2018-02-14 04:14:27 -0600 | received badge | ● Enthusiast |
2018-02-12 09:23:46 -0600 | commented question | K-Nearest for handwritten letters My colleague has adapted it for HOG+SVM already, but I need to do it with KNN. :( |
2018-02-12 07:21:21 -0600 | edited question | K-Nearest for handwritten letters K-Nearest for handwritten letters I'm working with this data set, which Is slightly unbalanced across the letter classes |
2018-02-12 06:46:55 -0600 | asked a question | K-Nearest for handwritten letters K-Nearest for handwritten letters I'm working with this data set, which Is slightly unbalanced across the letter classes |
2018-02-12 06:44:12 -0600 | edited question | Nearest for handwritten letters Nearest for handwritten letters I'm working with this data set, which Is slightly unbalanced across the letter classes: |
2018-02-12 06:43:11 -0600 | edited question | Nearest for handwritten letters Nearest for handwritten letters I'm working with this data set, which Is slightly unbalanced across the letter classes: |
2018-02-12 06:42:04 -0600 | asked a question | Nearest for handwritten letters Nearest for handwritten letters I'm working with this data set, which Is slightly unbalanced across the letter classes: |
2016-11-04 06:52:01 -0600 | commented question | Subtract operation creates result with noise Thanks a lot for testing this out. The input data is just getting passed into the code that calls opencv from a view controller in an iOS app that loads the input images from the device's filesystem. And then I return the results (result, regionmatchingTemplate Mat instances) back up for display to the user. Just curious, which platform did you test this on? I may switch to a different reference platform, as I've definitely had issues on iOS. |
2016-11-03 10:39:14 -0600 | received badge | ● Editor (source) |
2016-11-03 10:29:11 -0600 | asked a question | Subtract operation creates result with noise Hi all, I'm trying to subtract two Mat instances to obtain a result that represents a person's signature. Unfortunately, my resulting Mat seems to show noise along the top edge. Here are the source images and output: The templateToMatch: C:\fakepath\template.png The original source from which the ROI will be extracted, referred to as "formImage" in the code:C:\fakepath\sep-ira-completed-handwritten-p5.png The ROI extracted via matchTemplate and Rect:C:\fakepath\signed.png The result of running subtract on the template and extracted ROI: C:\fakepath\difference.png As you can see, difference.png shows noise creeping down over the actual signature. Can someone have a look at my implementation and tell me what I may be doing wrong? Is there a way I can mitigate this, if not avoid it altogether? Here's where the subtraction takes place: Here's the getSignatureRegion that uses template matching to extract the potentially signed region in the source doc: Here's another example where this time, I used a template to extract a region from an empty form where no signature is present in the ROI. I would expect the subtract operation to result in a nearly empty Mat, but again there is "noise" along the bottom edge of the result: Unsigned form: C:\fakepath\rollover-signature-page-unsigned.jpg Template to find ROI of empty signature box: C:\fakepath\template.png ROI that was extracted from unsigned form: C:\fakepath\signed.png And finally, the subtract result with a weird black rectangled along bottom edge: C:\fakepath\difference.png |