| dc.creator | Forero, Manuel G. | |
| dc.creator | Beltr?n, Carlos E. | |
| dc.creator | Gonz?lez-Santos, Christian | |
| dc.date | 2021-11-12T20:47:09Z | |
| dc.date | 2021-11-12T20:47:09Z | |
| dc.date | 2021-05-16 | |
| dc.date.accessioned | 2023-08-31T19:23:46Z | |
| dc.date.available | 2023-08-31T19:23:46Z | |
| dc.identifier | Forero M.G., Beltr?n C.E., Gonz?lez-Santos C. (2021) Automatic Classification of Zingiberales from RGB Images. In: Roman-Rangel E., Kuri-Morales ?.F., Mart?nez-Trinidad J.F., Carrasco-Ochoa J.A., Olvera-L?pez J.A. (eds) Pattern Recognition. MCPR 2021. Lecture Notes in Computer Science, vol 12725. Springer, Cham. https://doi.org/10.1007/978-3-030-77004-4_19 | |
| dc.identifier | 0302-9743 | |
| dc.identifier | https://link.springer.com/chapter/10.1007/978-3-030-77004-4_19 | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8557845 | |
| dc.description | Colombia is the country with the largest number of plant species in the world. Within it, Zingiberaceae plays an important ecological role within ecosystems, acting as pioneers in the process of natural regeneration of vegetation and restoration of degraded soils. In addition, they maintain important coevolutionary relationships with other animal and plant species, becoming an important element within the complex web of life in the tropics. Manual classification is time consuming, expensive and requires experts who often have limited availability. To address these problems, three image classification methods SVM, KNN with Euclidean and intersection distances were used in this work. The database used for training, testing and validation of the methods comprises RGB images taken in the natural habitat of the Zingiberales, from their germination to their optimal cutting time. The images were pre-processed, making an adjustment of white balance, contrast and color temperature. To separate the Zingiberales from the background, a graphical segmentation technique using GrabCut was used. The descriptors were obtained using the technique known as BoW, finding that the number of visual words most suitable for classification was between 20 and 40. It was found that a better classification result was obtained by separating the flowers of a species into two subclasses, due to their different coloration. The best results were obtained with the KNN method, using the three closest neighbors, obtaining an accuracy of 97%. | |
| dc.description | Universidad de Ibagu? | |
| dc.language | en | |
| dc.publisher | Universidad de Ibagu? | |
| dc.subject | Zingiberales | |
| dc.subject | Flower classification | |
| dc.subject | Bag of words | |
| dc.subject | Machine learning | |
| dc.subject | K-means | |
| dc.subject | SVM | |
| dc.subject | KNN | |
| dc.title | Automatic Classification of Zingiberales from RGB Images | |
| dc.type | Article | |
