I'm working on an android project that requires Real time Image Recognition feature. I'm a newbie and don't have too much knowledge of image processing. I have to detect only one image by the application, that is nothing more than a logo. Logo is in the shape of circle.
Please suggest appropriate solution.
Thank you.
I recommend to use OpenCV library. It will allow you to learn your application to recognize diffrent things. For example I've made my application to recognize cars based on the size and shape of the object.
there is a lot of examples for OpenCV how to recognize a logo or similar things
for detection of specific object you can follow some basic techniques of object localization such as Normalized Cross-correlation in other words its also known as template matching, you have to prepare a template of your log and just use it as a convolution mask, and convolve your input image with this mask, ideally at the location of the desired object, response of convolution will quite high, so you can further fine tune the process to localize your object.
For how to use template matching in opencv you can refer to its document page http://docs.opencv.org/doc/tutorials/imgproc/histograms/template_matching/template_matching.html
OR
As you have mentioned in your question, that your region of interest is circular in shape, you can use some shape measures after initial segmentation of your image.
Related
I'm developing an Android application to match two images using ORB feature detection .
The processing and matching logic is called in java using JNI functions.
The problem is that the feature detections works well for some images, but fails in some images and some cases.
Here is an example of images that fails in some unknown conditions
After some thoughts and discussions, I figured out that the problem is that the problem is the lack of features that's why the program fails. Someone in the opencv community tried this image and it gave him 60 keypoints which all of them doesn't survive the RobustMatcher tests.
So I need to enhance to features in this image in order to make the matching work.
In addition to equalizeHist, what can I do ?
I hope you can help me with some suggestions and maybe some examples guys.
One way is to enhance the edges of the image. Do a Laplacian filter for example and multiply the result to the original image. This job makes the features (edge) more salient. Of course before everything convert the image to a float type and at the end, normalize your image.
I must create an Android app that recognizes some objects from the camera (car steering wheel, car wheel). I tried with Haar classifier but without success and I'm running out of time (it's a school project). So I decided to look for another way. I found some other methods for my goal - ORB. I found what should I do in this answer. My problem is that things are messed up in my head. Can you give me a step-by-step answer of what to do to implement the answer from the question in the link I gave:
From extracting the feature points to training the KD tree and using it for every frame from the camera.
Bonus questions:
Can you give a definition of feature point? It's something I couldn't exactly understand.
Will be the detecting slow using ORB? I know OpenCV can be used in native android, wouldn't that make the things faster?
I need to create this app as soon as possible. Please help!
I am currently developing a similar application. I would recommend getting something working with a single reference image first for a couple of reasons:
It's easier to do and understand if you're just starting out, and you can change it later.
For android applications you have limited processing capabilities so more images = lower fps.
You should have a look at the OpenCV tutorials which are quite helpful. Once you go through the “OpenCV for Android SDK” section and understand the three tutorials you can pretty easily add in functionality that will allow you to analyse the video feed.
The basic logic path I'd recommend following when making the app is:
Read in the reference image.
Create and use your FeatureDetector, DescriptorExtractor and DescriptorMatcher.
Use the above to detect keypoints and then descrive keypoints (the first two, don't forget to convert it to a mat and then to greyscale).
Every time you get a frame from your camera repeat step 3. on it and then compare the keypoints in the images (with the third part of 2.).
Use the result to determine if there is a match (if there is then draw a box around it or something).
Get a new frame.
Try making it to work for a single object and then add in others later. Another thing you could add is a screen at the start to allow users to pick what they want to search for.
Also ORB is reasonably fast, especially compared to SIFT and SURF. I get about 3fps on a HTC One with a single reference image.
I have successfully integrated tesseract into my android app and it reads whatever the image that I capture but with very less accuracy. But most of the time I do not get the correct text after capturing because some text around the region of interest is also getting captured.
All I want to read is all text from a rectangular area, accurately, without capturing the edges of the rectangle. I have done some research and posted on stackoverflow about this two times, but still did not get a happy result!
Following are the 2 posts that I made:
https://stackoverflow.com/questions/16663504/extract-text-from-a-captured-image?noredirect=1#comment23973954_16663504
Extracting information from captured image in android
I am not sure whether to go ahead with tesseract or use openCV
Including the many links and answers from others, I think it's good to take a step back and note that there are actually two fundamental steps to optical character recognition (OCR):
Text Detection: This is the title and focus of your question, and it is concerned with localizing regions in an image that contain text.
Text Recognition: This is where the actual recognition happens, where the localized image regions from detection get segmented character-by-character and classified. This is also where tools like Tesseract come into play.
Now, there are also two general settings in which OCR is applied:
Controlled: These are images taken from a scanner or similar in-nature where the target is a document and things like perspective, scale, font, orientation, background consistency, etc are pretty docile.
Uncontrolled/Scene: These are the more natural and in-the-wild photos, e.g. those taken from a camera, where you are trying to recognize a street sign, shop name, etc.
Tesseract as-is is most applicable to the "controlled" setting. And in general, but for scene OCR especially, "re-training" Tesseract will not directly improve detection, but may improve recognition.
If you are looking to improve scene text detection, see this work; and if you are looking at improving scene text recognition, see this work. Since you asked about detection, the detection reference uses maximally stable extremal regions (MSER), which has a plethora of implementation resources, e.g. see here.
There's also a text detection project here specifically for Android too:
https://github.com/dreamdragon/text-detection
As many have noted, keep in mind that recognition is still an open research challenge.
The solution to improving the OCR output is to
either use more training data to train it better
filter it's input using some Linear Filter (grayscaling, high-contrasting, blurring)
In the chat we posted a number of links describing filtering techniques used in OCRing, but sample code wasn't posted.
Some of the links posted were
Improving input for OCR
How to train Tesseract
Text enhancement using asymmetric filters <-- this paper is easily found on google, and should be read fully as it quite clearly illustrates and demonstrates necessary steps before OCR-processing the image.
OCR Classification
I am developing a currency identification system for blind people. I need to check if the full currency note has been captured so I used square detection for that. It is currently working when the background is pure black or white, but not when the background is more advanced. What techniques can I use to solve this problem?
I am using OpenCV as my image processing framework. Can I use convolution? How?
need enhancement for square detection.
Result image of my code:
I am not sure whether rectangle detection is the best solution for what you want to do.
It will only work efficiently if the picture is taken right up from the money, and as you say will not be robust to cluttered backgrounds.
Is there a precise reason for not going to a direct pattern recognition system ?
I'd start with a picture of my currency and try to perform object recognition with it.
You will find loads of tutorials that can help you on the web, like for bottles or for bowls.
You might have a lot of possibilities, due to the number of currencies but you know it to be a finite number at least.
I'm trying to create a camera activity for taking photos to be OCR'd. Here's what I wish to accomplish:
A resizable box in the middle of the camera preview to indicate which particular area will be created into a Bitmap and processed by the OCR engine.
Continuous autofocus (done)
I'm using tesseract btw.
If anyone would care to point me to some reference / examples / tutorials, that would be great.
There's a viewfinder rectangle here:
https://github.com/rmtheis/android-ocr/blob/master/android/src/edu/sfsu/cs/orange/ocr/CaptureActivity.java
I've been doing something similar. Right now, I'm just sending the whole photo to a webservice and processing it with OCRfeeder, which will perform segmentation on the image and send each part with text in it to tesseract. I've been getting much better accuracy that way. In addition, you might want to perform some preprocessing to clean up the image first.
There can be two general approaches.
You can resize the image before sending it to OCR engine. Keep in mind that Tesseract engine you use has some kind of feature - it requires some space between characters and image borders, sometimes more than expected.
The second approach is to use field-level recognition, when you specify coordinates of the text block and send the full image to OCR engine. Have a look at http://www.ocrsdk.com, it's a cloud OCR SDK with web api recently launched by ABBYY, it's in beta, so for now it's free to use. It has a field level recognition methods and Android code samples. I work # ABBYY and can provide additional info on our products if necessary