Abstract In conventional cropping systems, removal of weed p opulation extensively relies on the application of chemical herbicides. However, this practice should be minimi zed because of the adverse effects of herbicide app lications on environment, human health, and other living organis ms. In this context, if the distribution of broadleaf and grass weeds could be sensed locally with a machine vision system, the n the selection and dosage of herbicides applications could be optimized automatically. This paper presents a simple, yet ef fective texture&based weed classification method using local pattern operators. The objective is to evaluate the feasibi lity of using micro&level texture patterns to classify weed images into broadleaf and grass categories for real&time select ive herbicide applications. Three widely&used texture operators, namely Local Binary Pattern (LBP), Local Ternary Pattern ( LTP), and Local Directional Pattern (LDP) are consi dered in our study. Experiments on 400 sample field images with 200 sam ples from each category show that, the proposed method is capable of effectively classifying weed images and provides su perior performance than several existing methods.

References

[1] Ahmad I., Siddiqi M., Fatima I., Lee S., and Lee Y., Weed Classification Based on Haar Wavelet Transform via k5Nearest Neighbor (k5NN) for Real5Time Automatic Sprayer Control System, in Proceedings of the 5 th International Conference on Ubiquitous Information Management and Communication , USA, pp. 156, 2011.

[2] Ahmed F., Bari H., Hossain E., Al5Mamun H., and Kwan P., Performance Analysis of Support Vector Machine and Bayesian Classifier for Crop and Weed Classification from Digital Images, World Applied Sciences Journal , vol. 12, no. 4, pp. 4325440, 2011.

[3] Ahmed F., Bari H., Shihavuddin A., Al5Mamun H., and Kwan P., A Study on Local Binary Pattern for Automated Weed Classification using Template Matching and Support Vector Machine , in Proceedings of the 12 th IEEE International Symposium on Computational Intelligence and Informatics , Budapest, pp. 3295 334, 2011.

[4] Bossu J., Gee C., Jones G., and Truchetet F., Wavelet Transform to Discriminate between Crop and Weed Perspective Argonomic Images, Computers and Electronics in Agriculture , vol. 65, no. 1, pp. 1335143, 2009.

[5] Ghazali K., Mustafa M., and Hussain A., Machine Vision System for Automatic Weeding Strategy using Image Processing Technique, American&Eurasian Journal of Agricultural & Environmental Science , vol. 3, no. 3, pp. 4515 458, 2008.

[6] Guyer D., Miles G., Gaulttney L., and Schreiber M., Application of Machine Vision to Shape Analysis in Leaf and Plant Identification, Transactions of the American Society of Agricultural and Biological Engineers , vol. 36, no. 1, pp. 1635171, 1993.

[7] Guyer D., Miles G., Shreiber M., Mitchell O., and Vanderbilt V., Machine Vision and Image Processing for Plant Identification, Transactions of the American Society of Agricultural Engineers , vol. 29, no. 6, pp. 150051507, 1986.

[8] Heusch G., Rodriguez Y., and Marcel S., Local Binary Patterns as an Image Preprocessing for Face Authentication, in Proceedings of the International Conference on Automatic Face and Gesture Recognition , Southampton, pp. 9514, 2006.

[9] Hsu C. and Lin C., A Comparison on Methods for Multiclass Support Vector Machines, IEEE Transaction on Neural Networks , vol. 13, no. 2, pp. 4155425, 2002.

[10] Jabid T., Kabir H., and Chae O., Robust Facial Expression Recognition Based on Local Directional Pattern, Journal of the Electronics and Telecommunications Research Institute , vol. 32, no. 5, pp. 7845794, 2010.

[11] Johnson G., Mortensen D., and Martin A., A Simulation of Herbicide Use Based on Weed Spatial Distribution, Weed Research, vol. 35, no. 1, pp. 1975205, 1995.

[12] Kabir H., Jabid T., and Chae O., Local Directional Pattern Variance (LDPV): A Robust Feature Descriptor for Facial Expression Recognition, International Arab Journal of Information Technology , vol. 9, no. 4, pp. 3825 391, 2012.

[13] Meyer G., Mehta T., Kocher M., Mortensen D., and Samal A., Textural Imaging and Discriminant Analysis for Distinguishing Weeds for Spot Spraying, Transactions of the American Society of Agricultural Engineers , vol. 41, no. 4, pp. 118951197, 1998.

[14] Mortensen D., Dieleman J., and Johnson G., Weed Spatial Variation and Weed Management, in Proceedings of Integrated Weed and Soil Management , pp. 2935309, 1998.

[15] Naeem A., Ahmad I., and Islam M., Weed Classification using two Dimensional Weed Coverage Rate (2D5WCR) for Real5Time Selective Herbicide Applications, in Proceedings of the International Conference on Computer, Information and Systems Science and Engineering , vol. 19, pp. 3355339, 2007.

[16] Naeem A., Ahmad I., Islam M., and Nawaz S., Weed Classification using Angular Cross Sectional Intensities for Real5Time Selective Herbicide Applications, in Proceedings of the International Conference on Computing Theory and Applications , Kolkata, pp. 7315736, 2007.

[17] Novartis, Sample Labels and Reference Guide , Greensboro, 1998.

[18] Ojala T., Pietikainen M., and Maenpaa T., Multiresolution Gray5Scale and Rotation Invariant Texture Classification with Local Binary Patterns, IEEE Transaction on Pattern Analysis and Machine Intelligence , vol. 24, no. 7, pp. 9715987, 2002.

[19] Rew L. and Cussans G., Patch Ecology and Dynamics5How Much Do We Know?, in Proceedings of the Brighton Crop Protection Conference , pp. 105951068, 1995.

[20] Shearer S. and Jones P., Selective Application of Post5Emergence Herbicides using Photoelectrics, Transactions of the American 94 The International Arab Journal of Information Techn ology Society of Agricultural Engineers pp. 166151666, 1991.

[21] Siddiqi M., Sulaiman S. , Faye I., and Ahmad I., A Real Time Specific Weed Discrimin System using Multi5Level Wavelet Decomposition, International Journal of Agriculture and Biology , vol. 11 565, 2009.

[22] S gaard H. , Weed Classification by Active Shape Models, Biosystems Engineering no. 3, pp. 2715281, 2005.

[23] S gaard H. and Olsen H. , Determination of Crop Rows by Image Analysis without Segmentation, Computers and Electronics in Agriculture , vol. 38, no. 2, pp. 141

[24] Tan X. and Triggs B., Enhanced Local Texture Feature Sets for Face Recognition under Difficult Lighting Conditions, in Proceedings of International Workshop on Analysis and Modeling of Faces and Gestures, 182, 2007.

[25] Ta ng L., Tian L., and Steward B. of Broadleaf and Grass Weeds Wavelets and an Artificial Neural Network, Transactions of the American Society of Agricultural Engineers , vol. 46, no. 1254, 2003.

[26] Tang L., Tian L., Steward B., and Reid J. Texture5based Weed Classification Wavelets and Neural Network for Real Selective Herbicide Applications, Proceedings of ASAE/CSAE SCGR Annual International Meeting, Canada, pp.

[27] Tian L., Reid J., and Hummel J. of a Precision Sprayer for Site Management, Transactions of the Society of Agricultural Engineers pp. 8935900, 1999.

[28] Weis M. and Gerhards R., Feature Extraction for the Identification of Weed Species in Digital Images for the Purpose of Site Control, in Proceedings of the Conference on Precision Agriculture 5375544, 2007.

[29] Woebbecke D., Meyer G. , Bargen Mortensen A., Shape Features for Identifying Young Weeds using Image Analysis, Transactions of the American Society of Agricultural and Biological Engineers no. 1, pp. 2715281, 1995.

[30] Woebbecke D., Meyer G. , Bargen Mortensen D., Color Indices for Weed Identi cation under Various Soil, Residue, and Lighting Conditions, Transactions of the American Society of Agricultural Engineers 38, no. 1, pp. 2595269, 1995.

[31] Zhang N. and Chaisattapagon Criteria for Weed Identification in Wheat Fields The International Arab Journal of Information Techn ology Engineers, vol. 34, no. 4, , Faye I., and Ahmad I., A Real Time Specific Weed Discrimination Level Wavelet International Journal of 11, no. 5, pp. 5595 , Weed Classification by Active Biosystems Engineering, vol. 91, , Determination of Crop Rows by Image Analysis without Computers and Electronics in 1415158, 2003. Tan X. and Triggs B., Enhanced Local Texture n under Difficult in Proceedings of IEEE International Workshop on Analysis and , Berlin, pp. 1685 ng L., Tian L., and Steward B., Classification of Broadleaf and Grass Weeds using Gabor Wavelets and an Artificial Neural Network, American Society of no. 4, pp. 12475 Steward B., and Reid J., based Weed Classification using Gabor ural Network for Real5time Selective Herbicide Applications, in Proceedings of ASAE/CSAE SCGR Annual , Canada, pp. 1514, 1999. J., Development of a Precision Sprayer for Site5Specific Weed Transactions of the American Engineers, vol. 42, no. 4, Weis M. and Gerhards R., Feature Extraction for the Identification of Weed Species in Digital Images for the Purpose of Site5specific Weed eedings of the 6th European Conference on Precision Agriculture, Greece, pp. , Bargen K., and , Shape Features for Identifying Image Analysis, American Society of Agricultural and Biological Engineers, vol. 38, , Bargen K., and , Color Indices for Weed cation under Various Soil, Residue, and Transactions of the Society of Agricultural Engineers, vol. C., Effective Criteria for Weed Identification in Wheat Fields using Machine Vision, American Society of Agricultural 38, no. 3, pp. 9655974, Faisal Ahmed degree in information technology Islamic University of Technology, Bangladesh in working as a lecturer in the Department of and Engineering, Islamic University of Technology, Bangladesh. His research interests include texture analysis, computer vision, and pattern recognition. Hasanul Kabir degree in the Kyung Hee University, South Korea. He is now working as an assistant professor in the Department of Computer Science and Engineering Technology, Bangladesh. His research interests incl ude feature extraction, motion estimation, computer vision, and pattern recognition. Shayla Bhuyan degree in engineering University research interests include control system, robotics, image processing, and artificial intelligence. Hossain Bari in computer science and information technology University of Technology, Bangladesh in working in the Samsung Bangladesh R & D Center Ltd, Bangladesh. His research interests include image processing a computer vision. Emam Hossain degree in information technology Islamic University of Technology, Bangladesh in working as a lecturer in the Department of CSE, Ahsanullah University of Science and Technology, Bangladesh. His research interests include image processing, computer vision, artificial intelligence, and patte rn recognition. The International Arab Journal of Information Technology, Vol. 11, No. 1, January 2014 Machine Vision, Transactions of the American Society of Agricultural Engineers, vol. , 1995. Faisal Ahmed received his BS degree in computer science and information technology from the Islamic University of Technology, Bangladesh in 2010. He is now working as a lecturer in the Department of Computer Science Islamic University of Technology, Bangladesh. His research interests include texture analysis, computer vision, and pattern recognition. Hasanul Kabir received his PhD in computer engineering from the Kyung Hee University, South He is now working as an assistant professor in the Department Computer Science and Engineering, Islamic University of Technology, Bangladesh. His research interests incl ude motion estimation, computer vision, Shayla Bhuyan received her BS degree in electrical and electronic engineering from the BRAC University, Bangladesh in 2011. Her research interests include control system, robotics, image processing, and artificial intelligence. Bari received his BS degree computer science and information technology from the Islamic University of Technology, Bangladesh in 2010. He is now working in the Samsung Bangladesh R & D Center Ltd, Bangladesh. His research interests include image processing and Emam Hossain received his BS degree in computer science and information technology from the Islamic University of Technology, Bangladesh in 2010. He is now working as a lecturer in the Department of CSE, Ahsanullah e and Technology, Bangladesh. His research interests include image processing, computer vision, artificial intelligence, and patte rn