Since you’re on a Linux box, I would highly recommend Google’s open source project ocropus. It’s not PHP, but I think it will be your best option. Of course you can call it from within PHP via exec. Its mature and has a lot of options. From the project site: The OCRopus engine is based … Read more
If anyone is looking into this, I’ve been trying different options and the following approach yields very good results. The following are the steps to get a working example: Add .NET Wrapper for tesseract to your project. It can be added via NuGet package Install-Package Tesseract(https://github.com/charlesw/tesseract). Go to the Downloads section of the official Tesseract … Read more
EDIT: I wrote a Python script for this. As your objective is blurring (for privacy protection), you basically need a high recall detector as a first step. Here’s how to go about doing this. The included code hints use OpenCV with Python. Convert to Grayscale. Apply Gaussian Blur. img = cv2.imread(‘input.jpg’,1) img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) … Read more
My friend Andrew and I implemented Stoke Width Transform (SWT) on a mobile phone during a class project at Cornell. Maybe you can get hint from the report. The report: http://www.cs.cornell.edu/courses/cs4670/2010fa/projects/final/results/group_of_arp86_sk2357/Writeup.pdf Our code: https://sites.google.com/site/roboticssaurav/strokewidthnokia Updated code: https://github.com/aperrau/DetectText
Use pytesseract.image_to_data() import pytesseract from pytesseract import Output import cv2 img = cv2.imread(‘image.jpg’) d = pytesseract.image_to_data(img, output_type=Output.DICT) n_boxes = len(d[‘level’]) for i in range(n_boxes): (x, y, w, h) = (d[‘left’][i], d[‘top’][i], d[‘width’][i], d[‘height’][i]) cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2) cv2.imshow(‘img’, img) cv2.waitKey(0) Among the data returned by pytesseract.image_to_data(): … Read more
I have played a bit with your input Normalization of lighting + dynamic range normalization helps a bit to obtain much better results but still far away from needed one. I would like to try sharpening of partial derivations to boost the letters from background and treshold out small bumps before integrate back and recolor … Read more
Since no one has posted a complete OpenCV solution, here’s a simple approach Obtain binary image. Load the image, convert to grayscale, and Otsu’s threshold Remove horizontal lines. We create a horizontal shaped kernel with cv2.getStructuringElement() then find contours and remove the lines with cv2.drawContours() Remove vertical lines. We do the same operation but with … Read more
In short, you would have to train the Tesseract engine to recognize the handwriting. Take a look at this link: Tesseract handwriting with dictionary training This is what the linked post says: It’s possible to train tesseract to recognize handwriting. Here are the instructions: https://tesseract-ocr.github.io/tessdoc/Training-Tesseract But don’t expect very good results. Academics have typically gotten … Read more
Like you I also faced many problems implementing OCR in Android, but after much Googling I found the solution, and it surely is the best example of OCR. Let me explain using step-by-step guidance. First, download the source code from https://github.com/rmtheis/tess-two. Import all three projects. After importing you will get an error. To solve the … Read more
On recent versions of Windows, the recommended way to gather information from one application to another (if you don’t own the targeted application of course) is to use the UI Automation technology. Wikipedia is pretty good for more information on this: Microsoft UI Automation Basically, UI automation will use all necessary means to gather what … Read more