Trung Hoang truhoada

Using Python 3 + Google Cloud Vision API's OCR to extract text from photos and scanned documents

Just a quickie test in Python 3 (using Requests) to see if Google Cloud Vision can be used to effectively OCR a scanned data table and preserve its structure, in the way that products such as ABBYY FineReader can OCR an image and provide Excel-ready output.

The short answer: No. While Cloud Vision provides bounding polygon coordinates in its output, it doesn't provide it at the word or region level, which would be needed to then calculate the data delimiters.

On the other hand, the OCR quality is pretty good, if you just need to identify text anywhere in an image, without regards to its physical coordinates. I've included two examples:

####### 1. A low-resolution photo of road signs

	URL Schemes

	Apple

	Apple Music — music://geo.itunes.apple.com/us/albums/<albumID>
	– music://geo.itunes.apple.com/us/artists/<artistID>

	Apple News — applenews://
	App Store — itms-apps://itunes.apple.com/app/<appID>
	Apple TV — videos://

	import Foundation

	extension Data {
	var prettyPrintedJSONString: NSString? { /// NSString gives us a nice sanitized debugDescription
	guard let object = try? JSONSerialization.jsonObject(with: self, options: []),
	let data = try? JSONSerialization.data(withJSONObject: object, options: [.prettyPrinted]),
	let prettyPrintedString = NSString(data: data, encoding: String.Encoding.utf8.rawValue) else { return nil }

	return prettyPrintedString
	}

	import Foundation
	import UIKit

	extension UIColor {
	convenience init(hexString:String) {
	let hexString:NSString = hexString.stringByTrimmingCharactersInSet(NSCharacterSet.whitespaceAndNewlineCharacterSet())
	let scanner = NSScanner(string: hexString)

	if (hexString.hasPrefix("#")) {
	scanner.scanLocation = 1