Object Detection using Convolutional Neural Network and Extended SURF with FIS
Adila Nuzhat1, Fahima Tabassum2, Md. Imdadul Islam3
1Adila Nuzhat, Computer Science & Engineering, Jahangirnagar University, Savar, Dhaka.
2Fahima Tabassum*, Institute of Information Technology, Jahangirnagar University, Savar, Dhaka.
3Md. Imdadul Islam, Computer Science & Engineering, Jahangirnagar University, Savar, Dhaka.
Manuscript received on June 01, 2020. | Revised Manuscript received on June 08, 2020. | Manuscript published on June 30, 2020. | PP: 918-925 | Volume-9 Issue-5, June 2020. | Retrieval Number: E9915069520/2020©BEIESP | DOI: 10.35940/ijeat.E9915.069520
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: The aim of the paper is to detect object using the combination of three algorithms: convolutional neural network (CNN) and extended speeded up robust features (SUFR) and Fuzzy inference system (FIS). Here three types of objects are considered: first, we consider RGB images of hundred different types of objects (for example anchor, laptop airplane, car etc.) taken from benchmark database; second, we take grayscale images of human fingerprint from recognized database; third, Bangla handwritten alphabet from standard database. In this paper we extend the SURF algorithm then the result of the extended SURF is applied in FIS to enhance accuracy of detection. Finally, three algorithms are combined and the accuracy of detection of combined technique is found better than individual one. The combined algorithm provides the average recognition rate for objects of first case as 94.21%, for human finger print as 92.17%%, for Bangla letter as 92.38% and for the Bangla digit as 93.69%.
Keywords: Accuracy of detection, entropy, confusion matrix, Euclidian distance of feature points and surface plot.