ABSTRACT

Trash content of raw cotton is a critical quality attribute. Therefore, its assessment is crucial for its processing and evaluation of its market value. Current technologies including gravimetric methods and surface scanners suffer from various limitations. Furthermore, worldwide the most commonly used method is still human grading. Thus, the need for implementing new technologies is growing. One of the best alternatives to aforementioned approaches is x-ray imaging since it allows a thorough analysis of contaminants in a very precise and quick manner. We have used x-ray radiographic imaging because of its real-time applicability. The segmentation of trash particles in 2D transmission images is not an easy task. We dealt with this problem by characterizing and identifying the background cotton via scale space filtering followed by a ‘background normalization’ process that removes the background cotton successfully while leaving the trash particles intact. We tested our technique on 280 cotton radiographs - graded from 1 to 7 according to its trash content by expert graders - and compared the results with the existing alternatives.