mail] Abstract: There are several techniques for image recognition. Among those methods, application of soft computing models on digital image has been considered to be an approach for a better result. The main objective of the present work is to provide a new approach for image recognition using Artificial Neural Networks. Initially an original gray scale intensity image has been taken for transformation. The Input image has been added with Salt and Peeper noise. Adaptive median Filter has been applied on noisy image such that the noise can be removed and the output image would be considered as filtered Image. The estimated Error and average error of the values stored in filtered image matrix have been calculated with reference to the values stored in original data matrix for the purpose of checking of proper noise removal. Now each pixel data has been converted into binary number (8 bit) from decimal values. A set of four pixels has been taken together to form a new binary number with 32 bits and it has been converted into a decimal. This process continues to produce new data matrix with new different set of values. This data matrix has been taken as original data matrix and saved in data bank. Now for recognition, a new test image has been taken and the same steps as salt & pepper noise insertion, removal of noise using adaptive median filter as mentioned earlier have been applied to get a new test matrix. Now the average error of the second image with respect to original image has been calculated based on the both generated matrices. If the average error is more than 45% then a conclusion can be made that the images are different and cannot be matched. But if the value of average error has been found to be less than or equal to 45%, an effort has been made to use the artificial neural network on test data matrix with reference to original data matrix thereby producing a new matrix of the second image(test image). The total average error has been calculated on generated data matrix produced after the application of artificial neural networks on test data matrix to check whether proper identification can be made or not. It has been observed that the value of average error is less than that of test image without application of artificial neural network. Further it has been observed that the test image is matching and recognized with respect to original image. Keywords: component; Digital Image Processing, Artificial Neural Network, The Feed forward back propagation neural network , Gray scale intensity Image, Salt and Pepper noise, Adaptive median filter. I. INTRODUCTION The main aim of image processing is to alter the visual impact such that the information content improves and as a result the said image is more suitable than original image. This technique helps in getting a better visibility of any portion or feature of interest of an image and suppressing the information in other portion or feature of that image. Image Recognition has been dedicated with finding the identity of an object being observed in the image from a set of known labels. Different Recognition techniques are available for use but the selection of an appropriate choice of such techniques depends mainly on a given task at hand and some other related parameters. Soft Computing is an emerging field built up of latest techniques like fuzzy logic, artificial neural networks, evolutionary computation and machine learning. Each soft computing technique can be applied to produce solutions to any problem that are too complex or noisy to tackle with conventional methods. This paper will provide a new approach for image recognition and processing using Artificial Neural Network. Artificial Neural Network has been one of the recent development tools that are inspired from biological neural networks. The main advantage of this new powerful tool is to use its capacity to solve problems that are not very easy to be solved by traditional computing methods. The traditional computers use step by step approach in solving a problem and each step should be well defined and computable. The computer cannot solve the problem if any step that the computer needs to follow is not known. So to solve a problem using a computer need all knowledge of how to solve the problem. But Artificial Neural Networks are new techniques that follow a different way from traditional computing methods to solve problems. Artificial Neural Networks may be considered as much more powerful because it can solve problems where how to solve have been not known exactly. Uses of artificial neural network have been spread to a wide range of domain like image recognition, fingerprint recognition and so on. Artificial Neural Networks have the capability to adapt, 1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 | learn, generalize and organize data. Some of the known structures of artificial neural network are perceptron, Adaline, Madaline, Kohonen, Back Propagation. II. RELATED WORK The appearance of digital computers [1] and the development of modern theories of learning and neural processing both occurred at about the same time, during the late 1940s. The study of artificial neural systems (ANS) [2] on computers remains an active field of biomedical research. Since that time, the digital computer has been used as a tool to model individual neurons as well as clusters of neurons, which are called neural networks. Traditional techniques from statistical pattern recognition were popular until the beginning of the 1990s.In the new era, 2000, Robert P.W. Duin, and Jianchang Mao [3] gave us a holistic summary and compared some well known methods in pattern recognition system. The review was mainly meant for statistical approaches. Artificial neural network (ANN) was discussed there as a part. As it is found that statistical methods are more or less suffer from unavailability of general mathematical methods for recognition of features. A new approach for feature extraction based on the calculation of eigen values from a contour was proposed and found that using feed forward neural network satisfactory results were obtained [4]. Artificial neural networks have increasingly been used as an alternative to classic pattern classifiers and clustering techniques. In the field of medical image processing, Kenji Suzuki [5] compared pixel based and non pixel based ANNs to show that the former approach is much better when it comes to segmentation and feature calculation. The paper also concludes that Massive-Training ANNs (MTANNs) can be used to enhance images. In 1993 review article on image segmentation, Pal and Pal [6] predicted that neural networks would become widely applied in image processing. Segmentation, based on neural networks is found to show rich capabilities [7]. Another related work in the domain of medical image processing shows artificial neural network for image segmentation. The approach was conjugated with real time applications. A hybrid neural network was proposed [8]. When compared with eigen face method this hybrid neural network shows that error rate found to be producing satisfactory results. A more real time approach in the direction of the advancement of artificial neural networks has show that, how the detection and quantification of persons can be done in cluttered beach scenes [9]. It shows neural-based classification system. An approach to perform neutral facial image recognition using Parallel Hopfield Neural Networks [10], shows encouraging results in recognition rate. A survey based on Hopfield neural networks was published in the year of 2007[11], where a broad Theoretical review of the concept was presented. Object recognition consists of locating the positions and possibly orientations and scales of instances of objects in an image. The purpose may also be to assign a class label to a detected object. Some other types of ANNs like feed-forward artificial neural network approaches can also be used for object recognition. Feed-forward networks usually consist of three to four layers in which the neurons are logically arranged. The first and last layers are the input and output layers respectively and there are usually one or more hidden layers in between the other layers. Here information is only allowed to "travel" in one direction. This means that the output of one layer becomes the input of the next layer, and so forward. In order for this to occur, each layer is fully connected to next layer and each neuron is connected by a weight to a neuron in the next layer. This paper aims to provide an alternative solution for object Recognition using Artificial Neural Network. Initially an original gray scale intensity image has been taken as a reference and it is saved as original data bank. For processing the method of transformation has been applied on the original image. Initially an original gray scale intensity image has been taken for transformation. The Input image has been added with Salt and Peeper noise. Adaptive median Filter has been applied on noisy image such that the noise can be removed and the output image would be considered as filtered Image. The estimated Error and average error of the values stored in filtered image matrix as have been calculated with reference to the values stored in original data matrix for the purpose of checking of proper noise removal. Now each pixel data has been converted into binary number (8 bit) from decimal values. Then a set of four pixels has been taken together to form a new binary number with 32 bits. Thereafter the binary number has been converted into a decimal number. This process has been continued for whole image row wise such that a new data matrix with different set of values has been produced. This data matrix has been taken as original data matrix and saved in data bank for reference. Now for recognition, a new test image has been taken and the same steps as salt & pepper noise insertion, removal of noise using adaptive median filter as mentioned earlier have been applied to get a new test matrix. Now the average error of the second image with respect to original image has been calculated based on the both generated matrices. If percentage error is more than 45% then a conclusion has been made that the images are different and not matching and no recognition is possible. On the other hand if the average error has been found to be less than or equal to 45%, an effort has been made to use artificial neural network on test data matrix with reference to original data matrix to produce a new matrix of the second image. The average error has been calculated on generated data matrix produced after applying Artificial Neural Network on test data matrix. It has been observed that if the average error is less than that of the value obtained earlier then it has been concluded that the images are matching and therefore can be recognized. A flow diagram for Image Recognition and Processing using Artificial Neural Network has been furnished in Fig -1 1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 | Fig -1 Flow Diagram III. IMPLEMENTATION A. Processing of Original Image. Step 1. The initial optimal image has been taken as furnished in Fig -2 which has been considered as original image. For simplicity first 10X10 matrix elements of Original image are shown. Table -1 Input Data Matrix 158 159 159 158 155 153 153 154 150 158 155 156 156 155 152 151 151 152 151 160 153 154 155 154 152 150 151 152 153 162 154 156 156 156 154 153 154 155 156 164 153 155 156 156 155 154 155 157 159 166 151 153 154 154 154 154 155 157 163 166 152 153 155 156 155 155 157 159 166 165 154 156 158 159 158 159 160 162 167 164 156 158 159 158 160 163 166 167 167 164 161 161 160 160 161 163 165 165 164 162 Step 2. The Input image has been added with Salt and Peeper noise. The average error after insertion of salt and pepper noise has been calculated which is 25.67%. For simplicity first 10X10 matrix elements of Original image with Noise are shown. Table -2 Input Data Matrix with Noise 158 159 159 158 155 153 153 154 255 158 155 156 156 155 152 151 151 152 0 160 255 154 155 154 152 0 151 255 153 255 154 156 156 156 154 153 0 155 156 164 153 255 0 156 155 154 0 157 159 166 0 153 154 255 255 0 155 255 163 166 152 255 155 156 255 155 157 159 166 165 154 255 158 159 0 255 160 162 0 164 156 158 0 158 160 255 166 0 167 164 161 161 160 160 161 163 165 165 164 162 B. Processing of Noisy Image Step 3. Adaptive median Filter has been applied on noisy image such that the noise can be removed and the output image would be considered as filtered Image. Step 4. The estimated Error and average error of the values stored in filtered image matrix have been calculated with reference to the values stored in original data matrix. The average error has been found as 5.397%. This shows the subsequent removal of noise. Step 5. The original image after removal of noise has been transformed into data matrix containing pixel values which have been furnished in Table -3. For simplicity first 10X10 matrix elements are shown. Table -3 Input Data Matrix after Noise Removal 145 173 164 155 163 143 172 140 152 159 176 141 151 152 155 151 140 168 152 160 132 160 164 136 172 0 162 145 154 163 173 154 141 167 149 175 139 161 156 165 138 154 153 156 152 146 160 158 159 165 167 152 165 155 155 153 146 160 162 165 155 136 157 151 155 166 153 175 164 164 149 169 157 162 163 154 170 152 166 164 155 157 158 157 158 162 165 166 163 166 160 160 160 159 160 162 164 164 163 163 Step 6. For easier calculation four pixels have been taken together. The four pixels have been taken row wise and converted into individual binary numbers. Step 7. The binary values of four pixels together side by side have been combined and formed as 32 bit binary number. Step 8. Now the 32 bit binary number has been converted into a decimal number. 1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 | Step 9. The decimal number as generated in step 5 has been placed in original data matrix termed as ORMAT[][], which have been furnished in Table-4. Table -4 Original Data Matrix ORMAT[][] 2444076187 2744102028 2560599206 2846199930 1599955047 2962069400 2610400424 2560665254 2812448634 1583111782 2225120392 2885722769 2594416807 2778697081 1549426020 2912587175 2511309729 2628102566 2728168313 1566203236 2325387676 2559746206 2678433956 2711325304 1566269029 2811798939 2610533024 2728764833 2711456630 1583111782 2609421719 2611386799 2762252702 2711653493 1549426020 2510921122 2744822424 2795806364 2728496500 1532583011 2610798237 2661459366 2745607070 2661126013 1499029093 2694881439 2695013540 2745409178 2678497685 1482186084 Step 10. The instructions furnished in step 6 to step 9 have been repeated for the total pixel value of the original image after noise removal as stored in Table -3. Therefore a matrix has been produced which has been stored in data matrix termed as ORMAT[][] as furnished in Table-4. It is to note that first 10X10 matrix elements are shown in Table-4 for easier presentation. C. Processing of second Image (Test Image) A new image has been taken which is considered as a test image. Now it is necessary to check whether the said image can be recognized or not. The test image has been furnished in Fig-5. For simplicity first 10X10 matrix elements of Test image(test data matrix) are shown as furnished in Table-5. Table -5 Test data Matrix 161 160 160 159 158 158 158 158 155 155 155 155 155 154 154 154 154 154 153 153 152 152 153 153 153 153 153 153 152 153 154 155 156 156 156 156 156 155 153 153 155 156 157 157 156 155 154 153 148 147 154 154 154 154 152 149 146 145 137 135 154 154 153 152 148 144 140 138 129 126 156 156 155 153 148 143 139 136 126 123 156 155 153 151 148 144 139 134 130 121 160 158 156 155 153 150 146 143 136 127 Step 11. Instructions as furnished in step 2 have been executed on test image to generate test data matrix with noise as furnished in Table -6. Table -6 Test data Matrix with Noise 161 160 160 255 158 158 158 158 255 155 155 155 155 154 154 154 154 255 153 255 152 152 153 153 153 153 153 153 255 153 154 155 156 156 156 156 156 155 153 153 155 156 157 157 156 155 0 153 148 147 154 154 154 154 152 149 146 145 137 255 154 154 255 152 0 144 140 138 255 255 0 156 155 153 0 143 139 136 126 0 156 155 255 151 148 144 139 134 130 121 160 158 255 155 153 150 146 143 136 127 Step 12. Instructions as furnished in step 3, 4 have been executed on test image with noise to generate test data matrix after noise removal as furnished in Table -7. Table -7 Test data Matrix After Noise Removal 160 161 160 158 155 154 154 156 149 159 155 156 156 154 152 151 152 153 151 159 152 153 154 153 152 151 152 154 151 156 152 154 156 156 154 154 154 156 151 151 152 154 156 156 154 153 153 154 153 149 151 153 154 153 150 148 146 146 152 146 151 152 153 151 147 143 140 139 141 134 152 154 154 152 147 141 138 136 128 122 157 158 156 151 145 141 137 134 130 120 162 161 158 154 150 148 145 143 137 127 Step 13. Procedures as mentioned from step 5 to step 9 have been executed on test image after noise removal to generate the decimal number which has been placed in test data matrix TESTMAT[][], which have been furnished in Table -8. Table -8 TESTMAT[][] 2694946974 2610600604 2510268328 2846133877 1566857841 2610732186 2560071833 2543821987 2762051193 1749640558 2560203417 2560071834 2543623579 2627506047 2039312775 2560269468 2593823388 2543293584 2442300546 2355928947 2560269468 2593757594 2576715398 2206433146 1903127414 2543426201 2526319250 2559739773 2004054125 1636001889 2543360407 2475658379 2374401397 1869244777 1701341285 2560268952 2475526792 2155508591 1802070636 1751408137 2644417687 2441972102 2188931182 1784963943 1667853056 2728500890 2526318991 2306831729 1818583910 1918727780 D. Calculation of Average Error of test data matrix based on original data matrix. Step 14. The estimated Error and average error of the values stored in decimal matrix as furnished in Table- 9 have been calculated with reference to the values stored in original data matrix as stored in Table 4. The average error has been found as 31%. The Estimated errors have been furnished in Table -9. Table -9 Estimated Error data 0.102644422 0.048650314 0.019655898 2.32074E-05 0.020686335 0.11861208 0.019280027 0.006577692 0.017919417 0.105190788 0.150590964 0.112849002 0.019577898 0.054410765 0.316173053 0.120963832 0.032856823 0.032270043 0.104783772 0.504229396 0.101007584 0.013287016 0.037976877 0.186216002 0.215070578 0.095445209 0.032259226 0.061941967 0.260893904 0.033408953 0.025316457 0.051975609 0.140411232 0.310662376 0.098046156 0.019653278 0.098110402 0.229020787 0.339537127 0.142781908 0.012877077 0.082468764 0.202751477 0.329244863 0.112622206 0.012475299 0.062595065 0.159749393 0.321043315 0.294525566 Step 15. Since the average error is less than 45%, necessary steps regarding the processing of test image has been made using the technique of artificial neural network for the purpose of recognition. 1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 | E. Processing of Image towards recognition using Artificial Neural Network. Step 16. The feed forward back propagation neural network has been used on the test data matrix of the test image for training and testing with reference to the original data matrix of the original image. A new data matrix named NEWMAT[][] has been produced as a result which has been furnished in Table -10. It is to note that the number of columns of the data matrix ORMAT[][] or TESTMAT[][] or NEWMAT[][] has been one fourth of the total number of columns in the Original Image data or Test Image data. So it takes considerably less time to complete the training and Testing using ANN. Table -10 Data Matrix NEWMAT[][] after ANN application 34996695 34996695 34996695 34996695 34996695 41271463 133924677 41271463 41271463 41271463 1980749736 1980749736 1980749736 1980749736 1980749736 2046388571 2046388571 2046388571 2046388571 2046388571 1976167179 1976167179 1976167179 1976167179 1976167179 2034758941 2034758941 2034758941 2034758941 2034758941 2025488160 2025488160 2025488160 2025488160 2025488160 2010595645 2010595645 2010595645 2010595645 2010595645 2011606687 2011606687 2011606687 2011606687 2011606687 1967583086 1967583086 1967583086 1967583086 1967583086 Step 17. Each value of the data matrix NEWMAT[][] has been converted into 32 bit binary number. Step 18. Now the 32 bit binary number has been divided into four 8 bit binary numbers. Step 19. Each 8 bit binary value has been converted into decimal and each of them has been considered as pixel values for four consecutive pixels row wise. Step 20. The instructions furnished in step 17 to step 19 have been repeated for the total values of the data matrix NEWMAT[][]. As a result a new modified data Matrix named MODMAT[][] has been produced as furnished in Table -11. It is to note that first 10X10 pixels are stored in Table -11 for better presentation. Table -11 Modified Data Matrix MODMAT[][] 164 131 170 161 149 152 157 165 170 168 16 176 129 152 166 154 156 163 164 161 0 159 160 161 144 166 162 167 165 159 165 141 158 173 139 160 160 164 160 153 154 162 155 160 163 160 163 166 162 154 163 157 160 162 166 166 162 170 150 156 161 156 160 161 164 163 168 159 149 152 160 157 161 159 160 158 160 152 170 182 163 162 164 157 153 150 161 154 155 156 167 167 166 152 144 142 149 164 153 152 F. Calculation of estimated Error and Average Error. Step 21. The estimated error and average error of the values as stored in Table -11 with reference to the values stored in Table -3 have been calculated and the average error has been found as 14.39%. The image based on values as stored in Table-11 has been formed which has been furnished in Fig-8. Step 22. Other test images as furnished in figure-9 have been taken for processing and recognition. IV. RESULTS A number of original and Test images have been taken and processed. The results are furnished as in Table -12. Table -12 Result Srl No Original Image Noisy Original Image Average Error with respect to Original Image Original Image after noise removal Average Error with respect to Original Image after Noise Removal (1) (2) (3) (4) (5) (6) 1 Fig -2 Fig -3 25.67% Fig -4 5.39% 2 Fig -2 Fig -3 26.42% Fig -4 2.93% Test Image Noisy Test Image Average Error due to Noise with respect to Test Image Test Image after noise removal Average Error with respect to Test Image (7) (8) (9) (10) (11) Fig -5 Fig -6 25.75% Fig -7 5.56% Fig -9 Fig -10 27.39% Fig -11 7.8% Average Error w. r.t to Original Image after noise Removal Test Image after training using ANN Average Error w.r.t to Original Image Remarks (12) (13) (14) (15) 31% Fig -8 14.39 Recognition Possible 64% --------- -------- Recognition Not Possible 1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 | Fig -2 Fig -3 Input Original Image Noisy Original Image Fig -4 Fig -5 Original Image after Noise Removal Test Image Fig -6 Fig -7 Noisy Test Image Test Image after Noise Removal Fig -8 Fig -9 Image after training using ANN Test Image Fig -10 Fig -11 Noisy Test Image Test Image after Noise Removal V. CONCLUSIONS It has been observed that if the average error is less than 45%, Artificial Neural network can be applied for training and testing for the purpose of recognition. Therefore the test image is recognized and matched successfully with original image. It has also been observed that, if the average error is greater than 45% then the image is recognized as a different image. In this paper salt and pepper noise has been inserted with an idea that all available images may contain certain noise which has to be removed for proper recognition. In this paper it has also been observed that it takes less time for training and testing using ANN as number of rows of the matrix used for training has one fourth number of columns compare to the original image. REFERENCES [1] M. Egmont-Petersena, D. de Ridderb, H. Handelsc, L. Beaurepaire, K.Chehdi; B.Vozel “Image processing with neural networks—a review", Pattern Recognition 35 (2002), 2002, PP-2280–2288 [2] Berend Jan van der Zwaag , Kees Slump , and Lambert Spaanenburg " Extracting Knowledge from Neural Networks in Image Processing" PP-143-145 [3] Anil K. Jain, Fellow, IEEE, Robert P.W. Duin, and Jianchang Mao, Senior Member, IEEE “Statistical Pattern Recognition: A Review”, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE VOL. 22, NO. 1, JANUARY 2000 [4] Andrzej Dziech, Ali Amuri, “CONTOUR RECOGNITION USING NEURAL NETWORKAPPLICATION”, Communications Dept., AGH Cracow University, Cracow, POLAND, Electronics and Communication Dept., Kielce University of Technology, Kielce, POLAND. [5] Kenji Suzuki, “Pixel-Based Artificial Neural Networks in Computer- Aided Diagnosis”, Department of Radiology, Division of Biological Sciences, the University of Chicago USA [6] N.R. Pal, S.K. Pal, "A review on image segmentation techniques", Pattern Recognition 26 (9) (1993) 1277– 1284. [7] S.K. Pal, A. Ghosh, "Neuro-fuzzy computing for image processing and pattern recognition", Int. J. Systems Sci. 27 (12) (1996) 1182– 1193 [8] Mostafa Jabarouti Moghaddam, Hamid Soltanian-Zadeh, “Medical Image Segmentation Using Artificial Neural Networks “. [9] Adilson Gonzaga, Armando Marin, Evandro A. Silva, Fabiana C. Bertoni Kelton A.P. Costa, Luciana A.L. Albuquerque “Neutral Facial Image Recognition Using Parallel Hopfield Neural Networks”, Universidade de São Paulo [10] Y.J. Zhang, "A survey on evaluation methods for image segmentation", Pattern Recognition 29 (8) (1996) 1335– 1340 [11] Humayun Karim Sulehria, Ye Zhang, “Hopfield Neural Networks— A Survey”, Proceedings of the 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases, Corfu Island, Greece, February 16-19, 2007. [12] Rafael C. Gonzalez, Richard E. Woods, " Digital Image Processing" , Second Edition, Prentice Hall Upper Saddle River, New Jersey 07458, TA1632.G66 2001, 698-740

[Walter Roberson]

Do you have permission to post this copyrighted paper?

[Walter Roberson]

Please reformat for readability.

http://www.mathworks.com/matlabcentral/answers/13205-tutorial-how-to-format-your-question-with-markup

[Greg Heath]

TEST

Answer 1

[Greg Heath]

It is obviously a way to generate, from one ideal image, many reasonable approximations of real world data that have passed thru a noise removal step.

Thank you for formally accepting my answer

Greg

Answer 2

[kiran kumar]

HI, ANS: TO MAKE IT RELAISTIC OR MORE CLOSER TO REAL TIME

EXPLANATION:

IN REAL TIME THE IMAGES NEED TO BE TRANSMITTED FROM ONE SYSTEM TO ANOTHER OR FROM ONE DEVICE TO ANOTHER FOR EXAMPLE IMAGE IS TAKEN USING A SATELLITE BUT IT IS BROADCAST ED TO EARTH, SO WHILE THEE IMAGE IS GETTING TRANSMITTED THERE IS A POSSIBILITY OF SPECKLE NOISE TO BE ADDED , SIMILARLY GAUSSIAN AND SALT AND PEPPER NOISES.SO IN ORDER TO MAKE THE IMAGE LOOK MORE REALISTIC THE IMAGE IS ADDED WITH NOISE AND THEN REMOVED ..NOISE CANNOT BE REMOVED PERFECTLY EVEN THOUGH U USE FILTERS...

[Image Analyst]

I think you mean "a real world situation" rather than real time, which generally means fast enough that humans can't see any pauses/delays. You would not add and remove noise to make it closer to real time.