Segmentation and Classification of Raw Arecanuts Based on Three Sigma Control Limits

Arecanut (Areca catechu L.) is one of the important commercial crops in India. There are several computer based technologies for other crops but there is no computer vision based advanced technology in identifying a grade, variety and diseases for an arecanut. In this paper, a novel method is proposed for classification of arecanut into two classes based on color. The proposed method has three steps: (i) Segmentation; (ii) Masking; and (iii) classification. The RGB image is converted into YCBCR color space. Three sigma control limits are used on the YCBCR image for the effective segmentation of arecanuts. Arecanut color space is modelled using three sigma control limits, in which it covers the most significant variation of the color components of the arecanut. The upper and lower limits of the color components are used to segment the arecanut effectively. Classification is done based on the red and green color components of the segmented region of the arecanuts. An experimental result shows the efficiency of the proposed approach.