johncordeiro's profile - activity

I'm doing exactly in this way, and the results are these in question.

I followed your advice and I edited my question. My results is getting better with SURF than SIFT. It didn't solve the problem yet.

I am trying to detect brands in pictures but I'm having some problems.

I did the cascade training with 500 positives samples and 1440 negatives samples, but I'm getting a lot of bad results. The cascade classifier detects the brand and further a lot of things that isn't the brand.

EDIT:

I tried to use SURF features to eliminate these bad results and look that it isn't work:

The same result occured with a image that is not my brand:

Look the detections:

My question is: How do I eliminate the bad results and just stay with the brand that I am looking for ? What I'm doing wrong ?

I trained a cascade classifier with de following arguments:

Positive Images: 500 Negative Images: 1440

Samples Creation:

perl bin/createsamples.pl positives negatives samples 1000 "opencv_createsamples -bgcolor 0 -bgthresh 0 -maxxangle 1.1 -maxyangle 1.1 maxzangle 0.5 -maxidev 40 -w 60 -h 25"

Train Cascade:

opencv_traincascade -data classifier -vec samples.vec -bg negatives -numStages 20 -minHitRate 0.999 -maxFalseAlarmRate 0.5 -numPos 500 -numNeg 1440 -w 60 -h 25 -mode ALL -precalcValBufSize 768 -precalcIdxBufSize 768 -mem 3072 -baseFormatSave

I generated de cascade.xml, and I'm detecting in a group of images using OpenCV for Java with:

objectDetector.detectMultiScale(image, objectDetections, 1.2, 1, Objdetect.CASCADE_FIND_BIGGEST_OBJECT | Objdetect.CASCADE_DO_ROUGH_SEARCH, new Size(), new Size());

My main goal is detect if there is or not the cascade classifier in searched images. So, finally my questions:

1 - What am I doing wrong ? 2 - Is there a good way to get the best detection results ?

It was very helpful for me, thanks!

Hi, I want to know where I must to start studying OpenCV Algorithms internally. I have a good experience using OpenCV Library, but I want more.

I know about the docs, but I find it a little confuse when explaining about math inside the Algorithms. I would like to know if you know books or some good content explaining OpenCV internally.

Thanks!

I'm collecting a lot of positive images to train the cascade classifier and so I have some doubts:

1 - I'm trying to recognize object that has 2 different formats, so it's better create 2 cascade's xml to each different format or 1 cascade's xml with a lot of 2 images formats ?

2 - The color of positive samples can influence in the object detection ? Is it better that the positive samples are in greyscale ?

Thanks for your help !