Common External Defect Detection of Mangoes Using Color Computer Vision
By: Patel, K. K
.
Contributor(s): Kar, A.
Publisher: New York Springer 2019Edition: Vol.100(4), Dec.Description: 559-568p.Subject(s): Construction Engineering and Management (CEM)Online resources: Click here
In:
Journal of the institution of engineers (India): Series ASummary: Development methodology of color computer vision for defects detection of two commercial varieties (Chausa and Dashehari) of Indian mangoes has been proposed in this research. First, images of the fruits of both cultivars were acquired using color (RGB) camera and proper lighting regime and arrangement to avoid highlights and light reflection. Second, an algorithm was developed for pre-processing and processing to segment the external defects of mangoes using LabView software. After image processing and filtering the defected particles, the number of pixels was counted whose gray level was found to be lower than the threshold value during the particle analysis. Performance of algorithm was also evaluated in terms of accuracy, efficiency and the overall time taken by the image during processing and analysis. The overall accuracy and efficiency of proposed algorithm was found to be 88.6% and 93.3%, respectively. The average time of inspection was found to be increased as the severity of defects on mango fruit’s surface increased.
| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology (PG) Archieval Section | Not for loan | 2021044 |
Development methodology of color computer vision for defects detection of two commercial varieties (Chausa and Dashehari) of Indian mangoes has been proposed in this research. First, images of the fruits of both cultivars were acquired using color (RGB) camera and proper lighting regime and arrangement to avoid highlights and light reflection. Second, an algorithm was developed for pre-processing and processing to segment the external defects of mangoes using LabView software. After image processing and filtering the defected particles, the number of pixels was counted whose gray level was found to be lower than the threshold value during the particle analysis. Performance of algorithm was also evaluated in terms of accuracy, efficiency and the overall time taken by the image during processing and analysis. The overall accuracy and efficiency of proposed algorithm was found to be 88.6% and 93.3%, respectively. The average time of inspection was found to be increased as the severity of defects on mango fruit’s surface increased.
Click on an image to view it in the image viewer
There are no comments for this item.