Home > Published Issues > 2019 > Volume 7, No. 2, June 2019 >

Algorithm for the Recognition of a Silhouette of a Person from an Image

Washington García1,2, Cristian Mera2, Leonel Santana2, and Luzmila Pro1
1. Universidad Nacional Mayor de San Marcos, Lima, Perú
2. Universidad Laica Eloy Alfaro de Manabí, Manta, Ecuador

Abstract—The tasks of recognizing people from images or videos are still considered complex for a computer because the pattern of a person has many variants and can be confusing with the pattern of an object or an animal. The objective of this research was to construct an algorithm that allows identifying the silhouette of a person from an image captured by a camera. The methodology used was a review of the literature and a framework that proposed three basic components: The unidentified pattern, the identification process, and the recognized pattern. Once the algorithm model was put to a test as a function of the Mat lab (Support Vector Machines (SVM)), the identification of patterns with people was achieved in four ways, when a person is upright.

Index Terms—recognition of patterns, recognition of images, recognition algorithms

Cite: Washington García, Cristian Mera, Leonel Santana, and Luzmila Pro, "Algorithm for the Recognition of a Silhouette of a Person from an Image," Journal of Image and Graphics, Vol. 7, No. 2, pp. 59-63, June 2019. doi: 10.18178/joig.7.2.59-63