Dataset Information

Nondestructive classification of saffron using color and textural analysis.

ABSTRACT: Saffron classification based on machine vision techniques as well as the expert's opinion is an objective and nondestructive method that can increase the accuracy of this process in real applications. The experts in Iran classify saffron into three classes Pushal, Negin, and Sargol based on apparent characteristics. Four hundred and forty color images from saffron for the three different classes were acquired, using a mobile phone camera. Twenty-one color features and 99 textural features were extracted using image analysis. Twenty-two classifiers were employed for classification using mentioned features. The support vector machine and Ensemble classifiers were better than other classifiers. Our results showed that the mean classification accuracy was up to 83.9% using the Quadratic support vector machine and Subspace Discriminant classifier.

SUBMITTER: Mohamadzadeh Moghadam M

PROVIDER: S-EPMC7174224 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Nondestructive classification of saffron using color and textural analysis.

Mohamadzadeh Moghadam Morteza M Taghizadeh Masoud M Sadrnia Hassan H Pourreza Hamid Reza HR

Food science & nutrition 20200227 4

Saffron classification based on machine vision techniques as well as the expert's opinion is an objective and nondestructive method that can increase the accuracy of this process in real applications. The experts in Iran classify saffron into three classes Pushal, Negin, and Sargol based on apparent characteristics. Four hundred and forty color images from saffron for the three different classes were acquired, using a mobile phone camera. Twenty-one color features and 99 textural features were e ...[more]

PMID: 32328258

Similar Datasets

Project description:BackgroundMicro computed tomography (micro CT) has been shown to provide exceptionally high quality imaging of the fine structural detail within urinary calculi. We tested the idea that micro CT might also be used to identify the mineral composition of urinary stones non-destructively.MethodsMicro CT x-ray attenuation values were measured for mineral that was positively identified by infrared microspectroscopy (FT-IR). To do this, human urinary stones were sectioned with a diamond wire saw. The cut surface was explored by FT-IR and regions of pure mineral were evaluated by micro CT to correlate x-ray attenuation values with mineral content. Additionally, intact stones were imaged with micro CT to visualize internal morphology and map the distribution of specific mineral components in 3-D.ResultsMicro CT images taken just beneath the cut surface of urinary stones showed excellent resolution of structural detail that could be correlated with structure visible in the optical image mode of FT-IR. Regions of pure mineral were not difficult to find by FT-IR for most stones and such regions could be localized on micro CT images of the cut surface. This was not true, however, for two brushite stones tested; in these, brushite was closely intermixed with calcium oxalate. Micro CT x-ray attenuation values were collected for six minerals that could be found in regions that appeared to be pure, including uric acid (3515 - 4995 micro CT attenuation units, AU), struvite (7242 - 7969 AU), cystine (8619 - 9921 AU), calcium oxalate dihydrate (13815 - 15797 AU), calcium oxalate monohydrate (16297 - 18449 AU), and hydroxyapatite (21144 - 23121 AU). These AU values did not overlap. Analysis of intact stones showed excellent resolution of structural detail and could discriminate multiple mineral types within heterogeneous stones.ConclusionsMicro CT gives excellent structural detail of urinary stones, and these results demonstrate the feasibility of identifying and localizing most of the common mineral types found in urinary calculi using laboratory CT.

Dataset Information

Nondestructive classification of saffron using color and textural analysis.

Publications

Nondestructive classification of saffron using color and textural analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets