No abstract

The image registration is a fundamental task in related to the Fourier-based scheme is the shifting properties of image processing used to match two or more pictures taken, for the Fourier transform [2], which allows robust estimation of example, at different time, from different sensors, or from . u different viewpoints. One of the major challenges related to image the translations using phase correlation [31. In order to account registration is the estimation of large motion, when input images for rotation and scaling, the image is transformed into a contain small overlapped area. Common image registration using uniform polar grid or log-polar grid. However, only phase the search algorithm can accurately finds large motion but correlation is not sufficient since the registration results usually requires high computation cost due to large search space. Fourier-contain errors in the case of large translations with small based technique is an alternative approach since it can rapidly overlapped area between the input images. achieve the registration results through its FFT algorithm. However, only Fourier-based technique cannot produce the In this paper, we proposed a FFT-based image registration correct results in the case of large translation. Thus, this paper algorithm cooperated with best-first search algorithm to presents a Fourier-based technique cooperated with best-first increase the performance of the image registration process. The search algorithm to analyze the correct translation between two Fourier phase correlation technique is used to estimate the input images. The Fourier-based technique is used to estimate the candidate translations to decrease searching space while best-first search algorithm is used to further search for the correct best-first search algorithm is then applied to obtain the best translation. The proposed technique can estimate large translation of angle and scale from candidate translations translations, scalings, and rotations in images by an extension of obtained from phase correlation [4]. well-known phase correlation technique. The experimental results using various image details show the accuracy of the proposed technique to detect large translations compared to the other II. FUNDAMENTAL THEORY techniques in frequency domain. APHAsE CORRELATION TECHNIQUE

This paper presents an approach to manage a large database using a compact color descriptor and a statistical method for accurately pruning the database. A compact color descriptor adopted in the proposed content-based image retrieval system is 63-bit binary Haar color histogram, which is very compact and can be effectively used for fast image search. In addition to fast searching using this compact descriptor, we further improve retrieval time by applying pruning technique, which looks for the candidate images similar to the query image from the database and ignore the rest that are not likely to the query image. The descriptors of the candidate images are then matched with that of the query. The most similar images will be retrieved and ordered according to their distance to the query. The proposed retrieval system can efficiently retrieve the most similar images from the database while can help reducing the retrieval time and the storage space.

No abstract

No abstract