An Effective Machine Learning Model

1164 Words Dec 16th, 2015 5 Pages
Object recognition is one of the most frontier and potentially revolutionary technologies in computer science and a central research topic in computer vision. Currently there are increasing number of researches targeting to give the meaning of our vision to computers. As we move deeper in understanding the image completely, having more exact and detailed object recognition becomes crucial. In this context, one cares not only about classifying images, but also about precisely estimating the class and location of objects contained within the images.
With the improvements in object representations and machine learning models, it is possible to achieve much advancement in Object Recognition. For the last few years, Deep Neural Network has proven to be an effective machine learning model. DNNs have a varied approach to classification problems. They consist of deep architectures which makes it possible to understand more complex models than shallow ones. With this ability and robust learning algorithms, it is possible to learn varied object representations without the need to hand design features.
The focus of our project is not only to classify objects, but also to localize the objects precisely in an image using the powerful machine learning algorithms of DNN [1]. The problem we address here is challenging as our aim is to detect a potentially large number object instances with varying sizes in a single image using a limited amount of computing resources.
In this project, we…
Open Document