Image analysis and data mining techniques for classification of morphological and color features for seeds of the wild castor oil plant (Ricinus communis L.).
Saved in:
| Title: | Image analysis and data mining techniques for classification of morphological and color features for seeds of the wild castor oil plant (Ricinus communis L.). |
|---|---|
| Authors: | Isaza, Cesar1 cesar.isaza@upq.edu.mx, Anaya, Karina1 karina.anaya@upq.mx, de Paz, Jonny Zavala1 jonny.zavala@upq.edu.mx, Vasco-Leal, Jose F.2 jose.vasco.leal@gmail.com, Hernandez-Rios, Ismael3 ismaelhr@colpos.mx, Mosquera-Artamonov, Jose D.4 xoce15@ingenieros.com |
| Source: | Multimedia Tools & Applications. Jan2018, Vol. 77 Issue 2, p2593-2610. 18p. |
| Subjects: | Seeds, Image analysis, Data mining, Castor oil plant, Seed morphology, Seed colors |
| Abstract: | In this study, a castor seed (Ricinus communis L.) classification process was developed using a precise image analysis technique, and several data mining algorithms. Castor seed oil has an excellent demand in the pharmaceutical sector, and it has recently aroused the interest of the biodiesel production companies. However, there are few studies describing the physical characteristics of Ricinus communis; thus, any advance in this field contributes to the design of technology that may increase the production of this oil, up to industrial levels. In fact, this work aims to contribute not only to understand the physical features of castor seed varieties, but also to unveil key information to develop better castor seed oil extraction machines. Additionally, a novel methodology to study accessions of castor seed gathered from several geographical locations is proposed. Particularly, an automatically accurate image analysis technique was implemented in order to extract color and morphological features from seeds. The data set of seeds was built considering fifty samples per accession. After that, several classification experiments were done using well known data mining algorithms in order to cluster all samples. Experimental results showed that it is possible to cluster studied seeds into ten similar classes with high accuracy (larger than 95 %). Moreover, image analysis and data mining techniques were efficient tools for the classification of seeds, and the color and morphological data gathered are really useful for the design of oil extraction equipment. In fact, the effectiveness in the correct classification instances was 100 %, with a computation time of 0.01 seconds. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | In this study, a castor seed (Ricinus communis L.) classification process was developed using a precise image analysis technique, and several data mining algorithms. Castor seed oil has an excellent demand in the pharmaceutical sector, and it has recently aroused the interest of the biodiesel production companies. However, there are few studies describing the physical characteristics of Ricinus communis; thus, any advance in this field contributes to the design of technology that may increase the production of this oil, up to industrial levels. In fact, this work aims to contribute not only to understand the physical features of castor seed varieties, but also to unveil key information to develop better castor seed oil extraction machines. Additionally, a novel methodology to study accessions of castor seed gathered from several geographical locations is proposed. Particularly, an automatically accurate image analysis technique was implemented in order to extract color and morphological features from seeds. The data set of seeds was built considering fifty samples per accession. After that, several classification experiments were done using well known data mining algorithms in order to cluster all samples. Experimental results showed that it is possible to cluster studied seeds into ten similar classes with high accuracy (larger than 95 %). Moreover, image analysis and data mining techniques were efficient tools for the classification of seeds, and the color and morphological data gathered are really useful for the design of oil extraction equipment. In fact, the effectiveness in the correct classification instances was 100 %, with a computation time of 0.01 seconds. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-017-4438-y |
