<p>To segregate the fruits which are defected manually is a very costly and time consuming process because the human decision may be very slow and irregular checks can happen in detection of fruits. In this paper, the areas affected by bacterial disease are separated using segmentation techniques and graded based on affected area. The manual approach for detection and classification of fruit is very difficult. We have considered sample images of mango fruit for our work. The images of the mango fruit are taken by recording the video of complete mango. The video of mango fruit is converted to 100 frames of each image and identify the affected part of the disease. In the first phase, the histogram stretching method is used for pre-processing and color feature is extracted from the mango fruit using pre-processed techniques, which makes use of the RGB color model. In the second phase watershed algorithm for automatic detection of video frames is used to segment the bacterial affected areas from normal area of the fruit. In the third phase template matching algorithm is used for feature extraction and classification for recognizing and matching the defected part of an image. Then these affected regions are graded by calculating the percentage of affected area. The experimental results shows that the effectiveness of the proposed method in recognizing the number of regions that are defected in the fruit image. © Research India Publications.</p>
cited By 0
N. Pujitha, Swathi, C., and Kanchana, V., “Detection of external defects on mango”, International Journal of Applied Engineering Research, vol. 11, pp. 4763-4769, 2016.