Object Recognition with Improved Features Extracted from Deep Convolution Networks
K Manohar, S Irfan, K Sravani · International Journal of Engineering & Technology · 2018
Object identification is a method for identify an exact object in an image. Object identification algorithm depends on matching, learning, and pattern recognition using appearance based feature technique. Object recognition has various method to detect objects it’s include feature extraction and machine learning methods, deep learning search as CNN. The deep learning convolution neural network (CNN) has been proved to be very efficient in feature extraction. CNN is compressed of one or more convolution layers and then follow by one or more totally connected layers. In Image types, the work with classifiers aims at explore the most appropriate types for high level deep features. The feature extracted from the image plays a significant role in image type. It is the process of retrieving the main data from the raw data, its finding the set of parameters that recognize the object uniquely. In feature extraction every nature is represent by a feature vector it’s become identity. In this work the features extracted from CNN applied as input to train machine learning classifiers and perform image classification. A systematic comparison between various classifiers is made for object recognition.