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

Image and Object Detection Techniques

Image and Object Detection Techniques is a research topic within Computer Vision and Pattern Recognition. Science Explorer counts 22k research works in it since 1951. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on robust line and curve detection using the Hough Transform, including techniques for line detection, circle and ellipse fitting, randomized algorithms, computer vision applications, edge detection, geometric fitting, and statistical optimization.

  • Hough Transform
  • Line Detection
  • Circle Fitting
  • Ellipse Detection
  • Randomized Algorithm
  • Computer Vision
  • Edge Detection
  • Geometric Fitting
  • Real-time Detection
  • Statistical Optimization
Research works
22k
fractional, since 1951
In the world top 10%
2.2k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+16%
the tick is no change
Largest producer
China
66% of the 10 largest, 2022-now
Image and Object Detection Techniques

Which countries lead Image and Object Detection Techniques research?

By volume, China and India publish the most (2k and 248 works in 2022-now).

By volume, 2022-now

  1. 1 China 2k works
  2. 2 India 248 works
  3. 3 United States 234 works
  4. 4 Germany 110 works
  5. 5 Japan 103 works
  6. 6 South Korea 86 works
  7. 7 Russia 79 works
  8. 8 United Kingdom 66 works
  9. 9 Indonesia 60 works
  10. 10 Türkiye 58 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: 65.8%India: 8.1%United States: 7.7%Germany: 3.6%6 others listed: 14.8%66%largest
China2,012 · 65.8%India248 · 8.1%United States234 · 7.7%Germany110 · 3.6%6 others listed452 · 14.8%

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

Which institutions lead Image and Object Detection Techniques research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Image and Object Detection Techniques research, followed by Shanghai Jiao Tong University and Harbin Institute of Technology.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 72 works
  2. 2 Shanghai Jiao Tong UniversityChina 33 works
  3. 3 Harbin Institute of TechnologyChina 31 works
  4. 4 Nanjing University of Aeronautics and AstronauticsChina 23 works
  5. 5 Beijing Institute of TechnologyChina 22 works
  6. 6 Beihang UniversityChina 22 works
  7. 7 Huazhong University of Science and TechnologyChina 22 works
  8. 8 Tsinghua UniversityChina 21 works
  9. 9 Zhejiang UniversityChina 21 works
  10. 10 Tongji UniversityChina 21 works

Who are the leading researchers in Image and Object Detection Techniques?

The most-cited researchers publishing on Image and Object Detection Techniques include Geoffrey E. Hinton, Ross Girshick and Xiangyu Zhang.

  1. 1 Geoffrey E. Hinton Canada 454k citations
  2. 2 Ross Girshick Israel 356k citations
  3. 3 Xiangyu Zhang 327k citations
  4. 4 Trevor Hastie United States 301k citations
  5. 5 Jian Sun 281k citations
  6. 6 Yann LeCun United States 256k citations
  7. 7 Andrew Zisserman United Kingdom 255k citations
  8. 8 Tien Yin Wong Singapore 237k citations
  9. 9 Kai You Wang China 224k citations
  10. 10 Stephen M. Smith United Kingdom 214k 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 and Object Detection Techniques?

The most cited paper in Image and Object Detection Techniques is "Distinctive Image Features from Scale-Invariant Keypoints" (David G. Lowe, 2004), with 56,041 citations. Next come "A Computational Approach to Edge Detection" (29,563) and "A method for registration of 3-D shapes" (18,308).

Most cited papers
#PaperReleasedCitations
1 Distinctive Image Features from Scale-Invariant Keypoints David G. Lowe · International Journal of Computer Vision 2 Jun 2004 56,041
2 A Computational Approach to Edge Detection John Canny · IEEE Transactions on Pattern Analysis and Machine Intelligence Nov 1986 29,563
3 A method for registration of 3-D shapes Paul J. Besl, Neil David McKay · IEEE Transactions on Pattern Analysis and Machine Intelligence Feb 1992 18,308
4 Object recognition from local scale-invariant features David G. Lowe Conference paper 1999 16,396
5 Active Shape Models-Their Training and Application Tim F. Cootes, Chris Taylor, David H. Cooper et al. · Computer Vision and Image Understanding Open access 1995 7,230
All 99 most cited papers, with filters and sorting

Where is Image and Object Detection Techniques research done?

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

Largest cities, 2022-now

  1. 1 BeijingChina 347 works
  2. 2 ShanghaiChina 156 works
  3. 3 Xi'anChina 114 works
  4. 4 WuhanChina 102 works
  5. 5 NanjingChina 98 works
  6. 6 GuangzhouChina 71 works
  7. 7 HangzhouChina 70 works
  8. 8 ChangshaChina 64 works
  9. 9 ChengduChina 62 works
  10. 10 TianjinChina 60 works

Where it is the local speciality

  1. ShenyangCN · 45.5 works4.3×
  2. Xi'anCN · 114.3 works4.0×
← less than its size predicts1×more →

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

See Image and Object Detection Techniques on the map

Where is the best place to study Image and Object Detection Techniques?

Among universities, judged by research, China University of Mining and Technology, Shanghai Jiao Tong University and Huazhong University of Science and Technology 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%10%20%30%mean 17.58%fractional works in this field (log) →share of work in the world top 10% →China University of …Technical University…Huazhong University …Shanghai Jiao Tong U…
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
1China University of Mining and TechnologyChina 71.926.0%5.6×14 +77.7%
2Shanghai Jiao Tong UniversityChina 69.215.4%3.5×33 +24.2%
3Huazhong University of Science and TechnologyChina 65.519.8%3.6×22 +22.2%
4Technical University of MunichGermany 62.422.5%2.9×8 +27.9%
5Hunan UniversityChina 62.320.7%5.5×13 +52.1%
6Tongji UniversityChina 60.512.2%4.1×21 +39.3%
7Tsinghua UniversityChina 60.214.4%2.8×21 +49.5%
8Central South UniversityChina 57.713.8%3.2×20 +101.0%
9Southeast UniversityChina 57.014.6%3.6×18 +50.4%
10Zhejiang Sci-Tech UniversityChina 56.916.4%11.1×11 +211.3%

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 and Object Detection Techniques, country by country

Is Image and Object Detection Techniques research growing?

Output in 2022-2025 was 16% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Image and Object Detection 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 and Object Detection Techniques as a percentage of every work published that year, 0.018% in 2024.

still counting0.020%0.040%0.060%Image and Object Detection Techniques0.017% in 202519801990200020102020

Fractional works of Image and Object Detection 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 and Object Detection Techniques9.8% 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 and Object Detection Techniques. Posts are plain text and can be reported.