In this paper, we recognize objects within images by collecting information from a large number of random-size patches of the image. The different backgrounds accompany the foreground object demand to have a learning system to identify each patch as belonging to the object category or to the background category. We strengthen a recent method called Evolution-COnstructed (ECO), which is based on the ensemble learning approach which combines several weak classifier. The improvement is relying on decreasing the overfitting problem. Two different improving ideas are proposed: 1) Pooling operation, which is applied to the weak classifiers data, 2) Random Forest algorithm, which combines the weak classifiers outcomes. Experimental results are reported for classification of 9 categories of Caltech-101 data sets and proved that our modifications boost the performance over the base method and other existing methods
H. Zayyan, M., Elmougy, S., & F. Alrahmawy, M. (2018). Representation Learning Framework of Object Recognition via Feature Construction. Mansoura Journal for Computer and Information Sciences, 14(1), 37-42. doi: 10.21608/mjcis.2018.311995
MLA
Muhammad H. Zayyan; Samir Elmougy; Mohammed F. Alrahmawy. "Representation Learning Framework of Object Recognition via Feature Construction". Mansoura Journal for Computer and Information Sciences, 14, 1, 2018, 37-42. doi: 10.21608/mjcis.2018.311995
HARVARD
H. Zayyan, M., Elmougy, S., F. Alrahmawy, M. (2018). 'Representation Learning Framework of Object Recognition via Feature Construction', Mansoura Journal for Computer and Information Sciences, 14(1), pp. 37-42. doi: 10.21608/mjcis.2018.311995
VANCOUVER
H. Zayyan, M., Elmougy, S., F. Alrahmawy, M. Representation Learning Framework of Object Recognition via Feature Construction. Mansoura Journal for Computer and Information Sciences, 2018; 14(1): 37-42. doi: 10.21608/mjcis.2018.311995