Stack Overflow
Stack Overflow

Questions tagged [approximate-nn-searching]

Approximate Nearest neighbor search (ANNS), also known as proximity search, similarity search or closest point search, is an optimization problem for finding closest points in metric spaces.

The interest for ANN search is that exact NNS can become very costly in terms of time of execution, when the dataset is big (number of points and especially dimension (curse of dimensionality)).

As a result, we accept the trade-off between speed and accuracy. The more speed, the less accuracy. In other words, we may find the exact NN, by performing a relatively fast search.

For example, in the picture below:

enter image description here

the point marked with an asterisk is the exact NN, but the ANN search may return as the point with the number 2, which is not the actual closest point to the query, but an approximation.

For more, visit wikipedia-ANN.

44 questions
2
votes
1 answer

How to disable JXTable default search action?

I have a JXTable in my swing app. When I press ctrl+F on the table, default search panel is opening. This panel finds only substrings. I need to find similar words with my InputText. For example, I write "test" result may be "tost", "tests",…
N0D1R
  • 313
  • 2
  • 11
2
votes
1 answer

Why k and l for LSH used for approximate nearest neighbours?

In all the Locality Sensitive Hashing explanations (i.e. http://en.wikipedia.org/wiki/Locality-sensitive_hashing#LSH_algorithm_for_nearest_neighbor_search ) They describe that k Hash Functions are generated, but only l (l < k) are used in the hash…
vardump
  • 658
  • 1
  • 10
  • 17
2
votes
1 answer

Adding an element to a VP tree (VP tree maintenance)

I have read few sources on VP-tree for similarity knn. No one wrote about adding an element to exists tree, which is required for maintenance. Explanation of adding element will be just great.
Omer Bar
  • 23
  • 3
2
votes
1 answer

Two sets of high dimensional points: Find the nearest neighbour in the other set

I have 2 sets: A and B. Both sets contain the same number of high dimensional points. How do I find the nearest neighbour in Set A for every point in Set B? I thought about using a Voronoi diagram but it seems (according to wikipedia) that it is not…
master_goon
  • 91
  • 6
2
votes
3 answers

Is Approximate Nearest Neighbour the fastest feature matching in Computer Vision?

When using feature descriptors [like SIFT, SURF] - is Approximate Nearest Neighbour the fastest method to do matching between images?
Slava V
  • 16,686
  • 14
  • 60
  • 63
1
vote
0 answers

Why are there occasional empty inner hits on nested kNN search?

I am having some issues using a nested kNN search. The problem is that occasionally, documents will be returned without any inner hits. How is this possible? Search result (notice the two last hits have empty inner hits): {'_shards': {'failed': 0,…
Bobby M
  • 11
  • 1
1
vote
1 answer

Attempting to implement a C++ library, need some pointers on how to interface with it

I'm relatively inexperienced in C++, and am trying to compile a library to DLL for use in Unity. As far as generating the DLL and interfacing with it, I've had success in getting my below function to call and return a dummy value in Unity, no…
Dan Hughes
  • 11
  • 4
1
vote
0 answers

Searching for closest statistically significant match in k-dimensional set

At a very high level this is similar to the nearest neighbor search problem. From wiki: "given a set S of points in a space M and a query point q ∈ M, find the closest point in S to q". But some significant differences. Specifics: Each point is…
ajit parthan
  • 11
  • 2
1
vote
0 answers

Neural Networks Descriptors in Approximate Nearest Neighbor for Image Retrieval

Disclamer: I don't know nothing about Neural Networks or deep learning. VLAD and Fisher Vectors with Product Quantization are a good example of how Approximate Nearest Neighbor can be used for good image retrieval. However, it has been proved how…
justHelloWorld
  • 6,478
  • 8
  • 58
  • 138
1
vote
2 answers

Error in calculating exact nearest neighbors in radius with FLANN

I am trying to find the exact number of neighbour nodes in a big 3D points dataset. The goal is for each point of the dataset to retrieve all the possible neighbours in a region with a given radius. FLANN ensures that for lower dimensional data can…
Constantino Mood
  • 21
  • 4
1
vote
1 answer

Which of these structures are for exact Nearest Neighbor and which ones for approximate version?

LSH is a popular algorithm for ANN. k-d Tree is maybe the most popular solution for exactly solving NN. However, reading this survey I found these structures and I don't understand which ones are for solving NN or…
justHelloWorld
  • 6,478
  • 8
  • 58
  • 138
1
vote
1 answer

LSH implementation in python 3 with Euclidean distance and seeing all neighbors in LSHForest

I am looking for an efficient implementation of LSH in python 3 that uses Euclidean distance. There is the "in-python" LSHForest implementation, but it uses cosine distances. Also, even using this implementation, I didn't find a way to see the…
user3861925
  • 713
  • 2
  • 10
  • 24
1
vote
1 answer

kd-tree stores points in inner nodes? If yes, how to search for NN?

The link in wikipedia about kd-trees store points in the inner nodes. I have to perform NN queries and I think (newbie here), I am understanding the concept. However, I was said to study Kd-trees from Computational Geometry Algorithms and…
gsamaras
  • 71,951
  • 46
  • 188
  • 305
1
vote
1 answer

How to lookup the most similar bit vector in an prefix tree for NN-search?

The problem I'm trying to solve is explained in this question: Finding the single nearest neighbor using a Prefix tree in O(1)? My question is regarding the Proposed solution section in that question page. In that section it's mentioned that we find…
Jack Twain
  • 6,273
  • 15
  • 67
  • 107
0
votes
1 answer

Weaviate - top hits for with_near_vector() doesn't include the record whose vector perfectly matches query vector

I have a very large Weaviate vector storage class (700,000 records) in which I pass my own custom vectors. I’m trying to get distances against a vector I pass as below. The vector is actually a match to one of the records, so I know the top hit…
lrthistlethwaite
  • 494
  • 2
  • 6
  • 23
1
2
3