Rank: 9 based on 1583 downloads (last 30 days) and 64 files submitted
photo

Brett Shoelson

E-mail
Company/University
MathWorks
Lat/Long
38.87422943115234, -77.1302490234375

Personal Profile:

I'm a biomedical engineer by training, but I love MATLAB and have worked as a Principal Application Engineer for MathWorks since 2005. I also co-write the Pick of the Week blog, with my friend Jiro.

Professional Interests:
(medical) image processing

 

Watch this Author's files

 

Files Posted by Brett View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
08 Jul 2013 Screenshot ImadjustGUI Launches an interactive GUI for modifying the parameters of IMADJUST. Author: Brett Shoelson gui, display, annotation, image intensity adjus..., imadjust, enhance 152 4
  • 4.5
4.5 | 2 ratings
10 Jun 2013 Screenshot clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson cluster, kmeans, data analysis, group data, number of clusters, sort data 79 8
  • 4.33333
4.3 | 6 ratings
23 May 2013 Screenshot edfRead A simple file reader for European Data Formatted (EDF-) files. Author: Brett Shoelson edf european data for... 128 20
  • 4.875
4.9 | 9 ratings
13 May 2013 Screenshot FindCirclesGUI Launches a GUI environment for the detection of circles in an image. Author: Brett Shoelson circle detection, imfindcircles, find circles, circular hough transf..., detect circles 64 3
  • 5.0
5.0 | 2 ratings
13 May 2013 Screenshot sliderPanel A new UICONTROL object with a slider as a child of a uipanel, with auto-linked edit box and labels. Author: Brett Shoelson example, gui tools, uicontrol slider pane... 29 3
  • 5.0
5.0 | 2 ratings
Comments and Ratings by Brett View all
Updated File Comments Rating
29 Jul 2013 Cascade Training GUI: Specify Ground Truth Interactive GUI for managing the selection and positioning of rectangular ROIs in a list of images. Author: Brett Shoelson

Ali, there are actually 3 features with which you can train the detector: HOG, HAAR, or LBP. I don't have enough experience creating detectors to tell you which will work best, and under what conditions. We chose HOG as the default, thinking that it would be a general-purpose feature, but I would recommend reading the references in the doc for trainCascadeObjectDetector for more insight.

"False positive rate" is an indication of the likelihood of falsely detecting an object; "false negative rate" indicates the likelihood of missing an object that really does exist.

In the training session, the OVERALL target true positive rate of the resulting detector is TPR^NumCascadeStages, where TPR is the per-stage true positive rate. Increasing this value may increase the number of correct detections, at the cost of increased training time. (Default: 0.995).

And:

The overall target false alarm rate of the resulting detector is FAR^NumCascadeStages, where FAR is the per-stage False Alarm Rate. Lower value
of FalseAlarmRate may result in fewer false detections, but in longer training and detection times. (Default: 0.5).

Once you've selected a detector--one you created, or one we supplied--you can tally the number of positives by querying the number of bounding boxes returned:

detector = vision.CascadeObjectDetector(detectorRequested);
bbox = step(detector, img); %detect object
nDetected = size(bbox,1);

This is done for you within CascadeTrainGUI!

HTH,
Brett

16 Jul 2013 XLSAPPEND Append data to the next-available row of an existing Excel file with a single call to ActiveX. Author: Brett Shoelson

Javier,
The first time you call the function, make sure that you have specified the filename properly, including the exact extension. ("XLS," "XLSX," ...). If appendToXLS doesn't find the Excel file, it will create a CSV-formatted one and operate on it. If that doesn't address your question, please feel free to contact me directly. Perhaps I could figure out specifics if I had your file to work with.
Cheers,
Brett

12 Jul 2013 clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson

@Hoi,
Hmmm. Well, that's clearly a "bug" in the sense that I could have dealt with that case more gracefully, but then--well, let's just say that I never anticipated that anyone would try to cluster a single scalar. :)

25 Jun 2013 clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson

Han, did you find some problem with the submission that led you to rate this so poorly? Do you have any comments to share that might help me understand why it merits a two-star rating?
Thanks,
Brett

24 Jun 2013 Cascade Training GUI: Specify Ground Truth Interactive GUI for managing the selection and positioning of rectangular ROIs in a list of images. Author: Brett Shoelson

@Ali:
I'm sorry, Ali. I don't really know what your question is. Are you concerned because your results aren't as good as you'd like unless your images are similar in size to the negative images you used? (One thing that occurs to me immediately is that 60 positive images might be too few to expect or get really good results.)
Cheers,
Brett

Comments and Ratings on Brett's Files View all
Updated File Comment by Comments Rating
30 Jul 2013 Cascade Training GUI: Specify Ground Truth Interactive GUI for managing the selection and positioning of rectangular ROIs in a list of images. Author: Brett Shoelson M, Ali

Thank you.

29 Jul 2013 Cascade Training GUI: Specify Ground Truth Interactive GUI for managing the selection and positioning of rectangular ROIs in a list of images. Author: Brett Shoelson Shoelson, Brett

Ali, there are actually 3 features with which you can train the detector: HOG, HAAR, or LBP. I don't have enough experience creating detectors to tell you which will work best, and under what conditions. We chose HOG as the default, thinking that it would be a general-purpose feature, but I would recommend reading the references in the doc for trainCascadeObjectDetector for more insight.

"False positive rate" is an indication of the likelihood of falsely detecting an object; "false negative rate" indicates the likelihood of missing an object that really does exist.

In the training session, the OVERALL target true positive rate of the resulting detector is TPR^NumCascadeStages, where TPR is the per-stage true positive rate. Increasing this value may increase the number of correct detections, at the cost of increased training time. (Default: 0.995).

And:

The overall target false alarm rate of the resulting detector is FAR^NumCascadeStages, where FAR is the per-stage False Alarm Rate. Lower value
of FalseAlarmRate may result in fewer false detections, but in longer training and detection times. (Default: 0.5).

Once you've selected a detector--one you created, or one we supplied--you can tally the number of positives by querying the number of bounding boxes returned:

detector = vision.CascadeObjectDetector(detectorRequested);
bbox = step(detector, img); %detect object
nDetected = size(bbox,1);

This is done for you within CascadeTrainGUI!

HTH,
Brett

23 Jul 2013 clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson Wong, Hoi

Haha. My data set is supposed to give me an array of numbers, but sometimes I got a singleton. That's how I found out. By the way, excellent submission!

23 Jul 2013 clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson Wong, Hoi

20 Jul 2013 clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson Xiong

thank you for your submission!

Top Tags Applied by Brett
utilities, gui, directories, files, image processing
Files Tagged by Brett View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
08 Jul 2013 Screenshot ImadjustGUI Launches an interactive GUI for modifying the parameters of IMADJUST. Author: Brett Shoelson gui, display, annotation, image intensity adjus..., imadjust, enhance 152 4
  • 4.5
4.5 | 2 ratings
10 Jun 2013 Screenshot clusterData Clusters an MxN array of data into an unspecified number (P) of bins. Author: Brett Shoelson cluster, kmeans, data analysis, group data, number of clusters, sort data 79 8
  • 4.33333
4.3 | 6 ratings
23 May 2013 Screenshot edfRead A simple file reader for European Data Formatted (EDF-) files. Author: Brett Shoelson edf european data for... 128 20
  • 4.875
4.9 | 9 ratings
13 May 2013 Screenshot FindCirclesGUI Launches a GUI environment for the detection of circles in an image. Author: Brett Shoelson circle detection, imfindcircles, find circles, circular hough transf..., detect circles 64 3
  • 5.0
5.0 | 2 ratings
13 May 2013 Screenshot sliderPanel A new UICONTROL object with a slider as a child of a uipanel, with auto-linked edit box and labels. Author: Brett Shoelson example, gui tools, uicontrol slider pane... 29 3
  • 5.0
5.0 | 2 ratings

Contact us