International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Since Year 2012 | Open Access | Double Blind Reviewed

ISSN: 2319-7064



Downloads: 168 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Comparative Studies | Electronics & Communication Engineering | India | Volume 7 Issue 6, June 2018


Object Recognition with Improved Features Extracted from Deep Convolution Networks

J. Siva Ramakrishna | Amarendra Reddy Namburi


Abstract: Object recognition is a process for identifying a specific object in an image. Object recognition algorithms depends on matching, learning, or pattern recognition algorithms using appearance- based or feature - based techniques. Object recognition techniques include feature extraction and machine learning models, deep learning models such as CNN. Deep learning with convolution neural networks (CNN) has been proved to be very effective in feature extraction. CNN is comprised of one or more convolutional layers and then followed by one or more fully connected layers. In Image classifications, the work with classifiers aims at exploring the most appropriate classifiers for high level deep features. The features extracted from the image play an important role in image classification. Feature extraction is the process of retrieving the important data from the raw data. Feature extraction is finding the set of parameters that recognize the object precisely and uniquely. In feature extraction, each character is represented by a feature vector, which becomes its identity. The major goal of feature extraction is to extract a set of features, which maximize the recognition rate. In this work, the features extracted from CNN applied as input to train machine learning classifier and perform image classification. A systematic comparison between various classifiers is made for object recognition.


Keywords: object recognition, Deep learning, image classification, support vector machine, extreme learning machine,


Edition: Volume 7 Issue 6, June 2018,


Pages: 941 - 945


How to Download this Article?

Type your Email Address Below, Click Anywhere Outside the Box, That will Activate the Download Button




How to Cite this Article?

J. Siva Ramakrishna, Amarendra Reddy Namburi, "Object Recognition with Improved Features Extracted from Deep Convolution Networks", International Journal of Science and Research (IJSR), Volume 7 Issue 6, June 2018, pp. 941-945, https://www.ijsr.net/get_abstract.php?paper_id=ART20183280



Similar Articles with Keyword 'object recognition'

Downloads: 106

Research Paper, Electronics & Communication Engineering, India, Volume 4 Issue 4, April 2015

Pages: 1730 - 1732

RTL Design and FPGA Implementation of Canny Edge Detector with Real Time Threshold Adjustment Capability

Lakshmamma K M | Chandana B.R

Share this Article

Downloads: 106

Research Paper, Electronics & Communication Engineering, India, Volume 4 Issue 6, June 2015

Pages: 295 - 300

Rotation and Scale Invariant Intrusion Detection for Security Systems

Rupali N. Wadekar | Dr. M. S. Nagmode [3]

Share this Article


Top