Detecting fraudulent labeling of rice samples using computer vision and fuzzy knowledge
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Pages (from-to) | 24675-24704 |
Journal / Publication | Multimedia Tools and Applications |
Volume | 76 |
Issue number | 23 |
Online published | 22 Feb 2017 |
Publication status | Published - Dec 2017 |
Link(s)
Abstract
Pakistan’s climate allows growing several types of crops, among them is rice. Basmati is one of the most harvested and most profitable varieties of rice because of its unique fragrance. Rice varieties are difficult to differentiate accurately by visual inspection. Therefore, dishonest dealers could easily mislabel or adulterate basmati rice with less valuable assortments that look similar. We need a way to guard the interests of our trade partners. Many different approaches have been proposed to detect adulteration or fraud labeling of rice, in particular, to detect mixtures of authentic basmati and non-basmati varieties. These techniques employ characteristics such as morphological parameters, physicochemical properties, DNA, protein, or metabolites and are expensive and time-consuming. In this paper, we propose a novel and inexpensive technique to detect fraudulent labeling. We use computer vision and a fuzzy classification database for detecting fault labels. For classification, we employ a neural network based approach, and for detecting fraudulent labels, we create a fuzzy classification knowledge database to label rice samples accurately. Our proposed approach is novel and achieves a precision of more than 90% (for 10 gram sample) in identifying fraudulent labels of rice. We conclude that our approach can help in identifying the rice varieties with a higher accuracy.
Research Area(s)
- Classification, Computer vision, Fuzzy knowledge, Neural network, Possibility theory
Citation Format(s)
Detecting fraudulent labeling of rice samples using computer vision and fuzzy knowledge. / Ali, Tenvir; Jhandhir, Zeeshan; Ahmad, Awais; Khan, Murad; Khan, Arif Ali; Choi, Gyu Sang.
In: Multimedia Tools and Applications, Vol. 76, No. 23, 12.2017, p. 24675-24704.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review