Science Explorer Interactive view Map

Handwritten Text Recognition Techniques

Handwritten Text Recognition Techniques is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 19k research works in it since 1951. 13.4% of them reached the world's top 10% most cited for their field and year.

This cluster of papers covers a wide range of topics related to handwriting recognition and text detection, including scene text recognition, document image analysis, neural networks for OCR, signature verification, text localization, and binarization techniques.

  • Handwriting Recognition
  • Text Detection
  • Scene Text Recognition
  • Document Image Analysis
  • Neural Networks
  • OCR Engine
  • Signature Verification
  • Text Localization
  • Convolutional Neural Networks
  • Binarization
Research works
19k
fractional, since 1951
In the world top 10%
2.5k
per year above
Top-10% rate
13.4%
share of its works in the world top 10%
Growth, 2013–17 → 2018–22
+42%
the tick is no change

Which countries lead Handwritten Text Recognition Techniques research?

By volume, China and India publish the most (1.3k and 1.1k works in 2022–2025).

By volume, 2022–2025

  1. 1 China 1.3k works
  2. 2 India 1.1k works
  3. 3 United States 302 works
  4. 4 Indonesia 141 works
  5. 5 Japan 119 works
  6. 6 Germany 99 works
  7. 7 France 90 works
  8. 8 Bangladesh 80 works
  9. 9 ?? 78 works
  10. 10 South Korea 77 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: 37.9%India: 32.2%United States: 9.2%Indonesia: 4.3%6 others listed: 16.5%38%largest
China1,252 · 37.9%India1,062 · 32.2%United States302 · 9.2%Indonesia141 · 4.3%6 others listed544 · 16.5%

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

Which institutions lead Handwritten Text Recognition Techniques research?

By volume in 2022–2025, Amrita Vishwa Vidyapeetham publishes the most Handwritten Text Recognition Techniques research, followed by University of Science and Technology of China and Xinjiang University.

Who are the leading researchers in Handwritten Text Recognition Techniques?

The most-cited researchers publishing on Handwritten Text Recognition Techniques include Yoshua Bengio, Alan Yuille and Anil K. Jain.

  1. 1 Yoshua Bengio Canada 17k citations
  2. 2 Alan Yuille United States 8.4k citations
  3. 3 Anil K. Jain United States 6.3k citations
  4. 4 Dacheng Tao Australia 6.1k citations

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

Where is Handwritten Text Recognition Techniques research done?

The largest centres of Handwritten Text Recognition Techniques research in 2022–2025 are Beijing (China), Chennai (India), Shanghai (China) and Wuhan (China). Among places with at least 20 works in it, it is an unusually large share of all research in Coimbatore and Greater Noida.

Largest cities, 2022–2025

  1. 1 Beijing China 252 works
  2. 2 Chennai India 102 works
  3. 3 Shanghai China 100 works
  4. 4 Wuhan China 67 works
  5. 5 Bengaluru India 67 works
  6. 6 Guangzhou China 66 works
  7. 7 Coimbatore India 64 works
  8. 8 Pune India 61 works
  9. 9 Hangzhou China 54 works
  10. 10 Xi'an China 49 works

Where it is the local speciality

  1. CoimbatoreIN · 64.3 works8.3×
  2. Greater NoidaIN · 23.2 works8.2×
← less than its size predictsmore →

Location quotient: how much more of its research is in Handwritten Text Recognition Techniques than the world average.

See Handwritten Text Recognition Techniques on the map

Where is the best place to study Handwritten Text Recognition Techniques?

Among universities, judged by research, University of Science and Technology of China, South China University of Technology and Amrita Vishwa Vidyapeetham 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 16.23%fractional works in this node (log) →share in the world top 10% →University of Science and Technology of China: 33, 16.7%South China University of Technology: 27, 26.7%Amrita Vishwa Vidyapeetham: 45, 4.6%Chandigarh University: 20, 6.1%International Institute of Information Technology, Hyderabad: 10, 22.7%Chitkara University: 24, 5.9%University of Science and Technology Beijing: 12, 24.7%Visvesvaraya Technological University: 13, 7.5%Huazhong University of Science and Technology: 15, 29.2%Indian Statistical Institute: 9, 18.2%South China Universi…University of Scienc…Chandigarh UniversityAmrita Vishwa Vidyap…
above the meannear itbelow it

One dot per university in the table below. The upper left is the interesting corner: small places doing unusually strong work.

#UniversityScoreTop 10%SpecialisationWorksGrowth
1 University of Science and Technology of ChinaChina 63.816.7%6.1×33 +386.8%
2 South China University of TechnologyChina 63.326.7%5.6×27 +108.2%
3 Amrita Vishwa VidyapeethamIndia 58.54.6%18.6×45 +79.0%
4 Chandigarh UniversityIndia 53.46.1%8.1×20 +216.7%
5 International Institute of Information Technology, HyderabadIndia 52.522.7%44.2×10 -49.6%
6 Chitkara UniversityIndia 51.65.9%13.5×24
7 University of Science and Technology BeijingChina 51.624.7%3.5×12 +309.1%
8 Visvesvaraya Technological UniversityIndia 50.67.5%20.9×13 +146.1%
9 Huazhong University of Science and TechnologyChina 50.129.2%2.1×15 +130.4%
10 Indian Statistical InstituteIndia 48.718.2%24.1×9 -20.9%

Universities only. Score blends excellence (30%), specialisation (25%), size (20%), growth (15%) and international reach (10%), 2015–2022; growth compares 2010–14 with 2015–19.

Is Handwritten Text Recognition Techniques research growing?

Output in 2018–2022 was 42% higher than in 2013–2017, peaking in 2025. The fastest-growing topics are Handwritten Text Recognition Techniques.

19801990200020102020
grewheldshrank

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

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.