Advances in Computer Science and Information Technology. Computer Science and Engineering. Second International Conference, CCSIT 2012, Bangalore, India, January 2-4, 2012. Proceedings, Part II

Research Article

Performance Evaluation of Segmentation of Frog-Eye Spot Lesions on Tobacco Seedling Leaves

Download
160 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-27308-7_48,
        author={P. Mallikarjuna and D. Guru},
        title={Performance Evaluation of Segmentation of Frog-Eye Spot Lesions on Tobacco Seedling Leaves},
        proceedings={Advances in Computer Science and Information Technology. Computer Science and Engineering. Second International Conference, CCSIT 2012, Bangalore, India, January 2-4, 2012. Proceedings, Part II},
        proceedings_a={CCSIT PATR II},
        year={2012},
        month={11},
        keywords={Image enhancement CIELAB color model Lesion area segmentation Performance measures},
        doi={10.1007/978-3-642-27308-7_48}
    }
    
  • P. Mallikarjuna
    D. Guru
    Year: 2012
    Performance Evaluation of Segmentation of Frog-Eye Spot Lesions on Tobacco Seedling Leaves
    CCSIT PATR II
    Springer
    DOI: 10.1007/978-3-642-27308-7_48
P. Mallikarjuna1,*, D. Guru1,*
  • 1: University of Mysore
*Contact email: pbmalli@yahoo.com, dsg@compsci.uni-mysore.ac.in

Abstract

In this paper, a new algorithm for segmentation of frog-eye spot lesions on tobacco seedling leaves is proposed. Segmentation algorithm consists of mainly two steps. First step is to approximate lesion extraction using contrast stretching transformation and morphological operations such as erosion and dilation. Second step refines the outcome of first step by color segmentation using CIELAB color model. We have also conducted a performance evaluation of segmentation algorithm by measuring the parameters such as Measure of overlapping (MOL), Measure of under-segmentation (MUS), Measure of over-segmentation (MOS), Dice similarity measure (DSM), Error-rate (ER), Precision (P) and Recall (R). In order to corroborate the efficacy of the proposed segmentation algorithm, an experimentation is conducted on our own dataset of 400 segmented areas of tobacco seedling leaves which are captured in uncontrolled lighting conditions. Experimental results show that our proposed segmentation algorithm achieved best average DSM and MOL accuracy as compared to our previous segmentation algorithm.