Object Classification and Detection using Deep Convolution Neural Network Architecture
Thumu Kiran1, Gurrala Nohar Reddy2, N. Srinivasan3

1Dr. N. Srinivasan, Assistant Professor, Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India.
2Mr. Gurrala Nohar Reddy, Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India.
3Mr. Thumu Kiran Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India.

Manuscript received on May 02, 2020. | Revised Manuscript received on May 21, 2020. | Manuscript published on May 30, 2020. | PP: 2768-2772 | Volume-9 Issue-1, May 2020. | Retrieval Number: F9834038620/2020©BEIESP | DOI: 10.35940/ijrte.F9834.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Abstract:-X-Ray security stuff screening frameworks are generally introduced in pretty much every station/air terminal to guarantee open vehicle security. In any case, the unwavering quality of manual recognition has been bothersome in genuine circumstances. For a stuff screener, recognizing the precluded things is typically so arduous and exhausting that missing some undermining things is unavoidable by and by. Particularly, in times of heavy traffic, travelers ordinarily take a great deal of time hanging tight for security checking in line. A solid programmed disallowed thing location framework is subsequently ideal for accelerating the screening procedure just as improving the precision of risk identification. X-Ray age is identified with the arrival vitality of the electrons when they arrive at the material, which is an element of the voltage of the material and the vitality of the electron bar. By estimating the X-Ray discharge and knowing the vitality of the electron pillar, the voltage of the material can be resolved. An information growth strategy for enhancing the X-Ray denied thing pictures utilizing GAN based methodology. In the first place, the forefronts containing precluded things are removed by a Region of Interest (ROI) division calculation from the gathered X-Ray security pictures. At long last, to confirm whether the created pictures have a place with its comparing class or not founded on the basic CNN model.
Keywords: Data Augmentation, Image Generation, Generative Adversarial Networks, Prohibited Item, X-ray image.
Scope of the Article: Deep Learning