# \#features2d

**URL:** https://forum.opencv.org/tag/features2d/68.md

[Latest](https://forum.opencv.org/latest.md) · [Categories](https://forum.opencv.org/categories.md) · [Tags](https://forum.opencv.org/tags.md)

---

## [cv2.findChessboardCorners() running endlessly on certain images](https://forum.opencv.org/t/cv2-findchessboardcorners-running-endlessly-on-certain-images/12972)

<div class="topic-metadata">

**Author:** [@JeremyKeusters](https://forum.opencv.org/u/JeremyKeusters)\
**Replies:** 4\
**Last updated:** [April 15, 2026, 11:16am UTC](https://forum.opencv.org/t/cv2-findchessboardcorners-running-endlessly-on-certain-images/12972 "2026-04-15T11:16:40Z")

</div>

Hi, First of all thanks for all your contributions to OpenCV. Problem statement I’m using OpenCV to find chessboard corners on an image. It can happen that an image is passed into the function that is of bad quality o…

---

## [Adjust sub-pixel coordinates in RefineChessboardCorners](https://forum.opencv.org/t/adjust-sub-pixel-coordinates-in-refinechessboardcorners/24050)

<div class="topic-metadata">

**Author:** [@Ueli\_Peter](https://forum.opencv.org/u/Ueli_Peter)\
**Replies:** 1\
**Last updated:** [September 30, 2025, 9:14pm UTC](https://forum.opencv.org/t/adjust-sub-pixel-coordinates-in-refinechessboardcorners/24050 "2025-09-30T21:14:43Z")

</div>

Hi, in the source code for selectAndRefineChessboardCorners I don’t understand line 161 and 170 here: opencv/modules/objdetect/src/aruco/charuco\_detector.cpp at 5.x · opencv/opencv · GitHub Before cornerSubPix (0.5, 0.5…

---

## [SIFT algorithm in opencvjs is undefined](https://forum.opencv.org/t/sift-algorithm-in-opencvjs-is-undefined/23973)

<div class="topic-metadata">

**Author:** [@2297098619pcz](https://forum.opencv.org/u/2297098619pcz)\
**Replies:** 5\
**Last updated:** [September 11, 2025, 10:03am UTC](https://forum.opencv.org/t/sift-algorithm-in-opencvjs-is-undefined/23973 "2025-09-11T10:03:50Z")

</div>

OpenCV version: 4.12.0 I added “‘SIFT’: \[‘create’\],” to features2d in opencv\_js.config.py. However, after building, references to cv.SIFT are still undefined. I also added the opencv\_contrib add-on module and enabled --…

---

## [findChessboardCornersSB not working, detects only some corners](https://forum.opencv.org/t/findchessboardcornerssb-not-working-detects-only-some-corners/22844)

<div class="topic-metadata">

**Author:** [@Falco\_Peregrinus](https://forum.opencv.org/u/Falco_Peregrinus)\
**Replies:** 2\
**Last updated:** [August 31, 2025, 2:13pm UTC](https://forum.opencv.org/t/findchessboardcornerssb-not-working-detects-only-some-corners/22844 "2025-08-31T14:13:43Z")

</div>

Hi. I have pictures of my checkerboard, but findChessboardCornersSB() or findChessboardCorners() cannot detect all corners, only some of them, or none, regardless of checkerboard dimensions that I input. I tried the…

---

## [Simple Blob Detector: How is a blob measured?](https://forum.opencv.org/t/simple-blob-detector-how-is-a-blob-measured/23157)

<div class="topic-metadata">

**Author:** [@CCN](https://forum.opencv.org/u/CCN)\
**Replies:** 4\
**Last updated:** [July 16, 2025, 7:35pm UTC](https://forum.opencv.org/t/simple-blob-detector-how-is-a-blob-measured/23157 "2025-07-16T19:35:08Z")

</div>

How is a blob measured in Simple Blob Detector? The equation for detecting the blob size seems to be as follows: Math.PI \* (kp.Size / 2) ^ 2) . According to OpenCV: OpenCV: cv::KeyPoint Class Reference it seems kp.Size i…

---

## [\[OpenCV.js\] Getting SIFT and FLANN to work](https://forum.opencv.org/t/opencv-js-getting-sift-and-flann-to-work/9987)

<div class="topic-metadata">

**Author:** [@Digizard](https://forum.opencv.org/u/Digizard)\
**Replies:** 7\
**Last updated:** [May 14, 2025, 9:26am UTC](https://forum.opencv.org/t/opencv-js-getting-sift-and-flann-to-work/9987 "2025-05-14T09:26:11Z")

</div>

Hi, all! I’m looking for help on how to use SIFT and FLANN with OpenCV.js. I basically want to translate this code from Python: needle = cv.imread('needle.png', 0) haystack = cv.imread('haystack.png', 0) sift = cv.SIF…

---

## [How to use opacity in drawKeypoints or drawMatches?](https://forum.opencv.org/t/how-to-use-opacity-in-drawkeypoints-or-drawmatches/20792)

<div class="topic-metadata">

**Author:** [@dustinfreeman](https://forum.opencv.org/u/dustinfreeman)\
**Replies:** 1\
**Last updated:** [April 10, 2025, 8:51pm UTC](https://forum.opencv.org/t/how-to-use-opacity-in-drawkeypoints-or-drawmatches/20792 "2025-04-10T20:51:08Z")

</div>

I’m using OpenCV 4.10 in python, but this should generalize to anyone using drawKeypoints or drawMatches. I want to draw the keypoints with less than 100% opacity over the image. I have tried: img3 = cv2.drawKeypoints(i…

---

## [Strange code in Fast Keypoint detector: (i - 3) % 3](https://forum.opencv.org/t/strange-code-in-fast-keypoint-detector-i-3-3/19682)

<div class="topic-metadata">

**Author:** [@vahagnIV](https://forum.opencv.org/u/vahagnIV)\
**Replies:** 3\
**Last updated:** [January 5, 2025, 8:31am UTC](https://forum.opencv.org/t/strange-code-in-fast-keypoint-detector-i-3-3/19682 "2025-01-05T08:31:02Z")

</div>

I see this code here: Am I missing something or is it an artifact that remained there after debugging?

---

## [Is traincascade and createsamples tools replaced by new?](https://forum.opencv.org/t/is-traincascade-and-createsamples-tools-replaced-by-new/19610)

<div class="topic-metadata">

**Author:** [@master\_cn](https://forum.opencv.org/u/master_cn)\
**Replies:** 1\
**Last updated:** [December 25, 2024, 11:00pm UTC](https://forum.opencv.org/t/is-traincascade-and-createsamples-tools-replaced-by-new/19610 "2024-12-25T23:00:00Z")

</div>

Why ocv\_add\_app(traincascade) and ocv\_add\_app(createsamples) is commented out in opencv/apps/CMakeLists.txt. Is this replaced by new tools?

---

## [Finding multiple instances of same object](https://forum.opencv.org/t/finding-multiple-instances-of-same-object/4987)

<div class="topic-metadata">

**Author:** [@mewil666](https://forum.opencv.org/u/mewil666)\
**Replies:** 3\
**Last updated:** [August 31, 2021, 9:01pm UTC](https://forum.opencv.org/t/finding-multiple-instances-of-same-object/4987 "2021-08-31T21:01:24Z")

</div>

Hi, I’m trying to find multiple instances of similar object in one picture. Object is this black ring on light background. So far, I was able to find it with: -template matching, with results differing from images a…

---

## [\[opencv.js\] support for findHomography()](https://forum.opencv.org/t/opencv-js-support-for-findhomography/1126)

<div class="topic-metadata">

**Author:** [@Scott\_Suhy](https://forum.opencv.org/u/Scott_Suhy)\
**Replies:** 22\
**Last updated:** [October 22, 2024, 2:56pm UTC](https://forum.opencv.org/t/opencv-js-support-for-findhomography/1126 "2024-10-22T14:56:05Z")

</div>

can anyone point me to a working example of calling findHomography() using opencv.js? I believe it is part of the subset.

---

## [Global adjustment to avoid dragging error in Image stitching](https://forum.opencv.org/t/global-adjustment-to-avoid-dragging-error-in-image-stitching/3750)

<div class="topic-metadata">

**Author:** [@martingra](https://forum.opencv.org/u/martingra)\
**Replies:** 4\
**Last updated:** [October 15, 2024, 2:03am UTC](https://forum.opencv.org/t/global-adjustment-to-avoid-dragging-error-in-image-stitching/3750 "2024-10-15T02:03:41Z")

</div>

I am working on an image stitching app. I have a camera fixed in the Z axis, so I only have movement in X or Y. The scale of the input image is always constant. I am using Template Matching (ORB) to get the matches and …

---

## [Number of keypoints does not match number of descriptors](https://forum.opencv.org/t/number-of-keypoints-does-not-match-number-of-descriptors/17866)

<div class="topic-metadata">

**Author:** [@farhadbat](https://forum.opencv.org/u/farhadbat)\
**Replies:** 1\
**Last updated:** [June 7, 2024, 5:16am UTC](https://forum.opencv.org/t/number-of-keypoints-does-not-match-number-of-descriptors/17866 "2024-06-07T05:16:03Z")

</div>

Hi everyone, I have a set of keypoints extracted with an aribirary keypoint detector (orb, random pixel, GFTT, etc). Now, I want to extract ORB descriptor to each keypoint. I used the following code for it; however, nu…

---

## [Is it possible to combine all of a video images to a large image?](https://forum.opencv.org/t/is-it-possible-to-combine-all-of-a-video-images-to-a-large-image/16568)

<div class="topic-metadata">

**Author:** [@jimmjimm11](https://forum.opencv.org/u/jimmjimm11)\
**Replies:** 2\
**Last updated:** [March 25, 2024, 7:28am UTC](https://forum.opencv.org/t/is-it-possible-to-combine-all-of-a-video-images-to-a-large-image/16568 "2024-03-25T07:28:19Z")

</div>

I try to record a video of a big item like wall surface, is it possible to combine all of video images into a big wall surface image?

---

## [Two image feature detect and match with some light reflect spots](https://forum.opencv.org/t/two-image-feature-detect-and-match-with-some-light-reflect-spots/16529)

<div class="topic-metadata">

**Author:** [@jimmjimm11](https://forum.opencv.org/u/jimmjimm11)\
**Replies:** 0\
**Last updated:** [February 21, 2024, 7:24am UTC](https://forum.opencv.org/t/two-image-feature-detect-and-match-with-some-light-reflect-spots/16529 "2024-02-21T07:24:58Z")

</div>

hi, I using a camera to capture a video of a item surface then combine video image into a huge 2D item surface image. when I try to detect feature of image by SIFT, soo many light reflect spots detect then makes match e…

---

## [BFMatcher limitation](https://forum.opencv.org/t/bfmatcher-limitation/16251)

<div class="topic-metadata">

**Author:** [@dima\_nozik](https://forum.opencv.org/u/dima_nozik)\
**Replies:** 0\
**Last updated:** [January 23, 2024, 5:07pm UTC](https://forum.opencv.org/t/bfmatcher-limitation/16251 "2024-01-23T17:07:50Z")

</div>

Hello , Why there is limitation on number of descriptors supported in BFMatcher::knnMatchImpl? According to code number of descriptors must be less 1 \<\< 18 . const int IMGIDX\_SHIFT = 18; const int IMGIDX\_ONE = (1 \<\< …

---

## [Non-planar object tracking](https://forum.opencv.org/t/non-planar-object-tracking/15835)

<div class="topic-metadata">

**Author:** [@bullseyepie](https://forum.opencv.org/u/bullseyepie)\
**Replies:** 2\
**Last updated:** [January 4, 2024, 5:07pm UTC](https://forum.opencv.org/t/non-planar-object-tracking/15835 "2024-01-04T17:07:57Z")

</div>

Hi everyone! I am currently working on a software to track real-world objects and place an equivalent 3D version on top of it. For the past 6 months i have extensively researched and developed multiple versions of the s…

---

## [Problems in aligning figures](https://forum.opencv.org/t/problems-in-aligning-figures/13581)

<div class="topic-metadata">

**Author:** [@serbring](https://forum.opencv.org/u/serbring)\
**Replies:** 0\
**Last updated:** [June 18, 2023, 1:01pm UTC](https://forum.opencv.org/t/problems-in-aligning-figures/13581 "2023-06-18T13:01:19Z")

</div>

Hi all, I have tried to follow this tutorial for aligning two figures but I get a wrong result. In particular, independently of the images I use for feeding the code, I always get a picture like that reported in the f…

---

## [OpenCV's cornerScore is different from FAST paper](https://forum.opencv.org/t/opencvs-cornerscore-is-different-from-fast-paper/13433)

<div class="topic-metadata">

**Author:** [@ShihanWang](https://forum.opencv.org/u/ShihanWang)\
**Replies:** 1\
**Last updated:** [June 12, 2023, 12:04pm UTC](https://forum.opencv.org/t/opencvs-cornerscore-is-different-from-fast-paper/13433 "2023-06-12T12:04:44Z")

</div>

Question About Fast9 Score v is the brightness of center pixel, v\_i is the i-th pixel brightness on circle. OpenCV use this code to calculate Fast9 Score. \\begin{align\*} & D = \\{v - v\_i\\}\_{i\\in\[0,24\]}\\\\ &\\text{for i=0…

---

## [FlannBasedMatcher raises (-215:Assertion failed) query.type() == type && indices.type() == CV\_32S && dists.type() == dtype in function 'runKnnSearch\_'](https://forum.opencv.org/t/flannbasedmatcher-raises-215-assertion-failed-query-type-type-indices-type-cv-32s-dists-type-dtype-in-function-runknnsearch/13407)

<div class="topic-metadata">

**Author:** [@Mina\_Samy](https://forum.opencv.org/u/Mina_Samy)\
**Replies:** 2\
**Last updated:** [June 6, 2023, 5:28am UTC](https://forum.opencv.org/t/flannbasedmatcher-raises-215-assertion-failed-query-type-type-indices-type-cv-32s-dists-type-dtype-in-function-runknnsearch/13407 "2023-06-06T05:28:26Z")

</div>

I am getting this error \`error: (-215:Assertion failed) query.type() == type && indices.type() == CV\_32S && dists.type() == dtype in function 'runKnnSearch\_'\` I am using Python 3.8, opencv-python==4.7.0 My task is to…

---

## ["OpenCV, overlaypatches , Dimensions of coords and onesTransposed matrices do not match!"](https://forum.opencv.org/t/opencv-overlaypatches-dimensions-of-coords-and-onestransposed-matrices-do-not-match/13366)

<div class="topic-metadata">

**Author:** [@Sandeep\_Kumar](https://forum.opencv.org/u/Sandeep_Kumar)\
**Replies:** 1\
**Last updated:** [May 31, 2023, 9:07am UTC](https://forum.opencv.org/t/opencv-overlaypatches-dimensions-of-coords-and-onestransposed-matrices-do-not-match/13366 "2023-05-31T09:07:58Z")

</div>

I’m encountering an OpenCV error : “Affine Transformation Matrix: \[0.9982519601601529, -0.0001474894468255113, 1661.997353717446; -0.000592161787642926, 0.9998475676606888, 447.0124025198956; -1.008188156421432e-06, …

---

## [Tracking a soccer field while camera pans/moves](https://forum.opencv.org/t/tracking-a-soccer-field-while-camera-pans-moves/12809)

<div class="topic-metadata">

**Author:** [@Chris\_Roughsedge](https://forum.opencv.org/u/Chris_Roughsedge)\
**Replies:** 0\
**Last updated:** [April 14, 2023, 12:30pm UTC](https://forum.opencv.org/t/tracking-a-soccer-field-while-camera-pans-moves/12809 "2023-04-14T12:30:24Z")

</div>

I’m currently using object detection to detect football players on a football pitch. From the x,y I receive I then want to transform them and use cv2.circle to plot them on a different image (a smaller birdseye view of t…

---

## [Calculate SIFT keypoints for all given points](https://forum.opencv.org/t/calculate-sift-keypoints-for-all-given-points/12514)

<div class="topic-metadata">

**Author:** [@apo1](https://forum.opencv.org/u/apo1)\
**Replies:** 4\
**Last updated:** [March 24, 2023, 4:04pm UTC](https://forum.opencv.org/t/calculate-sift-keypoints-for-all-given-points/12514 "2023-03-24T16:04:32Z")

</div>

I have a set of 2D points corresponding to the location of pixels in an image. I would like to compute SIFT keypoints and descriptors only for these points but I don’t find the appropriate methods in the online documenta…

---

## [Can I use USAC\_MAGSAC with cv2.findHomography?](https://forum.opencv.org/t/can-i-use-usac-magsac-with-cv2-findhomography/12383)

<div class="topic-metadata">

**Author:** [@lel](https://forum.opencv.org/u/lel)\
**Replies:** 1\
**Last updated:** [March 15, 2023, 11:47am UTC](https://forum.opencv.org/t/can-i-use-usac-magsac-with-cv2-findhomography/12383 "2023-03-15T11:47:58Z")

</div>

Hello, I would like to know if I could use the flag USAC\_MAGSAC in order to use MAGSAC++ for finding inliers. I know this is possible with the function cv2.findFundamentalMat but in the documentation there is no such fl…

---

## [Sift with Flann, results differs over iterations on same images](https://forum.opencv.org/t/sift-with-flann-results-differs-over-iterations-on-same-images/1955)

<div class="topic-metadata">

**Author:** [@daganm](https://forum.opencv.org/u/daganm)\
**Replies:** 9\
**Last updated:** [March 14, 2023, 5:24pm UTC](https://forum.opencv.org/t/sift-with-flann-results-differs-over-iterations-on-same-images/1955 "2023-03-14T17:24:05Z")

</div>

Hey ! I’m trying to create a Python script to find a homography in an image from a template but I’m stuck with a problem. If I run my function through a loop, results are evolving through time. It’s not completely rando…

---

## [How do I get DMatch coordinates in Java from Feature Detector?](https://forum.opencv.org/t/how-do-i-get-dmatch-coordinates-in-java-from-feature-detector/12342)

<div class="topic-metadata">

**Author:** [@Mich\_Po](https://forum.opencv.org/u/Mich_Po)\
**Replies:** 0\
**Last updated:** [March 13, 2023, 5:58pm UTC](https://forum.opencv.org/t/how-do-i-get-dmatch-coordinates-in-java-from-feature-detector/12342 "2023-03-13T17:58:53Z")

</div>

I need to get coordinates of each matched keypoint int helist of DMatch classes However, each DMatch only contains the distance in pixels between matched keypoints and no coordinates in either image 1 or image 2. How c…

---

## [OpenCV 4.7 Java DescriptorExtractor and DescriptorMatcher are missing, what do I use instead, no code in documenation](https://forum.opencv.org/t/opencv-4-7-java-descriptorextractor-and-descriptormatcher-are-missing-what-do-i-use-instead-no-code-in-documenation/12332)

<div class="topic-metadata">

**Author:** [@Mich\_Po](https://forum.opencv.org/u/Mich_Po)\
**Replies:** 2\
**Last updated:** [March 13, 2023, 5:56pm UTC](https://forum.opencv.org/t/opencv-4-7-java-descriptorextractor-and-descriptormatcher-are-missing-what-do-i-use-instead-no-code-in-documenation/12332 "2023-03-13T17:56:08Z")

</div>

I am trying to perform feature matching using this code from this question: OpenCV filtering ORB matches The ORB detection works, however DescriptorExtractor and DescriptorMatcher are no longer to be found in Feature2D …

---

## [Algorithm Behind Fast Feature detector](https://forum.opencv.org/t/algorithm-behind-fast-feature-detector/2911)

<div class="topic-metadata">

**Author:** [@sayan\_chaudhuri](https://forum.opencv.org/u/sayan_chaudhuri)\
**Replies:** 0\
**Last updated:** [April 22, 2021, 4:34am UTC](https://forum.opencv.org/t/algorithm-behind-fast-feature-detector/2911 "2021-04-22T04:34:37Z")

</div>

I am trying to implement the FASt feature detector from scratch for my college assignments. I am following the paper of Dr. Rosten and have used the segment test for corner detection criterion. But, I find that FAST feat…

---

## [Thread Safety for SURF.create(...)](https://forum.opencv.org/t/thread-safety-for-surf-create/12044)

<div class="topic-metadata">

**Author:** [@trausch](https://forum.opencv.org/u/trausch)\
**Replies:** 0\
**Last updated:** [February 19, 2023, 2:33pm UTC](https://forum.opencv.org/t/thread-safety-for-surf-create/12044 "2023-02-19T14:33:33Z")

</div>

I have noticed that with a high computing load (LoadAvarage from 30 and higher) the detector is created, but undefinable errors occur when I use it. All input parameters (of the detector at create and the images) are ide…

---

## [Generating descriptors from keypoints using SIFT](https://forum.opencv.org/t/generating-descriptors-from-keypoints-using-sift/12014)

<div class="topic-metadata">

**Author:** [@derekdoth](https://forum.opencv.org/u/derekdoth)\
**Replies:** 16\
**Last updated:** [February 16, 2023, 6:40pm UTC](https://forum.opencv.org/t/generating-descriptors-from-keypoints-using-sift/12014 "2023-02-16T18:40:54Z")

</div>

I’m attempting to generate descriptors from a set of keypoints for an image of interest using SIFT. Something like this: import cv2 as cv import numpy as np img = np.random.randn(1024,128).astype(np.uint8) keypoints=\[…

[Next page](https://forum.opencv.org/tag/features2d/68.md?match_all_tags=true&page=1&tags%5B%5D=features2d)
