• Vimal Sudhaker Bodke
• Omkar S. Vaidya

The completely unique methodologies for object detection in cluttered real pictures are proposed in this paper, where a single real time scenario is taken as model. The image edges are parted into contour segments & organized in an image representation that encodes their interconnections: the Contour segment Network. A computationally effective detection technique using Maximally Stable Extremal Regions (MSER) and Speeded up robust features (SURF) is developed to solve the issue of object detection, where paths are search through network & then resemble the model outlines with it. In this paper, real time cluttered images are considered and using proposed techniques such images to be detected from the complete scene. Simulated results show that both detection methods highlight accurate cluttered image. But, accuracy of matching the features among cluttered image and multiple objects in scene is highest in MSER while required computation time is lowest in SURF.

Cluttered images, MSER, Object Detection, and SURF.

"Comparative Analysis of SURF and MSER based Detection Technique of Cluttered Objects in Multi-objects Scene", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 6, page no.102-107, June-2018, Available :http://www.jetir.org/papers/JETIR1806401.pdf

"Comparative Analysis of SURF and MSER based Detection Technique of Cluttered Objects in Multi-objects Scene", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 6, page no. pp102-107, June-2018, Available at : http://www.jetir.org/papers/JETIR1806401.pdf