Secure Image Retrieval Search Engine

1
Secure Image Retrieval Search Engine
Presented by Ranjit R. Banshpal

1
1
2
OUTLINES

• Introduction
• Literature Survey
• Research Methodology to be employed
• Objectives
• Scope
• Scenario of work
• References

3
Introduction

• Scalable image search based on visual similarity
  has been an active topic of research in recent
  years.
• Here introduces an approach that enables
  query-adaptive ranking of the returned images
  with equal Hamming distances to the queries.

4
Literature Survey
Sr. No Title Authors Description
1.     Query-Adaptive Image Search with Hash Codes Yu-Gng Jiang, Jun Wang, Xiangyang Xue,, and Shih-Fu Chang. Here present a novel framework for query-adaptive image search with hash codes
2. Optimizing kd-trees for scalable visual descriptor indexing You Jia Jingdong Wang Gang Zeng Hongbin Zha Xian-Sheng Hua Here present a simple yet effective for partition hyper plane selection in the conventional kd-tree.
3. Weakly-Supervised Hashing in Kernel Space Yadong Mu, Jialie Shen2, Shuicheng Yan The proposed method generates hash functions in weakly-supervised setting, where a small portion of sample pairs are manually labeled to be similar or unalike.
5
Methodology

• Here use a rapid template matching based on two
  column histogram hashing.
• To make more efficient while searching image use
  some local invariant image descriptors to extract
  and quantize based on a set of visual words.
• To avoid error during hash code request providing
  Secure hashing which protected the request in
  real time environment .
• And compressed hashing algorithm is used to
  improve extra memory allocation.

6
Objectives

• Provide efficient and fast image retrieval.
• Compressed hashing as a technique to compress the
  memory and store more data in the given space and
  to improve the retrieval time.
• Secure hashing is also use for protecting the
  request in real time environment.

7
Scope

• Following are the area where it can be use
• Like military image database,
• personal photograph album,
• Document storage system etc.

8
Block diagram of proposed system
Select image to search
Providing training for bitwise weights of the
hash codes for a various set of predefined
semantic concept classes.  
Generate hash code of image
Secure hashing method
Extract and quantize image feature  
Database
Retrieve images
9
REFERENCES

1. Yu-Gng Jiang, Jun Wang, Member, IEEE, Xiangyang
   Xue, Member, IEEE, and Shih-Fu Chang, Fellow,
   IEEE, "Query-Adaptive Image Search with Hash
   Codes, IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 15,
   NO. 2, FEBRUARY 2013
2. A. W. Smeulders,M.Worring, S. Santini, A. Gupta,
   and R. Jain, Content-based image retrieval at
   the end of the early years, IEEE Trans. Pattern
   Anal. Mach. Intell., vol. 22, no. 12, pp.
   13491380, Dec. 2000.
3. Silpa-Anan and R. Hartley, Optimised KD-trees
   for fast image descriptor matching, in Proc.
   IEEE Conf. Computer Vision and Pattern
   Recognition, 2008.
4. Bin Li, Delie Ming, Wenwen Yan, Xiao Sun, Tian
   Tian, and Jinwen Tian, Image Matching Based on
   Two-Column Histogram Hashing and Improved
   RANSAC, IEEE GEOSCIENCE AND REMOTE SENSING
   LETTERS, VOL. 11, NO. 8, AUGUST 2014.
5. H. Jegou, M. Douze, and C. Schmid, Improving
   bag-of-features for Large scale image search,
   Int. J. Comput. Vision, vol. 87, pp. 191212,
   2010.

10

1. David Nister and Henrik Stewenius, Scalable
   Recognition with a Vocabulary Tree, Computer
   Society Conference on Computer Vision and Pattern
   Recognition (CVPR06) IEEE 2006.
2. K. Mikolajczyk and J. Matas. Improving
   descriptors for fast tree matching by optimal
   linear projection,. In ICCV, pages 18, 2007.
3. T. Liu, A. W. Moore, A. G. Gray, and K. Yang. An
   investigation of practical approximate nearest
   neighbor algorithms. In NIPS, 2004.

11
THANK YOU