Automated Paddy Variety Recognition from Color-Related Plant Agro-Morphological Characteristics

Full Text (PDF, 1157KB), PP.12-22

Views: 0 Downloads: 0


Basavaraj S. Anami 1,* Naveen N. M. 1 Surendra P. 2

1. K. L. E. Institute of Technology, Hubballi, Karnataka, India, 580030

2. University of Agricultural Sciences, Dharwar, Karnataka, India, 580005

* Corresponding author.


Received: 4 Apr. 2018 / Revised: 19 Apr. 2018 / Accepted: 11 May 2018 / Published: 8 Jan. 2019

Index Terms

Paddy plant, variety recognition, DUS agro-morphological characteristics, k-means clustering, PCA


The paper presents an image-based paddy plant variety recognition system to recognize 15 different paddy plant varieties using 18 color-related agro-morphological characteristics. The k-means color clustering method has been used to segment the target regions in the paddy plant images. The RGB, HSI and YCbCr color models have been employed to construct color feature vectors from the segmented images and the feature vectors are reduced using Principal Component Analysis (PCA) technique. The reduced color feature vectors are used as input to back propagation neural network (BPNN) and support vector machine (SVM). The set of six combined agro-morphological characteristics recorded during maturity growth stage has given the highest average paddy plant variety recognition accuracies of 91.20% and 86.33% using the BPNN and SVM classifiers respectively. The work finds application in developing a tool for assisting botanists, Rice scientists, plant breeders, and certification agencies.

Cite This Paper

Basavaraj S. Anami, Naveen N. M., Surendra P., " Automated Paddy Variety Recognition from Color-Related Plant Agro-Morphological Characteristics", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.11, No.1, pp. 12-22, 2019. DOI: 10.5815/ijigsp.2019.01.02


[1]Grillo, O., Blangiforti, S., & Venora, G., (2017). Wheat landraces identification through glumes image analysis. Computers and Electronics in Agriculture, Volume 141, pp. 223-231.

[2]Perez-Sanz, Fernando, Pedro J. Navarro, and Marcos Egea-Cortines, (2017). Plant phenomics : an overview of image acquisition technologies and image data analysis algorithms.  GigaScience, Volume 6, pp. 1-18.

[3]Suchit Purohit and Savita R. Gandhi, (2017). Application of Sparse Coded SIFT Features for Classification of Plant Images. International Journal of Image, Graphics and Signal Processing 9, Volume 10, pp. 50.

[4]Sridhar, T. C., Dushyantha, B. M., Kumar, B. R. and Nishanth, G. K., (2016). Morphological Characterization of Traditional Rice (Oryza sativaL.) Genotypes of Southern Transitional Zone, Karnataka, According to DUS Test Guidelines. Research Journal of Agricultural Sciences, Volume 7(2), pp. 317-323.

[5]Joly, A., Goëau, H., Bonnet, P., Bakić, V., Barbe, J., Selmi, S., Yahiaoui, I., Carré, J., Mouysset, E., Molino, J.F. and Boujemaa, N., (2014). Interactive plant identification based on social image data. Ecological Informatics, Volume 23, pp. 22-34.

[6]Caglayan, A, Guclu O, Can A., (2013), A plant recognition approach using shape and color features in leaf images. In: Petrosino A. (eds) Image analysis and processing- ICIAP 2013, Lecture Notes in Computer Science, Springer, Berlin, Heidelberg Volume 8157, pp. 161–170.

[7]Korir, N. K., Han, J., Shangguan, L., Wang, C., Kayesh, E., Zhang, Y., & Fang, J., (2013). Plant variety and cultivar identification: advances and prospects. Critical reviews in biotechnology 33, Volume 2, pp. 111-125.

[8]Yang W, Duan L, Chen G, Xiong L, Liu Q. (2013). Plant phenomics and high-throughput phenotyping: accelerating rice functional genomics using multidisciplinary technologies. Current Opinion in Plant Biology, Volume 16, pp. 180–187.

[9]Subudhi, H. N., Samantarays, S., Swain, D. and Singh, O.N., (2012). Collection and agro-morphological characterization of aromatic short grain rice in eastern India. African Journal of Agricultural Research 7, Volume 36, pp. 5060-5068.

[10]Kumar, N., Belhumeur, P. N., Biswas, A., Jacobs, D. W., Kress, W. J., Lopez, I. C., & Soares, J. V., (2012). Leafsnap: A computer vision system for automatic plant species identification. In Computer vision–ECCV, Springer, Berlin, Heidelberg, pp. 502-516.

[11]N Shobha Rani, LV Subba Rao and B C Viraktamath, (2006). National Guidelines for the conduct of tests for Distinctness, Uniformity and Stability: Rice (Oryza sativa L) – Zero Draft, Directorate of Rice Research, Rajendranagar, Hyderabad – 500030, Andhra Pradesh, India. pp. 39.

[12]Luccheseyz L, Mitray S., (2001). Color image segmentation: a state-of-the-art survey. In: Proceedings of the Indian National Science Academy. Volume 67, pp. 207–221.

[13]Ito, Hiroshi, and Tomoya Akihama, (1962). An approach for the symbolization of colors in rice plant and its adoption for the classification of rice varieties, Japanese Journal of Breeding 12, Volume 4,  pp. 221-225.

[14]Shearer, S.A. and R.G. Holmes. (1990). Plant identification using color co-occurrence matrices. Transactions of the ASAE 33, Volume 6, pp. 2037-2044.

[15]Garg, Ishu, and Bikrampal Kaur, (2016), Color based segmentation using K-mean clustering and watershed segmentation. In Computing for Sustainable Global Development (INDIACom), 3rd International Conference, IEEE, pp. 3165-3169.