ALGORITHM FOR OBJECT RECOGNITION
Navjot Kaur, Someet Singh, Sheetal Kundra, Sant Baba, Bhag Singh · 2013
I. Introduction Object prediction represents an important field of predicting image objects, based on their shape information. Prediction of the partly cover and coupled objects accurately, leads to the reduced execution time and elapsed time. [7]Each image contains up to several hundred objects, which were manually arranged not to overlap or touch each other. The algorithm is divided into levels. In the first level thresh-hold values for the image are defined. Morphological operation is applied on binary image to erode away the boundaries of regions of foreground pixels.[3] And in the second level features of the current object are matched with the preloaded features in data set.[8] The minimum equivalence distance to which the current object matched in data set is considered.