ISSN (Online) : 2278-1021 ISSN (Print) : 2319-5940 International Journal of Advanced Research in Computer and Communication Engineering Vol. 3, Issue 10, October 2014 Copyright to IJARCCE www.ijarcce.com 8287 Image stitching by extracted key frames using absolute difference method Mr. Sarvajeet Bhosale 1 , Mr. K. R. Desai 2 Student of ME, Bharati Vidyapeeth College of Engineering, Kolhapur, India 1 Associate Professor, Bharati Vidyapeeth College of engineering, Kolhapur, India 2 Abstract: Image stitching presents different stages to render two or more overlapping images into a seamless stitched image, from the detection of features to blending in a final image. In this process, Scale Invariant Feature Transform (SIFT) algorithm [1] can be applied to perform the detection and matching control points step, due to its good properties. The process of create an automatic and effective whole stitching process leads to analyze different methods of the stitching stages.RANSAC is used for fine results. Keywords: Image stitching, Video frame extraction, SIFT, RANSAC. I. INTRODUCTION Feature-based method is one of methods of Image stitching. And we propose a method based on invariant scale feature, which mainly includes two key parts: image matching and image blending. Image matching is used to find the motion relationship between two images or several images, and it directly relates to the success rate and the speed of the total process. While image blending is used to eliminate the various illumination of the adjacent image or color does not consecutive caused by the geometric correction or dynamic scene illumination. In that way two images can stitch into a seamless image. Video frame mosaic is a process that integrates two or more frames into a large-size image with a wide field of view [15]. Image mosaic joints the two images directly in the early times. At this time, if two images don’t match that splicing effect not to be unstable, therefore, using image mosaic technology based on the Feature matching [16] causes two large displacement difference images to carry on the examination and the match, the splicing effect is good [5]. Video frames can be used for stitching to create one larger image. Given a sequence of images taken from a single point in space, but with varying orientations, it is possible to map the images into a common reference frame and create a perfectly aligned larger photograph with a wider field of view. This is normally referred to as panoramic image stitching. II.ACTUAL ALGORITHM The entire algorithm mainly includes: Extracted video frame from an video sequence, extract SIFT features; match features to get potential feature matches; match image sequence; match the image completely and blend the image, which can be described as the figure1. Algorithm: The algorithm for video frame is represented as,  Collect a set of overlapping images from the video input (video frames)  Choose a reference image Fig 1: The Entire process of the paper  For each image “x”: 1. Find feature matches between reference and x 2. Determine transform from x to reference 3. Transform x and place both on composite surface 4. Composite becomes new reference.  Run aesthetic algorithms. A. Extracted frames from video The video frame [11] is taken as the input and it is processes using the video processing in Matlab. The key frames are extracted from the video [7, 8]. These frames are given as the input to the SIFT algorithm and are used for creating the panoramic image [12]. For extraction of key frames the sum of absolute difference method is used. Sum of Absolute difference is a simplest method in order to find the relation between two image windows. To represent the difference few of the mathematical formulas are given as: a) The difference between two points in one dimension is given as: d(A,B) = |x1 – x2| b) The difference between two points in two dimensions can be formulated as: