Sign In

Communications of the ACM

ACM TechNews

Computer Geeks Develop Algorithm to Detect Defects in Fruits and Grade Them Automatically

Manual grading of fruits is subjective, time-consuming, and inefficient.

Indian computer scientists have developed an algorithm to automatically detect defects in fruits and grade them using the latest image processing techniques.

Credit: Outlook India

Researchers at Annamalai University in India have developed a new image-processing technique that automatically checks the quality of fruits based on their color and texture.

The researchers took a set of healthy oranges and another of oranges with skin defects and developed a database of images, each of which were tagged with a series of attributes. The team then used an image-processing tool called a "grey level co-occurrence matrix" to develop the new fruit-checking algorithm.

The researchers say the image-analysis technique was used to classify oranges into two commercial grading stages, and successfully extracted useful and meaningful features to uniquely represent the external surface for classification purposes.

They note the technique also could be useful for detecting skin damage on other fruits.

From Outlook India
View Full Article


Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


No entries found