1. How to submit my research paper? What’s the process of publication of my paper?
The journal receives submitted manuscripts via email only. Please submit your research paper in .doc or .pdf format to...
2. Can I submit an abstract?
The journal publishes full research papers. So only full paper submission should be considered...[Read More]

An Efficient Contour Based Fine-Grained Algorithm for Multi Category Object Detection

Rafflesia Khan, Tarannum Fariha Raisa, and Rameswar Debnath
Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh

Abstract—Object detection from a real-time image is gaining increasing research interest in recent years as it can substantially facilitate a wide range of content-based multimedia applications. Detecting objects from real time image with fine grained details requires extensive amount of preprocessing, computation and time. In addition, multi category object detection is a very complex and diverse problem domain. Some traditional object detection and recognition models previously train their model with huge number of rich and highly annotated images and then divide an input image into set of bounding boxes and calculate the confidence score for each object category in the image. Most of the existing approaches require huge amount of time and computation for object detection. On the other hand, some models only work with local images where image has a single, focused and center-based object. In order to overcome such limitations of existing models, we are proposing a Region of Interest (ROI) based object detection model. In our proposed work, instead of using a fixed number of bounding boxes (e.g. n×n) or working with local images, our model identifies all the ROI at any location of the image. We have tested our algorithm on a number of benchmark datasets for fine-grained object detection. In our work, we have demonstrated significant efficiency as well as accuracy in term of object detection. We have significantly improved the algorithm to detect object irrespective of location, number of object in the image, object overlapping and minuscule objects. Our proposed model can reduce the noise in an image, and thereby, can identify ROI even from poor quality image, noisy background, irrelevant context and misleading feature. To demonstrate the accuracy of our proposed algorithm we have introduced a feature matching approach to identify the detected objects correctly.

Index Terms—artificial intelligence, object detection, region of interest, blur image, laplacian variance, OpenCV

Cite: Rafflesia Khan, Tarannum Fariha Raisa, and Rameswar Debnath, "An Efficient Contour Based Fine-Grained Algorithm for Multi Category Object Detection," Journal of Image and Graphics, Vol. 6, No. 2, pp. 127-136, December 2018. doi: 10.18178/joig.6.2.127-136

Copyright © 2012-2018 Journal of Image and Graphics, All Rights Reserved
E-mail: joig@ejournal.net