Assessment of trash content of cotton using 2D x-ray imagery

Date

2004-08

Journal Title

Journal ISSN

Volume Title

Publisher

Texas Tech University

Abstract

Trash content of raw cotton is a critical quality attribute. Therefore, its assessment is crucial for evaluating its processing and market value. Current technologies, including gravimetric and surface scanning methods, suffer from various limitations. Furthermore, worldwide, the most commonly used method still is 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. In other work, we have successfully used x-ray tomographic imaging in the detection and classification of cotton contaminants. In this work, we choose to use x-ray radiographic imaging because of its real-time applicability.

The segmentation of trash particles in 2D transmission images is difficult since the background cotton is not uniform. In addition, there is considerable overlap between the gray levels of subtle trash types and dense cotton. 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.

Furthermore, we have successfully employed stereo x-ray vision for recovering the depth information of the piled trash in controlled samples. While adding to the accuracy with which the trash is counted, this method is much faster than the tomographic approach, as it requires only two projections.

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 systems of cotton trash evaluation. Results obtained with the proposed method were highly correlated with those obtained using the current systems. Given that the approach described here provides the trash mass in real-time, when realized, it will have a wide-spread usage in the cotton industry.

Description

Citation