• H.PARVEEN BEGUM
• R.S.PRIYA

The study on find the new Bag-of-Words model based on level Invariant Feature Transform. SIFT has been broadly used in large-scale image recovery applications. Feature quantization by vector quantization plays a critical role in Bow model, which generates visual words from the high- dimensional SIFT features, so as to adapt to the wrong way up file structure for the scalable retrieval. Traditional feature quantization approaches suffer several issues, such as obligation of visual codebook instruction, limited uniformity, and update inefficiency. To avoid the above problems, in this paper, a original feature quantization scheme is proposed to competently quantize each SIFT descriptor to a descriptive and discriminative vector, which is called binary SIFT. Our quantizer is autonomous of image collections. In addition, by taking the first 32 bits out from BSIFT as code word, the generated BSIFT naturally lends itself to adapt to the classic inverted file structure for image indexing. Moreover, feature filtering, code word expansion, and query sensitive mask shielding reduce the quantization error. Without any unambiguous codebook for quantization, our approach can be readily applied in image search in some resource-limited scenarios. paper price the proposed algorithm for large-scale image search on two public image data sets. trial results make obvious the index efficiency and retrieval exactness of our approach. In the existing system used in Traditional, feature quantization. Traditional feature quantization approaches suffer several issues, such as necessity of diagram codebook training, limited reliability, and keep posted wastefulness. The most popular method for feature quantization is vector quantization. Originally used in lossy data compression, vector quantization divides a large set of training SIFT features into non-overlapped groups by clustering. To avoid the existing system problems, in this paper, a novel feature quantization scheme is proposed to efficiently quantize each SIFT descriptor to a descriptive and discriminative bit-vector, which is called binary SIFT (BSIFT). In this paper approach can be gladly applied in image search in some resource-limited scenarios.

Keywords: Image, cluster, sender, receiver

"FINDING NEW IDEA FOR BSIFT: TOWARD DATA-INDEPENDENT CODEBOOK FOR LARGE SCALE IMAGE SEARCH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 2, page no.1361-1364, February-2020, Available :http://www.jetir.org/papers/JETIR2002197.pdf

"FINDING NEW IDEA FOR BSIFT: TOWARD DATA-INDEPENDENT CODEBOOK FOR LARGE SCALE IMAGE SEARCH", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 2, page no. pp1361-1364, February-2020, Available at : http://www.jetir.org/papers/JETIR2002197.pdf