Pleco 2.2 Instruction Manual : OCR
The Pleco Optical Character Recognizer system is a paid add-on module; if purchased, you can access it by tapping on the menu button at the bottom right corner of your iPhone's screen, then tapping on"Read+OCR" (second tab from the left) and on the "Optical Character Recognizer" command at the top of the screen.
If you haven't purchased the OCR module yet, you can do so through the Add-ons tab; there's also a demo version accessible through there (just tap on the "Optical Character Recognizer" item). We strongly recommend that you try out that demo version before purchasing this module; this is a totally new feature, not just for us but for Chinese dictionary software in general, and while we're working hard to improve it, there are a number of limitations and you may not find that it works well enough to be usable for you yet.
The new Optical Character Recognizer system in Pleco 2.2 is our first attempt to introduce a totally new way to look up unknown characters since the debut of our original Palm OS software way back in 2001. Rather than handwriting in unknown characters, or tediously looking them up in a radical index, using OCR you can simply point your iPhone's camera at a word to look it up instantly; you don't even need to tap a shutter button, you just line up the camera with the word and the definition appears instantly.
Much like our handwriting recognizer, our OCR system works by matching characters to templates in a database; it turns the image of the character into a simple mathematical structure, identifies its key features (lengths / positions / curvatures of strokes, etc), then searches through its database of 10,000+ Chinese characters to find the one that most closely matches that pattern.
However, while the handwriting recognizer always has a very clear picture of the character you drew - it knows exactly where every stroke is located, where it starts / ends, what order strokes were drawn in, where it overlaps other strokes - the OCR system has to contend with a much murkier one; characters on a camera image can be small, grainy, and out-of-focus, and the same calligraphic flourishes that make printed Chinese text so pretty to look at also make it harder to see the underlying structure of each character.
OCR is also up against some psychological hurdles compared to handwriting input; while a mis-recognized handwritten character can be chalked up to one's poor handwriting / incorrect stroke order, with a printed character there's nobody to blame but the recognition software. On top of which, because OCR must recognize multiple characters at a time, there's no opportunity for it to show you its other, less likely matches like the handwriting recognizer does. Handling lots of characters at once also means that even if gets a higher percentage of them accurate on the first try, if just a few of those are incorrect it'll still feel as if it got the entire block of text wrong. So while handwriting only has to contend with one character at a time, and can even be forgiven for getting that character wrong as long as the correct character is among its top 5 matches, OCR has to deal with multiple characters and get every one of them exactly correct in order to seem like it's doing its job.
(this is all a convoluted way of asking you to be patient if things don't work perfectly every time; we're new at this, we're working on all sorts of cool new image processing / analytical tools to bring this even closer to character recognizer perfection, but in the meantime we hope you'll find it accurate enough to be useful in its current form)
Here are some specific limitations to keep in mind when using our OCR system:
The OCR module now supports any device running iOS 4.0 or later that supports multitasking - i.e., the iPhone 3GS, iPhone 4, 3rd- and 4th-generation iPod Touch, and iPad. Older devices like the iPhone 3G unfortunately don't have enough RAM to use OCR in live or still image mode.
Devices without cameras can only use OCR in still image mode with images loaded from a computer or downloaded from the web; on the iPad you can also use Apple's Camera Connection Kit to copy images into memory directly from a digital camera.
The iPod Touch 4th-generation is a special case, because while it does have a built-in camera, its camera does not support autofocus and so cannot get a clear image of text at close range. (we're quite certain of this - we've tested it extensively) Hence, if you intend to use live OCR on your iPod, we recommend testing the demo version thoroughly first to make sure that it meets your needs, and possibly also purchasing an add-on macro lens to improve its close-up focus abilities.
Tap on "Optical Character Recognizer" at the top of the "Read+OCR" tab to get to the main OCR screen shown here:
The "Live Video" options will only be visible if your device has a built-in camera.
Live Video
Lookup Words: the primary way of using Pleco OCR (and the one shown in our demo video): point your phone's camera at a word and its definition instantly pops up below. If you turn on the "Take over wild button" option in Settings, you'll also be able to access this screen by tapping on an "OCR" button in the main Dict tab when the search input bar is open.
Capture Flashcards: point the camera at a word and hold it there for a second or so to add it to your flashcard database; only visible if you've purchased the flashcard add-on.
Capture Text: point the camera at a longer block of text and tap on a button to bring up that block of text in a document reader screen; you can then tap on characters in the text to look them up, or save the output to a text file. This is best for short blocks of text of no more than a paragraph or so.
Still Image
Block Recognizer: select a large portion of an image and recognize all of the Chinese text in it at once. You can then bring up this text in the document reader, copy it to the pasteboard, or simply tap on characters in the image to look them up just as in our regular document reader.
Scroll Lookup Words: look up vocabulary one-word-at-a-time just like "Lookup Words" in the live OCR system, but instead of pointing at the words you want to look up, you scroll / zoom around the image until they're in the recognition area.
Scroll Capture Text: works the same as Scroll Lookup Words, but for capturing longer blocks of text and looking them up in our document reader / saving them to a text file (a la "Capture Text" in live OCR).
After choosing one of the "Still Image" options you'll be confronted with an additional menu asking where you want to get the image from:
Take Photo: take a picture with your iPhone's built-in camera (only visible on camera-equipped-devices, obviously). You can save the image after you take it from the main recognizer screen.
Photo Library: use a photo from your iPhone's photo library / camera roll; this is where photos will end up if you sync them over from iPhoto or using Apple's Camera Connection Kit or if you previously took them with your phone's camera.
Image File: select an image file (.png, .jpg, etc) that's been copied into Pleco's document storage area or downloaded with the built-in web browser and crop / recognize that.
Tap on "Lookup Words" in the main screen above to get to the actual recognizer interface:
Lots of options here, but most of them are fairly straightforward:
Top Bar:
Middle:
Bottom Bar:
To look up a word, point your iPhone's camera at the word you want to look up and square up that word within the recognition area. It's OK if there are additional characters in the recognition area too; just make sure that the left edge of the recognition area (where the > is located) is lined up with the first character in the word, and (if there's more than one line of text visible) that the top edge of the word is lined up with the top of the recognition area.
The OCR system will show you every character it recognizes within the recognition area in green, and once it's confident enough in a particular couple of characters, it will "lock on" to those characters, show them in blue instead of green, and display their definition. If you point at a different set of characters it'll quickly lock on to those instead, so you can scan along a whole line of text and read definitions as you go. (both the blue and green colors used can be changed in Settings)
Both horizontal and vertical text are supported; if the recognition area is resized to be vertical (significantly taller than it is wide), the > indicator will move from the left side of it to the top, indicating that Pleco is now recognizing text vertically. To pause the system and temporarily stop recognizing characters, tap on the pause button, or to combine characters from two different lines of text, tap on span lines. Tap on the history button (second from the right at the top of the screen) to scroll through the last few words recognized.
The recognition area is the bright green box in the center of the screen; it can be resized by dragging any of the four corners (which resize it symmetrically but don't move it around - it always remains centered in the same spot). Pleco's recognizer will only attempt to recognize characters within that area; it doesn't look outside of it at all, so it won't pick up a character that's half-in, half-out (or at least won't do so accurately).
It's perfectly OK if the recognition area is longer than necessary for a particular word, as long as the word is aligned with the left side (or the top if you're recognizing vertical text). In fact, it can even help with recognition accuracy - seeing more characters helps the system get a better picture of their size / darkness / etc - so it's quite reasonable to resize it as large as it will go and just leave it that way all the time. Since it won't look outside of the box, though, resizing it to just one character wide is an easy way to look up the meanings of individual characters by themselves, and can also help to avoid "cheating" if you're looking at a word that you're supposed to know; looking up one character of a forgotten word may give you a hint without revealing the whole word's meaning / pronunciation.
If you find that characters are too small for the recognition area, try zooming in (though this can reduce accuracy), or just hold the iPhone closer to the text you want to recognize. Conversely, since the speed of the OCR system is directly proportional to the size of the recognition area, if you find that the characters you're recognizing are very large, you can consider turning on the "Shrink big images" option in Settings to reduce their size before recognizing them (greatly improving speed).
If you find that the recognizer sometimes thinks a compound character like 林 is actually two characters (木木), it may be that it's having a tough time detecting the size of the font; making the recognition area wider may help with this, or if turn off the "Allow multiple lines" option in Settings (and make sure that the recognition area never stretches down to part of the next line of text) that should help also.
Tap on the "pause" button at the bottom of the screen to stop recognizing characters and bring up this alternate toolbar at the bottom of the screen:
Tap on flashcard to add the current word to your flashcard database, or tap on details to bring up a full-screen dictionary definition (from which you can play audio, view example sentences, tap on individual characters in the headword to look up their meanings / stroke order / components, etc). Tap on resume to start recognizing characters again.
While paused, you can also tap on any character in the recognition area to look up the word starting at that character, useful if you've captured more than one word at a time. You can tap on the first character of the currently selected word to shrink the length of the selection, useful for looking up the individual characters that make up words.
Also while paused, you can also tap-hold on a character to bring up a screen listing similar-looking characters:
Tap on the correct character to replace it in the recognized text. (this will be forgotten as soon as you un-pause the recognizer)
Often when reading Chinese you'll encounter a word that starts on one line and ends on the next, much like a hyphenated word in English (though much more common). For example:
我要给阿Ｑ做正传，已
经不止一两年了。
已经 is a single word, but since it starts on one line and ends on another, there's no way to simply point the recognizer at it and recognize the whole word.
Our solution to this is the conveniently-located "span lines" button. To use it, point the camera at the first part of the word (已 in the above example), then tap on "span lines" - you'll see that character / characters appear just above the recognition area, like this:
After that, point the camera at the second part of the word (经 in this case) to see the result for the entire word. Tap on the "span lines" button again (renamed to "cancel span") to return to normal recognition.
Tap on the camera icon (second from the left at the top of the screen) to bring up an additional toolbar just below the top one:
The first two buttons control the OCR's zoom factor. This is strictly a digital zoom - there's no magnifying lens in an iPhone camera, all we can do is blow up the image - so it only goes up to a maximum zoom factor of 4x; tap on the zoom in button once to go from 1x to 2x, then again to go to 4x.
The next button toggles the built-in LED flash - only available on the iPhone 4. It works quite well to illuminate objects at close range (like most of the text you're likely to be looking up with OCR), but it can also confuse the recognizer by making some parts of an image much brighter than others (so it's difficult to see where the text is) - turning on the Sauvola Binarization option in Settings can help considerably with this (at the cost of making the recognizer a bit slower).
The next option toggles the image orientation - horizontal versus vertical lines of text; Pleco will try to guess this automatically based on the size of the recognition area, but you can manually override it with this setting.
The final option toggles between black-on-white and white-on-black text. Most of the time the recognizer can figure this out automatically too, but if you find that it gets it wrong (you'll know because the recognized characters will have absolutely nothing to do with the text you're looking at), you can tap on this button to manually force it to one mode or the other. (the icon in the bar above is for black-on-white)
New in Pleco 2.2.2 is the ability for the recognizer to automatically pause the recognizer when it detects that your device has stopped moving, and resume recognizing characters once you start moving again. This is the best solution we've come up with so far to the problem of OCR output being "jittery" and changing the recognized characters when users' hands are shaking.
You'll be prompted to turn on this option the first time you launch OCR; you can enable / disable it later in Settings / OCR / Live Video / Motion Detection / Enable. When the system detects that the device has stopped moving, it will change the color / thickness of the box surrounding the recognition area (just as during a normal pause) and stop updating the character display until you start moving again:
There are lots of settings to customize the threshold at which the system detects that the device has moved, so hopefully with a little tweaking you'll be able to get it to consistently pause when you want it to pause and resume when you want it to resume.
The second of the three "live" OCR modes is Capture Flashcards. This mode, only available if you've purchased the flashcard add-on module (though we're planning to include a free "lite" version of that in our next major update, 2.3), lets you point your camera at a word to instantly add it to your flashcard database; it's almost like using a barcode scanner.
The interface for this is almost exactly the same as that for Lookup Words above. Tap on "Capture Flashcards" in the main screen and you'll see a prompt asking you to select a category for your new flashcards; choose that category and you'll be presented with our standard live OCR interface. However, in Capture Flashcards mode, after pointing at the same word for a second or so (this interval can be changed in Settings), you'll hear a beep and the screen will flash a message telling you you've created a new flashcard. This is especially useful for digitizing a long list of words at the end of a textbook chapter - you can enter each word in a fraction of the time it would take enter it manually.
Your new flashcard will be based on the currently-displayed dictionary definition; tapping on the Switch Dictionary button will change the dictionary used for the current and subsequent cards, though you can also go back and change their definitions later through Organize Flashcards.
One important Settings option specific to Capture Flashcards is "Unknown word handling." With the default behavior, "Truncate," the system will create a card based on the longest match it can find for the word in the recognition area; if it only matches the first character then it'll only create a card for that character. However, if you change this option to "Create Custom," you'll be prompted to create a brand new custom flashcard instead, with the headword prepopulated with the recognized characters; this is especially useful for items like character names that aren't likely to appear in a dictionary.
The final "live" OCR mode is the most confusing but possibly also the most powerful; with "Capture Text," instead of recognizing a single word at a time, you can recognize a larger block of text - several words, a sentence or even an entire paragraph - and bring it up in a document reader screen, save it to a text file, or save it to the system pasteboard to insert into another app.
This is similar in a lot of ways to still image capture mode, but unlike in that system, in Capture Text you see the results "live" on the screen so that you can make sure your text is framed up / recognized correctly (rather than having to go back and take another picture if the system gets it wrong the first time). However, since it's accessing the iPhone's camera in video mode instead of photo mode, the images it gets are much lower-resolution, so it can't see clearly enough to recognize an entire page of text (and even if it could, it would be so slow as to barely constitute an improvement over still image capture).
The interface to this is still very similar to Lookup Words, but with no Switch Dictionary / entry scroll buttons, and two new buttons replacing "flashcard" and "details" when paused:
Capture: bring up the recognized text in a standard Pleco document reader screen; you can tap on words in that to view their meaning, or save the results to a text file.
Copy: copies the recognized text to the system pasteboard, so that you can easily paste it into another application.
Also, the history button is missing in the top bar; there's no history function for Capture Text at the moment, though if you turn on the "Combine captured text" option in Settings, each time you tap on "capture," the recognized text will be appended to the end of the previously-captured text instead of replacing it; you'll end up with a copy of all of the text captured during a particular recognition session. (though for scanning full pages we'd recommend trying your luck with still image mode instead)
Pleco's OCR system also supports a still image recognition mode, much like a more conventional OCR system but optimized to work well with images from a camera (as opposed to images from a scanner) and to facilitate easily looking up unknown words.
This option is the most traditional of the three; it simply takes an entire image (or a cropped portion of it) and recognizes the text on it. It will begin recognizing as soon as you open the image; you can resize the crop area while it's recognizing, you don't need to wait for it to finish.
Once the recognizer finishes, the image will be overlaid with the recognized characters just as in live OCR. You can pinch-zoom to view these characters in detail:
Tap on any word in the image to instantly look up its definition:
Tap anywhere in the image to exit the popup reader "bubble." The interface to this is the same as in the main dictionary popup reader.
Tap on the "hide chars" button at the bottom of the screen to hide the green character overlay; you can still tap on characters to look them up. The "capture" and "clip" functions work exactly like they do in the live Capture Text mode - "capture" brings up the recognized text in a standard Pleco document reader screen (from which you can save it to a text file), and "clip" copies the recognized text to the system pasteboard so that you can easily paste it into another application.
Tap-hold on a mis-recognized character to correct it. Normally this has the same interface as the Live OCR equivalent, but if you've purchased our Fullscreen Handwriting Recognizer add-on you'll get this screen instead:
Simply draw the correct character on top of the original image to enter it using our handwriting recognizer. The results at the bottom of the screen when this screen initially opens are the best matches the OCR system came up with.
Tap on the picture icon in the top toolbar to hide / show a menu of image controls (similar to Camera Controls for Live OCR):
The first two buttons rotate the image 90 degrees to the left / right.
The next option toggles the image orientation - horizontal versus vertical lines of text; Pleco will try to guess this automatically by analyzing the image layout, but you can manually override it with this setting. If you see a lot of incorrect / wrongly-located characters, double-check that this setting is configured correctly.
The final option toggles between black-on-white and white-on-black text. Most of the time the recognizer can figure this out automatically too, but if you find that it gets it wrong (you'll know because the recognized characters will have absolutely nothing to do with the text you're looking at), you can tap on this button to manually force it to one mode or the other. (the icon in the bar above is for black-on-white)
This mode works very similarly to the live video "Lookup Words" mode, but instead of pointing your phone's camera at words you drag / zoom a still image around to position the words in the recognition area:
The image controls toolbar is the same as in Block Capture, and the history / flashcard / span lines / details / dictionary buttons work just like they do in Lookup Words. The main addition is the hide defn button - tap on this to hide the definition area, making it easier to pan / zoom around the image. You can also make the buttons and definition area smaller via Settings / OCR / Still Image / Interface.
This uses the same interface as Scroll Lookup Words above (panning around images to look up words within the recognition area), but instead of looking up individual words you can capture larger entire blocks of text and copy them to the pasteboard or send them to Pleco's document reader (much like Capture Text from Live Video OCR). It's useful when you want more fine-grained control over the text you're copying out of OCR, but for most users the Block Capture mode will probably do a better job with the same thing.
Return to Table of Contents