Performance Evaluation of SIFT & FLANN and HAAR Cascade Image Processing Algorithms for Object Identification in Robotic Applications

In this paper we present two different algorithms for applications based on image processing for a robotic arm. For feature extraction Scale Invariant Feature Transform (SIFT) algorithm is applied and for local feature matching, the Fast Library for Approximate Nearest Neighbors (FLANN) is applied to match the query image and reference image in data set. This paper also presents a method of image analysis by means of the wavelets–HAAR spectrum. It discusses about the algorithm in which the input frame is compared with data base. It converts BGR values to HSV after which it identifies the contour of object using several iteration process. The performances of both the algorithms are compared based on the time consumption and accuracy. The SIFT algorithm, which provides feature extraction and Flann, which provides feature matching with reference to the training image, when combined would identify the desired object from the input image. The HAAR classifier is based on a database with many images which consists of positive and negative samples. The algorithm runs on image iteration with the database and identifies the desired object from the input image. Size of the database is proportional to the accuracy of the function implemented through HAAR classifier algorithm. Keywords— SIFT, Flann, HAAR classifier, positive and