Ask Your Question

procton's profile - activity

2019-04-10 03:44:04 -0500 commented answer Use of LBPHFaceRecognizer (python)

Thank you !

2019-04-10 03:43:40 -0500 marked best answer Use of LBPHFaceRecognizer (python)

I am testing the python version of LBPHFaceRecognizer and results seems not bad, but I noted something strange. Making the prediction, let's say:

label= face_recognizer.predict(gray)
print('prediction', label)

I see that label is a tuple with 2 values, the first is the prediction, the second I guess is the probability. Now when probability is low the prediction is fine, while when it is high, I have false positive.

Maybe this value is not the probability, so the question is, what is its real meaning ? Thanks

2019-04-10 02:54:13 -0500 asked a question Use of LBPHFaceRecognizer (python)

Use of LBPHFaceRecognizer (python) I am testing the python version of LBPHFaceRecognizer and results seems not bad, but

2019-01-30 01:17:02 -0500 received badge  Nice Question (source)
2018-09-14 09:46:02 -0500 received badge  Enlightened (source)
2018-09-14 09:46:02 -0500 received badge  Good Answer (source)
2018-07-04 14:53:23 -0500 edited question Manage mp4 video

Manage mp4 video Hi Community, I am afraid to know the answer, anyway this is may question: is it possible to load a mp4

2018-07-04 14:30:04 -0500 asked a question Manage mp4 video

Manage mp4 video Hi Community, I am afraid to know the answer, anyway this is may question: is it possible to load a mp4

2018-06-06 14:11:01 -0500 answered a question I want to extract the biggest connected element.

You shoul do binary thresholding and then find contours. The biggest should approximate the elephant.

2018-03-01 05:56:27 -0500 commented question detection of paint defect in car door handles

Well, I think that if someone posts a question on a technical forum as it is, he deserves something different than 'try

2018-02-22 13:54:45 -0500 commented question How detect very small blobs

@Telegramm I did some experiments with Laplacian, but I am not sure of what could be good parameters in my scenario. Mor

2018-02-20 13:08:12 -0500 commented question How detect very small blobs

Good catch @Balaji !!!, I also noticed the shift that you pointed out. My goal is to detect small blobs. Till now I was

2018-02-20 00:40:24 -0500 edited question How detect very small blobs

How detect very small blobs I need to find differences on the following two images. The first one has very small blobs (

2018-02-20 00:33:15 -0500 commented question How detect very small blobs

I updated my post with color images

2018-02-20 00:32:29 -0500 edited question How detect very small blobs

How detect very small blobs I need to find differences on the following two images. The first one has very small blobs (

2018-02-19 16:17:52 -0500 edited question How detect very small blobs

How detect very small blobs I need to find differences on the following two images. The first one has very small blobs (

2018-02-19 16:17:03 -0500 asked a question How detect very small blobs

How detect very small blobs I need to find differences on the following two images. The first one has very small blobs (

2018-02-02 18:37:15 -0500 answered a question What are m00, m10, m01 ect

please, take a look here, you will find a formal definition with examples. https://docs.opencv.org/2.4/modules/imgproc/d

2018-01-18 06:52:45 -0500 commented question Bottle Detection

post a download link from gdrive or similar

2018-01-17 03:52:34 -0500 commented answer Any tool for cropping positive samples

Regarding image crop or anything else?

2018-01-15 09:33:53 -0500 edited answer Any tool for cropping positive samples

Take a look at https://www.cs.auckland.ac.nz/~m.rezaei/Tutorials/Creating_a_Cascade_of_Haar-Like_Classifiers_Step_by_Ste

2018-01-15 09:33:12 -0500 answered a question Any tool for cropping positive samples

Take a look at https://www.cs.auckland.ac.nz/~m.rezaei/Tutorials/Creating_a_Cascade_of_Haar-Like_Classifiers_Step_by_Ste

2018-01-06 06:01:49 -0500 commented question Detecting multiple instances of an object

Try a look at https://docs.opencv.org/2.4/doc/tutorials/features2d/feature_homography/feature_homography.html#feature-ho

2017-12-22 06:11:14 -0500 marked best answer Lines detection

Hi All, the following is a quite difficult task so any kind of help, even simple, will be much appreciated.

After color segmentation I generated the following image

image description

I need to get lines that approximates white areas (roads), as shown in the following hand-made image

image description

Using probabilistic HoughLines with following parameters (image and lines are Mat instances):

Imgproc.HoughLinesP(image, lines, 2, Math.PI /180, 200, 100, 5);

I get the following result:

image description

I tried several combinations of parameters and shown result seems to be the best that I can achieve.

My questions:

  1. Overall, what do you think of this approach ?

  2. Any idea on how to select 'strongest' lines after HoughLines transform ? Is there any way to cluster every bundle of lines into a single significative line ?

Thanks

2017-12-22 06:04:30 -0500 answered a question Particle analyze in binary image

You can do the following: find contours on this image, which is already binarized with black background so it's ready

2017-12-22 01:40:15 -0500 commented answer Lines detection

Yes, but I always use Java :) even if it is the worst choice with Opencv

2017-12-21 16:57:19 -0500 received badge  Nice Answer (source)
2017-12-21 14:03:07 -0500 received badge  Self-Learner (source)
2017-12-21 13:50:47 -0500 edited answer Lines detection

Well, after hard work I have a solution. I look forward your inputs, ideas and improvements. First, I did some noise re

2017-12-21 13:44:04 -0500 answered a question Lines detection

Well, after hard work I have a solution. I look forward your inputs, ideas and improvments. First, I did some noise rem

2017-12-21 11:27:58 -0500 commented question Lines detection

I tried dbscan using Apache Maths. I am able to cluster centers of Houghlines, but I am not able to return back to lines

2017-12-21 11:22:55 -0500 commented question Lines detection

thanks moHe. Do you have concrete example ?

2017-12-18 15:36:06 -0500 commented question Lines detection

there is an additional complexity thay I omitted. I have a set of images (the one I posted is just an example), each cou

2017-12-18 15:06:14 -0500 commented question Lines detection

There should be 14 centers, since there are 14 segments. The main problem is that I don't know how to deal with object l

2017-12-18 12:36:55 -0500 answered a question can anybody give me a link of tutorials of using opencv with android studio?

This may be useful: http://blog.codeonion.com/2015/11/25/creating-a-new-opencv-project-in-android-studio/

2017-12-18 12:34:31 -0500 answered a question How to work with OPENCV4ANDROID- in android studio

You may try the following tutorial http://blog.codeonion.com/2015/11/25/creating-a-new-opencv-project-in-android-studio/

2017-12-18 11:58:34 -0500 asked a question Lines detection

Lines detection Hi All, the following is a quite difficult task so any kind of help, even simple, will be much appreciat

2017-12-09 04:10:07 -0500 commented question Road detection and machine learning

OK, this answer solves almost all questions. So which should be the correct approach ? Maybe random forest using ground

2017-12-09 03:44:37 -0500 asked a question Road detection and machine learning

Road detection and machine learning My goal is to detect roads from high resolution aerial images. I would like to adopt

2017-12-06 10:07:17 -0500 received badge  Nice Answer (source)
2017-12-05 15:05:05 -0500 commented question Removal Greenish Shadows from Background

have you tried simple edge detection ? I think that some blurring (GaussianBlur), threshold and findContours should be e

2017-12-05 14:54:31 -0500 marked best answer How manage RGB Pan sharpened image

I have a high resolution (about 30 cm) RGB pan sharpened image (3 channels, 16x3 bit). My need is to make some edge detection aimed to segment human artifacts.

I load the image with Mat rgbPanSharpen = Imgcodecs.imread(rgbPanSharpenImage, Imgcodecs.IMREAD_UNCHANGED); but after that I have some doubts on how proceed.

I think I could work on single channels (using Core.split) having single 16 bit images, may be also converting to 8 bit, but I am afraid this approach is lossy.

Which should be the correct approach to make edge detection on such kind of images ? (I don't ask for code, just the correct logical approch to follow)

This a sample image

2017-12-05 14:54:31 -0500 received badge  Scholar (source)
2017-12-05 13:14:06 -0500 received badge  Self-Learner (source)