[{"data":1,"prerenderedAt":469},["ShallowReactive",2],{"project-14593906":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":46,"post_text":48,"what":49,"said":90,"maker_in_thread":190,"shape":198,"grid":203,"attempts":430,"same_week":431,"maker_shows":18,"maker_hidden":461,"reader_version":462,"card":463},"14593906","Copyfish","Extract text from images, videos or PDF","title","Show HN: Copyfish – Extract text from images, videos or PDF","https:\u002F\u002Faddons.mozilla.org\u002Fen-us\u002Ffirefox\u002Faddon\u002Fcopyfish-ocr-software\u002F","addons.mozilla.org","a9t9",1497960575,2017,292,89,75,2242,4,"legend","productivity","ocr text extraction","desktop_app",[24,25,26,27],"ocr","text extraction","browser extension","chinese subtitles","curious",-0.042,{"positive":31,"neutral":32,"mixed":33,"critical":34},7,28,0,14,49,{"privacy":37,"docs":39,"performance":40,"idea":42,"execution":44},{"positive":33,"critical":38},11,{"positive":33,"critical":33},{"positive":41,"critical":41},1,{"positive":43,"critical":41},3,{"positive":45,"critical":33},2,[41,43,41,43,41,43,33,33,41,43,41,33,47,41,33,33,41,43,41,41,33,33,33,43,47,41,43,43,47,43,33,41,43,43,47,43,43,43,43,47],5,null,{"problem":50,"audience":48,"pricing":59,"motivation":66,"time_to_build":48,"stack":70,"openness":87,"stage":88,"team_size":89},{"value":51,"source":52,"evidence":53},"Extracting text from images, videos and PDFs in the browser","inferred",[54,56],{"id":55},"post",{"id":57,"by":11,"text":58},"14594496","Well, at least this confirms that the screenshots are not manipulated ;) The tricky part for the OCR in this example is the diverse background, as the Chinese characters are…",{"value":60,"source":61,"evidence":62},"Free; ocr.space has a free tier and a paid PRO tier","maker",[63],{"id":64,"by":11,"text":65},"14595967","Actually, based on my tests, there are only a few good services: Abbyy (best recognition rate but by far most expensive), Google Cloud Vision (second best recognition rate),…",{"value":67,"source":61,"evidence":68},"Maker wanted to help watch Chinese movies",[69],{"id":57,"by":11,"text":58},[71,83],{"value":72,"source":73,"evidence":74},"Uses ocr.space OCR API for recognition","commenter",[75,79],{"id":76,"by":77,"text":78},"14597382","bpicolo","It more or less does. `For developers: Copyfish is published under the GPL open-source license. As OCR software, it uses the free OCR API from https:\u002F\u002Focr.space\u002F .`",{"id":80,"by":81,"text":82},"14594959","ythn","Under the hood, the extension is using: https:\u002F\u002Focr.space\u002Focrapi",{"value":84,"source":73,"evidence":85},"Published under GPL open-source license",[86],{"id":76,"by":77,"text":78},"open_source","launched","unknown",{"praise":91,"objections":107,"requests":131,"questions":152,"alternatives":168},[92,100],{"value":93,"source":73,"evidence":94},"Useful for reading and watching Chinese content",[95,96],{"id":57,"by":11,"text":58},{"id":97,"by":98,"text":99},"14596772","Zyst","This seems cool, I just tried it in chrome and it has support for pop-up dictionaries, so I'll be using this for some beginner reading assistance. Thanks for making this!",{"value":101,"source":73,"evidence":102},"Could help accessibility",[103],{"id":104,"by":105,"text":106},"14596908","bondolo","This seems like it could be very useful for accessibility applications.",[108,123],{"value":109,"source":73,"evidence":110},"Sends images to third-party server (ocr.space), a privacy concern",[111,115,119],{"id":112,"by":113,"text":114},"14594448","gressquel","Is the OCR-extraction performed in the client? if its transferred to a server then people should be aware of this so sensitive data from documents\u002Fpdf is not submitted.",{"id":116,"by":117,"text":118},"14594467","qz_","Yeah apparently it uses https:\u002F\u002Focr.space\u002F, deal-breaker for me.",{"id":120,"by":121,"text":122},"14596298","angry_octet","We need to evolve a grammar for describing privacy implications, because proper classification of this software would allow it to be marked as malware\u002Fspyware. It is beyond…",{"value":124,"source":73,"evidence":125},"Recognition accuracy mistakes on some text",[126,130],{"id":127,"by":128,"text":129},"14594411","imron","I saw the heading on HN and thought \"I wonder if it works with Chinese\". I saw the first example screenshot on the page was a Chinese movie and thought \"Great, it does\" I saw the…",{"id":57,"by":11,"text":58},[132,141],{"value":133,"source":73,"evidence":134},"Keep a history of OCRed text when used on video",[135,138],{"id":136,"by":128,"text":137},"14594692","> as the Chinese characters are directly inside the movie. Yep, same with TV shows, and soft-copies of transcripts are difficult to come by, hence my interest in something like…",{"id":139,"by":11,"text":140},"14595650","> When used on a video does it keep a history of all OCRed text? Not yet - but this feature is already on my todo list ;) Thanks for the hint about the chinese forums!",{"value":142,"source":73,"evidence":143},"Clear disclosure that data is sent to a third party",[144,148],{"id":145,"by":146,"text":147},"14596669","mnem","No, however the description of the plugin should make it clear data will be uploaded to a third party server for recognition so the user can make a choice about that.",{"id":149,"by":150,"text":151},"14604984","tripzilch","I don't find that clear at all. And this is also important to non-developers. Also, for nearly all documents I ever need to scan, if they're important enough to require scanning,…",[153,157],{"value":154,"source":73,"evidence":155},"Is OCR done client-side or on a server?",[156],{"id":112,"by":113,"text":114},{"value":158,"source":73,"evidence":159},"Which OCR engine is used?",[160,164],{"id":161,"by":162,"text":163},"14594286","Nimsical","This is cool! Wondering what you're using for OCR?",{"id":165,"by":166,"text":167},"14594457","ransom1538","Is this using TesseractOCR?",[169,177,184],{"value":170,"source":73,"evidence":171},"Google Cloud Vision, ABBYY, Microsoft OCR",[172,173],{"id":64,"by":11,"text":65},{"id":174,"by":175,"text":176},"14600185","ocrcustomserver","Like a9t9 said, ABBYY, Microsoft and Google offer this. If your images however differ from the typical text document, recognition from those services will fail. OCR is highly…",{"value":178,"source":73,"evidence":179},"Project Naptha",[180],{"id":181,"by":182,"text":183},"14594488","CM30","Hmm, I've seen a few apps and extensions like this before. I think Project Naptha was a heavily advertised one that did the same thing a few years back. But how's the accuracy…",{"value":185,"source":61,"evidence":186},"Tesseract.js",[187],{"id":188,"by":11,"text":189},"14596932","There is simply no good OCR engine available that can run inside a Chrome or Firefox extension. The best available is Tesseract.js. And while this engine is fantastic as a…",{"comments":191,"answered":45,"key":192},6,[193,196,197],{"id":194,"text":195},"14595416","I understand that hosted OCR, just like SaaS in general, is not suitable for every use case. On the other hand, the OCR.space OCR API has a very strict privacy policy:…",{"id":188,"text":189},{"id":64,"text":65},{"commenters":199,"max_depth":200,"maker_replies":191,"first_comment_mins":201,"lifespan_hours":202},59,9,58,165,[204,206,208,209,212,215,218,220,221,222,226,229,233,237,240,243,245,248,251,254,256,258,260,263,265,268,271,273,276,279,281,285,288,291,294,297,300,303,306,307,310,312,316,318,320,323,325,328,330,332,334,336,339,342,345,346,350,352,353,354,355,359,363,366,367,371,373,376,378,380,384,386,388,389,390,392,393,396,399,402,405,408,411,414,416,419,421,424,426],[112,33,43,205,113,33],"project\u002Fneutral\u002Fprivacy",[116,33,41,207,117,33],"project\u002Fcritical\u002Fprivacy",[194,33,33,205,11,41],[210,33,43,205,211,33],"14595491","stingraycharles",[213,33,41,207,214,33],"14595617","cantrevealname",[216,33,33,217,77,33],"14596551","commenter\u002Fneutral\u002Fprivacy",[145,33,43,219,146,33],"project\u002Fneutral\u002Fdocs",[76,33,43,219,77,33],[149,33,41,207,150,33],[223,33,33,224,225,33],"14597988","commenter\u002Fcritical\u002Fprivacy","m-p-3",[227,33,41,207,228,33],"14599093","icebraining",[230,33,43,231,232,33],"14597353","maker\u002Fneutral\u002Fnone","JoblessWonder",[234,33,33,235,236,33],"14599140","commenter\u002Fneutral\u002Fnone","jolmg",[238,33,33,235,239,33],"14599263","treitnauer",[241,33,33,235,242,33],"14604221","ignoramceisblis",[244,33,33,235,236,33],"14604913",[246,33,33,217,247,33],"14595958","superasn",[249,33,41,207,250,33],"14596071","kebman",[252,33,33,217,253,33],"14596456","ghostly_s",[255,33,33,217,146,33],"14596704",[188,33,33,257,11,41],"project\u002Fneutral\u002Fperformance",[259,33,43,257,175,33],"14600212",[261,33,41,207,262,33],"14600025","awqrre",[264,33,43,205,175,33],"14600204",[266,33,33,235,267,33],"14604304","kronos29296",[269,33,33,235,270,33],"14604494","drez",[272,33,33,235,175,33],"14605791",[274,33,47,275,267,33],"14643457","project\u002Fpositive\u002Fidea",[277,33,33,217,278,33],"14599021","johnvonneumann",[280,33,41,207,262,33],"14600018",[282,41,33,283,284,33],"14597449","other\u002Fneutral\u002Fnone","TekMol",[286,41,33,283,287,33],"14598296","irrational",[289,41,33,283,290,33],"14598506","Volt",[292,41,33,283,293,33],"14598357","eriknstr",[295,45,33,283,296,33],"14594350","ImJasonH",[298,45,41,207,299,33],"14596422","mdani",[301,45,33,217,302,33],"14597696","pbhjpbhj",[304,45,47,305,98,33],"14596919","project\u002Fpositive\u002Fexecution",[120,43,41,207,121,33],[308,43,43,205,309,33],"14596334","Nadya",[311,43,41,207,121,33],"14596549",[313,43,41,314,315,33],"14596337","project\u002Fcritical\u002Fnone","mholt",[317,43,33,235,253,33],"14596417",[319,43,41,207,121,33],"14596513",[321,43,33,217,322,33],"14597183","cortesoft",[324,43,33,224,121,33],"14599157",[326,43,33,283,327,33],"14602637","jasonkostempski",[329,43,33,283,322,33],"14608556",[331,43,33,283,327,33],"14609835",[333,43,33,283,322,33],"14623094",[335,43,33,283,327,33],"14628639",[337,18,43,219,338,33],"14594931","xophishox",[340,18,43,219,341,33],"14594947","jklinger410",[343,18,47,344,309,33],"14594957","project\u002Fpositive\u002Fperformance",[80,18,43,219,81,33],[347,18,41,348,349,33],"14595301","project\u002Fcritical\u002Fidea","RhodesianHunter",[351,18,33,283,113,33],"14595880",[64,18,33,257,11,41],[174,18,43,257,175,33],[181,47,43,257,182,33],[356,47,43,357,358,33],"14594550","project\u002Fneutral\u002Fidea","maggit",[360,191,43,361,362,33],"14596880","project\u002Fneutral\u002Fnone","chrischen",[364,191,43,361,365,33],"14597905","yjftsjthsd-h",[97,31,47,305,98,33],[368,369,43,361,370,33],"14594740",8,"dontchooseanick",[372,200,33,283,349,33],"14595326",[374,200,33,283,375,33],"14597896","asenna",[377,200,33,283,349,33],"14616250",[379,200,33,283,175,33],"14600228",[381,382,43,257,383,33],"14594285",10,"foota",[127,382,41,385,128,33],"project\u002Fcritical\u002Fperformance",[57,382,33,387,11,41],"maker\u002Fpositive\u002Fperformance",[136,382,43,361,128,33],[139,382,33,361,11,41],[391,382,43,357,128,33],"14595814",[104,38,47,275,105,33],[161,394,47,395,162,33],12,"project\u002Fpositive\u002Fnone",[397,394,43,219,398,33],"14594300","jffry",[400,394,43,205,401,33],"14594479","whitten",[403,394,43,361,404,33],"14594588","tobltobs",[406,394,43,361,407,33],"14594709","tangue",[409,394,43,361,410,33],"14594942","samfisher83",[412,394,43,361,413,33],"14601465","PokemonNoGo",[165,415,43,361,166,33],13,[417,34,43,231,418,33],"14595001","sjs382",[420,34,33,231,11,41],"14595706",[422,34,33,235,423,33],"14595911","vdRrsithZm",[425,34,33,235,423,33],"14595920",[427,428,47,275,429,33],"14594317",15,"zhangkehu",[],[432,437,442,447,452,456],{"id":433,"name":434,"points":435,"category":436},"14558582","Snips",372,"ai",{"id":438,"name":439,"points":440,"category":441},"14583882","Decaffeinate",361,"languages",{"id":443,"name":444,"points":445,"category":446},"14587669","rust-algorithms",320,"learning_science",{"id":448,"name":449,"points":450,"category":451},"14597485","NBox",286,"security_privacy",{"id":453,"name":454,"points":455,"category":441},"14588333","html5-parser",169,{"id":457,"name":458,"points":459,"category":460},"14597544","Upstart.me",168,"web_saas",false,"v2",{"id":464,"name":5,"line":6,"ai":461,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":465,"top":18,"kw":466,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":467,"url":9,"mix":468,"praise":93,"objection":109,"sub":21},14593906,-0.04,[24,25,26,27],"1313130013105100131100035133530133533335",[31,32,33,34],1794036556489]