Science Explorer Back to mapMap
Discussion
Topic · Computer Vision and Pattern Recognition

Image Retrieval and Classification Techniques

Image Retrieval and Classification Techniques is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 49k research works in it since 1956. 9.9% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on shape matching, object recognition, and content-based image retrieval using techniques such as local binary patterns, feature descriptors, and rotation-invariant methods. It also explores the application of these methods in medical imaging, semantic relevance modeling, and machine learning for image annotation.

  • Shape Matching
  • Content-Based Image Retrieval
  • Texture Classification
  • Local Binary Patterns
  • Feature Descriptors
  • Semantic Relevance
  • Rotation Invariant
  • Medical Applications
  • Machine Learning
  • Image Annotation
Research works
49k
fractional, since 1956
In the world top 10%
4.9k
per year above
Top-10% rate
9.9%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+1%
the tick is no change
Largest producer
China
55% of the 10 largest, 2022-now
Image Retrieval and Classification Techniques

Which countries lead Image Retrieval and Classification Techniques research?

By volume, China and India publish the most (2.8k and 869 works in 2022-now).

By volume, 2022-now

  1. 1 China 2.8k works
  2. 2 India 869 works
  3. 3 United States 513 works
  4. 4 Japan 161 works
  5. 5 South Korea 140 works
  6. 6 France 131 works
  7. 7 United Kingdom 130 works
  8. 8 Germany 127 works
  9. 9 Indonesia 107 works
  10. 10 Italy 98 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 55.4%India: 17.0%United States: 10.0%Japan: 3.1%6 others listed: 14.4%55%largest
China2,833 · 55.4%India869 · 17.0%United States513 · 10.0%Japan161 · 3.1%6 others listed734 · 14.4%

Shares of the rows listed above, not of the whole node.

Which institutions lead Image Retrieval and Classification Techniques research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Image Retrieval and Classification Techniques research, followed by Xidian University and Centre National de la Recherche Scientifique.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 93 works
  2. 2 Xidian UniversityChina 52 works
  3. 3 Centre National de la Recherche ScientifiqueFrance 41 works
  4. 4 University of Science and Technology of ChinaChina 41 works
  5. 5 Tsinghua UniversityChina 37 works
  6. 6 Zhejiang UniversityChina 36 works
  7. 7 Wuhan UniversityChina 36 works
  8. 8 Shanghai Jiao Tong UniversityChina 33 works
  9. 9 University of Electronic Science and Technology of ChinaChina 31 works
  10. 10 Northwestern Polytechnical UniversityChina 30 works

Who are the leading researchers in Image Retrieval and Classification Techniques?

The most-cited researchers publishing on Image Retrieval and Classification Techniques include Kaiming He, Yoshua Bengio and Geoffrey E. Hinton.

  1. 1 Kaiming He Israel 562k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Geoffrey E. Hinton Canada 454k citations
  4. 4 Xiangyu Zhang 327k citations
  5. 5 Karl John Friston United Kingdom 310k citations
  6. 6 Trevor Hastie United States 301k citations
  7. 7 Sudhir Kumar United States 295k citations
  8. 8 Jian Sun 281k citations
  9. 9 Xiaogang Wang China 260k citations
  10. 10 Yann LeCun United States 256k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Image Retrieval and Classification Techniques?

The most cited paper in Image Retrieval and Classification Techniques is "ImageNet: A large-scale hierarchical image database" (Jia Hao Deng, Wei Dong, Richard Socher et al., 2009), with 63,518 citations. Next come "ImageNet Large Scale Visual Recognition Challenge" (40,843) and "Learning Multiple Layers of Features from Tiny Images" (25,341).

Most cited papers
#PaperReleasedCitations
1 ImageNet: A large-scale hierarchical image database Jia Hao Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition Conference paper Jun 2009 63,518
2 ImageNet Large Scale Visual Recognition Challenge Olga Russakovsky, Jia Hao Deng, Hao Su et al. · International Journal of Computer Vision 10 Apr 2015 40,843
3 Learning Multiple Layers of Features from Tiny Images Alex Krizhevsky Open access 2024 25,341
4 Textural Features for Image Classification Robert M. Haralick, K. Shanmugam, Its'Hak Dinstein · IEEE Transactions on Systems Man and Cybernetics Nov 1973 22,878
5 Object recognition from local scale-invariant features David G. Lowe Conference paper 1999 16,396
All 100 most cited papers, with filters and sorting

Where is Image Retrieval and Classification Techniques research done?

The largest centres of Image Retrieval and Classification Techniques research in 2022-now are Beijing (China), Xi'an (China), Shanghai (China) and Nanjing (China). Among places with at least 20 works in it, it is an unusually large share of all research in Guilin.

Largest cities, 2022-now

  1. 1 BeijingChina 462 works
  2. 2 Xi'anChina 175 works
  3. 3 ShanghaiChina 168 works
  4. 4 NanjingChina 133 works
  5. 5 WuhanChina 133 works
  6. 6 GuangzhouChina 115 works
  7. 7 HangzhouChina 101 works
  8. 8 ChengduChina 100 works
  9. 9 ShenzhenChina 88 works
  10. 10 ChongqingChina 85 works

Where it is the local speciality

  1. GuilinCN · 28.3 works5.3×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Image Retrieval and Classification Techniques than the world average.

See Image Retrieval and Classification Techniques on the map

Where is the best place to study Image Retrieval and Classification Techniques?

Among universities, judged by research, Xidian University, Wuhan University and University of Science and Technology of China score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%20%40%mean 23.91%fractional works in this field (log) →share of work in the world top 10% →China University of …Wuhan UniversityXidian UniversityUniversity of Scienc…
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Xidian UniversityChina 76.319.4%12.7×52 +13.4%
2Wuhan UniversityChina 71.526.0%4.5×36 +21.2%
3University of Science and Technology of ChinaChina 69.116.3%6.1×41 +131.6%
4China University of GeosciencesChina 67.327.2%5.7×15 +141.3%
5Hong Kong University of Science and TechnologyChina 67.322.5%5.2×12 +201.8%
6Nanyang Technological UniversitySingapore 64.523.5%3.5×16 +17.9%
7Renmin University of ChinaChina 62.125.8%6.4×12 +191.7%
8Northwestern Polytechnical UniversityChina 61.719.1%4.7×30 +23.7%
9Shanxi UniversityChina 60.728.1%6.0×9 +287.9%
10University of Hong KongChina 60.031.2%1.8×10 +234.8%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Image Retrieval and Classification Techniques, country by country

Is Image Retrieval and Classification Techniques research growing?

Output in 2022-2025 was 1% higher than in 2018-2021, peaking in 2010. The fastest-growing topics are Image Retrieval and Classification Techniques.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Image Retrieval and Classification Techniques as a percentage of every work published that year, 0.035% in 2024.

still counting0.050%0.10%0.15%Image Retrieval and Classification Techniques0.032% in 202519801990200020102020

Fractional works of Image Retrieval and Classification Techniques over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Image Retrieval and Classification Techniques9.7% in 2025200020102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Discussion

Ask a question or share a note about Image Retrieval and Classification Techniques. Posts are plain text and can be reported.