The International Arab Journal of Information Technology (IAJIT)


A Vision Approach for Expiry Date Recognition using Stretched Gabor Features

Product"expiry date represent important information for products consumption. They must contain clear information in the label. The expiry date informati on stamped on the cover of product faced some chall enges due to their writing in pencil and distorted characters. In this paper, an automated vision approach for recognizin g expiry date numerals of industrial product is presented. The system cons ists of four stages namely, numeral string pre"proc essing, numerals string segmentation, features extraction and numeral recog nition. In pre"processing module, we convert the image to binary image based on threshold. A vertical projection process i s adopted to isolate numerals, in the segmentation module. In the features extraction module, Fourier Magnitude (FM), Local En ergy (LE) and Complex Moments (CM) derived from Str etched Gabor (S"Gabor) filters outputs are extracted at various filter orientations. Also, the mean and the varianc e of each feature map are extracted. The recognition process is achieved by c lassifying the extracted features, which represent the numeral image, with trained Multilayer Neural Network (MNN) using k"fol d cross validation procedure. Through experiments, we demonstrate the richness of the S"Gabor features of information is highlighted. Consequently, the set of features shows its usefulness for practical usage. Keyword : Computer vision, FM, CM, LE, numeral recognition, N N, S"Gabor filters. Received March 21, 2013; accepted December 24, 2013 ; published in September 4, 2014 1. Introduction In machine vision inspection application, the syste m must be able to perform successfully label verifica tion [15]. In computer vision inspection system, charact er verification and recognition is an important resear ch field. There are also many control applications whe re the products should be identified via numeral codes such as: Product reference, batch number and expiry , date. In recent years, many researchers related to industrial applications have been developed like: Vehicle license plate recognition [6, 18, 23, 26] a nd product code inspection as quality control of the l abel of medical product [24], control of the numeral on pulp bales [10], visa card numeral code reading [7] and check amount recognition [16] and container,code recognition [25]. The product codes are often print ed somewhere on the product and presents some difficulties to recognize them. Expiry date of the product is important information for consumer. This information appears such numerical or alphanumerica l characters as shown in Figure 1. Figure 1. Examples of expiry date images. In the production line, expiry date faces some difficulties due to the pencil stamping m ethod, packaging phase and many others constrains. Also, depending to the storage duration of the product ex piry date may be appearing distorted and presenting hole s, and the characters can be warped. Too, the characte r image may be skewed; the thickness and the shape of characters are incoherent. Despite the importance o f this information in our daily use, it is not treate d before in literature. This paper presents an automated vis ion approach for product Expiry Date Recognition (EDR). It can be established by a digit series stamped on the cover of the product with different form Figure 1. As all previous works [25], the proposed EDR system is divided into four main modules: Expiry date image preprocessing, expiry date code segmentation, featu res extraction and finally numerals classification. In the first stage, the input image is binarized using morphological operator. Then, the segmentation is performed using vertical projection. Then, a set of features are extracted from Stretched Gabor (S,Gabor) filters output like Fourier Magnitude (FM), Local Energy (LE) and complex moment with statistical features. Finally, Multilayer Neural Network (MNN) is used to classify the expiry date numeral in

[1] Al,Jamimi H. and Mahmoud S., Arabic Character Recognition using Gabor Filters, Innovations and Advances in Computer Sciences and Engineering , Springer Netherlands, pp. 113, 118, 2010.

[2] Anagnostopoulos C., Anagnostopoulos I., Loumos V., and Kayafas E., A License Plate, Recognition Algorithm for Intelligent Transportation System Application, IEEE Transaction on Intelligent Transportation Systems , vol. 7, no. 3, pp. 377,392, 2006.

[3] Bigun J. and du Buf J., Symmetry Interpretation of Complex Moments and the Local Power Spectrum, Vision Communication Image Representation , vol. 6, no. 2, pp. 154,163, 1995.

[4] Bovik C., Clark M., and Geisler S., Multichannel Texture Analysis using Localized Spatial Filters, IEEE Transactions Pattern Analysis Machine Intelligence , vol. 12, no.1, pp. 55,73, 1990.

[5] Chan W. and Coghill G., Text Analysis using Local Energy, Pattern Recognition , vol. 34, no. 12, pp. 2523,2532, 2001.

[6] Chang S., Chen L., Chung Y., and Chen S., Automatic License Plate Recognition, IEEE Transaction on Intelligent Transportation Systems , vol. 5, no. 1, pp. 42,53, 2004.

[7] Chiang J., An Automated Numeral Reading System for VISA Card Application Forms, Computers in Industry , vol. 35, no. 2, pp.175, 183, 1998.

[8] Duan T., Du T., Phuoc T., and Hoang N., Building an Automatic Vehicle License Plate Recognition System, in Proceedings of International Conference on Computer Science , Atlanta, USA, pp. 59,63, 2005.

[9] Gazzah S. and Amara N., Networks and Support Vector Machines Classifiers for Writer Identification using Arabic Script, the International Arab Journal of Information and Technology , vol. 5, no. 1, pp. 92,101, 2008.

[10] Heikkonen J. and Mantynen M., A Computer Vision Approach To Digit Recognition on Pulp Bales, Pattern Recognition Letters , vol. 17, no. 4, pp. 413,419, 1996

[11] Heitger F., Rosenthaler L., Heydt R., Peterhans E., and Kubler O., Simulation of Neural Contour Mechanisms: From Simple to End, Stopped Cells, Vision Research, vol. 32, no. 5, pp. 963,981, 1991.

[12] Jain A. and Farrokhnia F., Unsupervised Texture Segmentation using Gabor Filters, in Proceedings of International Conference on The Proposed Approach The Met hod

[1] The Method

[5] A Vision Approach for Expiry Date Recognition using Stretched Gabor Features 455 Systems , Man and Cybernetics , California, USA, pp. 14,19, 1990.

[13] Jiao J., Ye Q., and Huang Q., A Configurable Method for Multi,Style License Plate Recognition, Pattern Recognition , vol. 42, no. 3, pp. 358,369, 2009.

[14] Kovesi P., Image Features from Phase Congruency, Videre: Journal of Computer Vision Research , vol. 1, no. 3, pp. 1,26, 1999.

[15] Malamas E., Petrakis E., Zervakis M., Petit L. and Legat J., A Survey on Industrial Vision Systems Applications and Tools, Image and Vision Computing , vol. 21, no. 2, pp. 171,188, 2003.

[16] Palacios R. and Gupta A., A System for Processing Handwritten Bank Checks Automatically, Image and Vision Computing , vol. 26, no. 10, pp. 1297,1313, 2008.

[17] Robbins B. and Owens R., 2D Feature Detection via Local Energy, Image and Vision Computing , vol. 15, no. 5, pp. 353,368, 1997.

[18] Sedighi A. and Vafadust M., A New and Robust Method for Character Segmentation and Recognition in License Plate Images, Expert Systems with Applications , vol. 38, no. 11, pp. 13497,13504, 2011.

[19] Shanthi N. and Duraiswamy K., A Novel SVM, Based Handwritten Tamil Character Recognition System, Pattern Analysis and Applications , vol. 13, no. 2, pp. 173,180, 2010.

[20] Simona E., Petkov N., and Kruizinga P., Comparison of Texture Features based on Gabor Filters, IEEE Transactions on Image Processing , vol. 11, no. 10, pp. 1160,1167, 2002.

[21] Sun C. and Si D., Skew and Slant Correction for Document Images using Gradient Direction, in Proceedings of the 4 th International Conference on Document Analysis and Recognition , Ulm, Germany, pp. 142,146, 1997.

[22] Sung J., Bang Y., and Choi S., A Bayesian Network Classifier and Hierarchical Gabor Features for Handwritten Numeral Recognition, Pattern Recognition Letters , vol. 27, no. 1, pp. 66,75, 2005.

[23] Suresh V., Kumar M., and Rajagopalan A., Super Resolution of License Plates in Real Traffic Videos, IEEE Transactions on Intelligent Transportation Systems , vol. 8, no. 2, pp. 321,331, 2006.

[24] Valveny E. and Lopez A., Numeral Recognition for Quality Control of Surgical Sachets, in Proceedings of the 7 th International Conference on Document Analysis and Recognition , Washington, USA, pp. 379,383, 2003.

[25] Wu W., Liu Z., Chen M., Yang X., and He X., An Automated Vision System for Container, Code Recognition, Expert Systems with Applications , vol. 39, no. 3, pp. 2842,2855, 2012

[26] Youssef S. and AbdelRahman S., A Smart Access Control using an Efficient License Plate Location and Recognition Approach, Expert Systems with Applications , vol. 34, no. 1, pp. 256,265, 2008. Ahmed Zaafouri received the BSc degree in electrical engineering from the High school of sciences and techniques of Tunis, the MS degree in automatic from same school respectively in 2004 and 2006. Currently, he is an assistant professor in high institute of applied mathematics and informatics of Kairouan. He has published about 10 research papers in many journal and international conferences. His research interests are focused on computer vision, artificial intelligence, pattern recognition and neural networks. Mounir Sayadi received the BSc degree in electrical engineering from the High school of sciences and techniques of Tunis, the DEA degree in Automatic and Signal Processing from same school and the PhD degree in signal processing from the National School of engineers of Tunis, respectively in 1992, 1994 and 1998. He is currently an Associate Professor at the High school of sciences and techniques of Tunis. He has published over 40 scholarly research papers in many journals and international conferences. He was the Technical Program Co,Chairman of the IEEE International Conference on Industrial Technology, 2004, Tunisia. His research interests are focused on signal and im age processing, classification and segmentation. Farhat Fnaiech received the BSc degree in mechanical engineering in 1978 from Ecole Sup des Sciences et Techniques of Tunis and the master degree in 1980, The PhD degree from the same school in Electrical Engineering in 1983 and the Doctorate Es Science in Physics form the Sciences Faculty of Tunis in 1999. He is currently Professor at the High school of sciences and techniques of Tunis . Pr Fnaiech is Senior Member IEEE and has published over 150 research papers in many Journals and International Conferences. He was the general chairman and member of the International Board Committee of many International Conferences. His is Associate Editor of IEEE Transactions Industrial Electronics. He is serving as IEEE Chapter committe e coordination sub,committee delegate of Africa Regio n 8. His main interest research areas are nonlinear adaptive signal processing, nonlinear control of po wer electronic devises, digital signal processing, imag e processing, intelligent techniques and control.