Locality Sensitive Hashing for satellite images using texture feature vectors

Buaba, Ruben; Gebril, Mohamed; Homaifar, Abdollah; Kihn, E. A.; Zhizhin, Mikhail

doi:10.1109/aero.2010.5447003

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, SVM achieves high classification rate compare to Decision Trees and C4.5 classification techniques. Although there exist many tree-based methods e.g., [7,8,11,12,13], for applications with memory constraints, hashing based ANN techniques have attracted more attention. The ANN techniques have constant query time and also substantially reduced storage as they usually store only compact binary codes for each point in X.…”

Section: Image Feature Signaturesmentioning

confidence: 99%

“…Hash function Universality Suppose U is a universe of keys, and Gj H is a family of a finite collection of hash functions [12] We define the following objective function measuring the empirical accuracy on the labeled data for a family of hash functions H (5) So the general algorithm can be described as: 1. Extract local features from every image 2. compute distances of the query to all training examples using LSH with the objective function as in (5)and pick the nearest neighbors; 3.…”

Section: Image Feature Signaturesmentioning

confidence: 99%

See 1 more Smart Citation

Satellite imagery retrieval: Features & metrics evaluation

Gebril

Homaifar

Buaba

et al. 2012

2012 IEEE Aerospace Conference

View full text Add to dashboard Cite

In this paper, an evaluation technique based on several image feature attributes along with image classifications is investigated. Furthermore, a semi-supervised technique based on support vector machine (SVM) for image classification and a Locality Sensitive Hashing (LSH) based searching algorithm to search for similarity of satellite imagery is presented. Given a query image, the goal is to retrieve matching images in the database based on the shape features extracted from satellite imagery data.The experimental results demonstrate superior results based on shape features which provide a better classification accuracy using both support vector machine and the semi-supervised hashing search methods . 1 2

show abstract

Section: Image Feature Signaturesmentioning

confidence: 99%

Section: Image Feature Signaturesmentioning

confidence: 99%

Satellite imagery retrieval: Features & metrics evaluation

Gebril

Homaifar

Buaba

et al. 2012

2012 IEEE Aerospace Conference

View full text Add to dashboard Cite

show abstract

“…Certain common genome sequences are often queried more times than the rest [22]. (2) Similarly, earthquake detection or satellite image data, both high-dimensional data [6,28], often query certain similar regions of the space that are of more interest. These queries can be viewed as part of a query workload.…”

Section: Motivationmentioning

confidence: 99%

“…While the LSH family (explained further in Section 3) in [14] was originally defined for the Hamming distance, it was later defined for other distance measures such as the Euclidean distance [9]. Effective Variants of LSH: LSH has been shown to be useful in various domains such as biomedical sciences [5,7,22], geological sciences [6,28], etc. Several works were subsequently proposed [4,10,11,13,15,16,24,26] to improve upon the original work.…”

Section: Related Workmentioning

confidence: 99%

qwLSH: Cache-conscious Indexing for Processing Similarity Search Query Workloads in High-Dimensional Spaces

Jafari,

Ossorgin,

Nagarkar

2019

Preprint

View full text Add to dashboard Cite

Similarity search queries in high-dimensional spaces are an important type of queries in many domains such as image processing, machine learning, etc. Since exact similarity search indexing techniques suffer from the well-known curse of dimensionality in high-dimensional spaces, approximate search techniques are often utilized instead. Locality Sensitive Hashing (LSH) has been shown to be an effective approximate search method for solving similarity search queries in high-dimensional spaces. Often times, queries in real-world settings arrive as part of a query workload. LSH and its variants are particularly designed to solve single queries effectively. They suffer from one major drawback while executing query workloads: they do not take into consideration important data characteristics for effective cache utilization while designing the index structures. In this paper, we present qwLSH, an index structure for efficiently processing similarity search query workloads in high-dimensional spaces. We intelligently divide a given cache during processing of a query workload by using novel cost models. Experimental results show that, given a query workload, qwLSH is able to perform faster than existing techniques due to its unique cost models and strategies.

show abstract

Satellite image retrieval using low memory locality sensitive hashing in Euclidean space

Buaba¹,

Homaifar²,

Gebril³

et al. 2011

Earth Sci Inform

Self Cite

View full text Add to dashboard Cite

This paper presents the use of the Low Memory Locality Sensitive Hashing (LMLSH) technique operating in Euclidean space to build a data structure for the Defense Meteorological Satellite Program (DMSP) satellite imagery database. The LMLSH technique finds satellite image matches in sublinear search time. The texture feature vectors of the images are extracted using pyramid-structured wavelet transform coupled with Gaussian central moment technique. These feature vectors and families of hash functions, drawn randomly and independently from a Gaussian distribution, are used to build hash tables. Given a query, the hash tables are used to pull out the best matches to that query and this is done in a sublinear search time complexity. When tested, our algorithm has proven to be approximately twenty six times faster than the Linear Search (LS) algorithm. In addition, the LMLSH algorithm searches about two percent of the entire database randomly to find the possible matches to any given query without loss of accuracy compared to the absolute best matches returned by its LS counterpart.

show abstract

Locality Sensitive Hashing for satellite images using texture feature vectors

Cited by 7 publications

References 16 publications

Satellite imagery retrieval: Features & metrics evaluation

Satellite imagery retrieval: Features & metrics evaluation

qwLSH: Cache-conscious Indexing for Processing Similarity Search Query Workloads in High-Dimensional Spaces

Satellite image retrieval using low memory locality sensitive hashing in Euclidean space

Contact Info

Product

Resources

About

Locality Sensitive Hashing for satellite images using texture feature vectors

Cited by 7 publications

References 16 publications

Satellite imagery retrieval: Features &amp; metrics evaluation

Satellite imagery retrieval: Features &amp; metrics evaluation

qwLSH: Cache-conscious Indexing for Processing Similarity Search Query Workloads in High-Dimensional Spaces

Satellite image retrieval using low memory locality sensitive hashing in Euclidean space

Contact Info

Product

Resources

About

Satellite imagery retrieval: Features & metrics evaluation

Satellite imagery retrieval: Features & metrics evaluation