swift - Why does tesseract OCR recognition quality degrade when run on iOS device versus Simulator -


simply put, near perfect text recognition tesseractocr when run code on iphone 6 simulator, recognition degrades substantially when run same code on actual iphone 6. on device, of degradation occurs near non-text artifacts (e.g., lines). in case, there consistent single character recognition error same alphanumeric string. of text bold, not. there several font sizes.

so question is: know why recognition quality better on simulator , can if improve recognition on iphone?

i have built simple ios test app translates image text using tesseractocrios. eventually, images come device camera, use test image of invoice formatted jpeg. process looks following:

jpeg->uiimage->nsdata->uiimage->tesseract

i'm assuming process lossless. intermediate translation nsdata part of overall process because device camera yields image data , photo library stores image data—the use of jpeg test image @ point makes process little convoluted.

to install tesseractocrios followed instructions on wiki. installed tesseractocrios 4.0.0 using following pod file.

platform :ios, '9.0' use_frameworks! workspace 'documentcapturev2' xcodeproj 'documentcapturedemo/documentcapturedemo.xcodeproj/'  target 'documentcapturedemo'    pod 'tesseractocrios', '4.0.0' end  target 'documentcapturedemotests'    pod 'tesseractocrios', '4.0.0' end  target 'documentcapturedemouitests'    pod 'tesseractocrios', '4.0.0' end  post_install |installer|    installer.pods_project.targets.each |target|        target.build_configurations.each |config|            config.build_settings['enable_bitcode'] = 'no'        end    end end

the post install bit added make work on iphone 6 device. absent bit of pod file stuff (it took searching find bit of magic), link fails when trying run on device (can't use weak library , enable bitcode).

the code use recognize text below (basically example code on github). did change recognition time 1 10 thinking iphone might need more time. didn't make difference.

func updatepagetext(page: page, image: uiimage?) {     if image != nil {         // create new `g8recognitionoperation` perform ocr asynchronously         // assumed there .traineddata file language pack         // want tesseract use in "tessdata" folder in root of         // project , "tessdata" folder referenced folder , not         // symbolic group in project         let operation = g8recognitionoperation(language: "eng")          // use original tesseract engine mode in performing recognition         // (see g8constants.h) other engine mode options         operation.tesseract.enginemode = g8ocrenginemode.tesseractonly;          // let tesseract automatically segment page blocks of text         // based on analysis (see g8constants.h) other page segmentation         // mode options         operation.tesseract.pagesegmentationmode = g8pagesegmentationmode.autoonly;          // optionally limit time tesseract should spend performing         // recognition         //operation.tesseract.maximumrecognitiontime = 10.0;          // set delegate recognition class         // (see `progressimagerecognitionfortesseract` ,         // `shouldcancelimagerecognitionfortesseract` methods below)         operation.delegate = self;          // optionally limit tesseract's recognition following whitelist         // , blacklist of characters         //operation.tesseract.charwhitelist = @"01234";         //operation.tesseract.charblacklist = @"56789";          // set image on tesseract should perform recognition         operation.tesseract.image = image;          // optionally limit region in image on tesseract should         // perform recognition rectangle         //operation.tesseract.rect = cgrectmake(20, 20, 100, 100);          // specify function block should executed when tesseract         // finishes performing recognition on image          operation.recognitioncompleteblock = {(tesseract: g8tesseract!)->void in             page.text = tesseract.recognizedtext.stringbytrimmingcharactersinset(nscharacterset.whitespaceandnewlinecharacterset())             page.save()         }          // finally, add recognition operation queue         operationqueue.addoperation(operation);     }  }

i assuming uiimage pass updatepagetext complete (i.e., not still loading). have looked @ thresholdedimage on iphone 6 , there nothing odd can see. there's virtually no documentation on tesseract configuration haven't tried there.


Comments

Post a Comment

Popular posts from this blog

java - pagination of xlsx file to XSSFworkbook using apache POI -

right in code, reading xlsx file, xssfworkbook, , writing database. but, when size of xlsx file increases, causes outofmemory error. can not increase server size, or divide xlsx file pieces. tried loading workbook using file (instead of inputstream), didn't either. i looking way read 10k rows @ time (instead of entire file @ once) , iteratively write workbook , database. is there way apache poi? poi contains called "eventmodel" designed purpose. it's mentioned in faq : the ss eventmodel package api reading excel files without loading whole spreadsheet memory. require more knowledge on part of user, reduces memory consumption more tenfold. based on awt event model in combination sax. if need read-only access, best way it. however, may want double check first if issue somewhere else. check out this item : i think poi using memory! can do? 1 comes quite lot, reason isn't might think. so, first thing check - what's source of prob...
Read more

Unlimited choices in BASH case statement -

consider simple bash snippet: case $option in 1) image=${options[0]%.tar} ;; 2) image=${options[1]%.tar} ;; 3) image=${options[2]%.tar} ;; 4) image=${options[3]%.tar} ;; *) echo "invalid option" exit 1 esac in real script numbers goes 30. makes pretty long. can somehow specify cases variable? something this: case $option in $i) image=${options[$(($i-1))]%.tar} any pointer appreciated. you can match against multiple patterns in single clause: case $option in 1|2|3: echo "$option one, 2 or three" ;; esac if still typing you, can use simple pattern matching: case $option in # following matches # - single-digit numbers 0-9 # - two-digit numbers starting either 1 or 2 # - number 30 [0-9]|[12][0-9]|30) image=${options[$(($option-1))]%.tar} ;; *) echo "invalid option" 1>&2 exit 1 esac
Read more

apache - How do I stop my index.php being run twice for every user -

we've got webapp initial html served using apache , php. i noticed index.php being run twice every request. seems caused / effected rewrite rules in our .htaccess - rewritecond %{http_host} ^(www\.|hotels\.)ourdomain\.com$ [nc,or] rewritecond %{server_name} ^(www\.|hotels\.)ourdomain\.com$ [nc] rewriterule (.*) http://ourdomain.com/$1 [r=301] rewriterule ^hotels/([^/]+)/?\??(.*)$ ?d=$1&$2 [qsa] the final rule moving parameter url path query string. i.e. http://ourdomain.com/hotels/vegas?someparam=1 becomes http://ourdomain.com?d=vegas&someparam=1 if go directly query string version index.php run once. if use url redirected, index.php run twice (i'm checking adding error_log('end of index.php') file). so example going http://ourdomain.com/hotels/paris hits file twice http://ourdomain.com?d=paris hits once. i've seen this question , had @ blog mentioned , , can't find empty string url's (i've tried using yslow process). ...
Read more