Mosaicing Of Microscope Images Based On SURF

Image mosaic was originally generated to address the limitation of camera, multiple images are mapped to the same coordinate system using the mapping of overlap region. And then images are stitching by coverage of overlap region. The technology includes many basic computer vision algorithms, such as image matching, image fusion. And it has been applied to virtual reality, bio-medicine, video games and other entertainment. So image mosaic is a hotspot in the field of image processing.In medicine, biology and other fields, the view of microscope image is reducing as the magnification increasing. At low magnification view, it is difficult to observe large samples of details. However, when the details can be seen at high magnification, we can't observe the whole sample. So how to get the high-resolution image of the whole sample at high magnification is a difficult problem. The image mosaic algorithm can be achieved using multiple high-resolution images of the mosaic of local produce panoramic images is an effective way to solve the problem.In this paper, we describe the design of a mosaicing technique for images from a microscope system with automatically controlled object stage and image capture unit. Due to the limited field of view in microscope imagery, larger objects are split up into many adjacent, but slightly overlapping frames. In many fields, such as medicine or biology, it is vastly beneficial that these image patches are recomposed to a single (panoramic) image. We propose a feature matching and registration method based on SURF (Speeded-Up Robust Features). This method is most accurate for microscopy images, which usually have repetitive, blob-like structures. Further steps in our algorithm are estimation of transformation parameters for image warping and blending for elimination of color and luminance differences between images. For feature matching, we propose a new method of dividing descriptor windows. This increases matching speed considerably. The experimental results provided demonstrate the performance of our method.In the algorithm of SURF, the descriptor window is divided into 4×4 regular subregions. Each response of the subregions is weighted with a Gaussian centered at the key point. This defines a vector of length 128. In order to reduce the computational cost, we propose a new method for dividing the descriptor window. Our region dividing method can approximate the Gaussian weighting measure. Thus computational cost is saved in generating Gaussian mask and convolution. This also increases the matching speed considerably as the length of vectors is reduced by half. And it reflects speed advantage in the contrast with SIFT.