[{"data":1,"prerenderedAt":209},["ShallowReactive",2],{"project-11284733":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":39,"post_text":41,"what":42,"said":71,"maker_in_thread":136,"shape":146,"grid":149,"attempts":173,"same_week":174,"maker_shows":137,"maker_hidden":202,"reader_version":203,"card":204},"11284733","Match","Scalable reverse image search built on Kubernetes and Elasticsearch","title","Show HN: Scalable reverse image search built on Kubernetes and Elasticsearch","https:\u002F\u002Fgithub.com\u002Fpavlovml\u002Fmatch","github.com","alexkern",1457982030,2016,139,13,252,2264,12,"notable","ai","reverse image search","api",[21,24,25,26,27],"elasticsearch","perceptual hashing","kubernetes","image matching","curious",0.02,{"positive":31,"neutral":32,"mixed":33,"critical":34},1,5,0,2,8,{"idea":37,"design":38},{"positive":33,"critical":31},{"positive":33,"critical":31},[33,40,33,40,33,40,33,40,40,33,31,31,32],3,null,{"problem":43,"audience":41,"pricing":41,"motivation":41,"time_to_build":41,"stack":50,"openness":68,"stage":69,"team_size":70},{"value":44,"source":45,"evidence":46},"Finds images that visually look similar to a given image","maker",[47],{"id":48,"by":11,"text":49},"11286383","Match is built for finding images that visually look similar. It doesn't understand the semantics of the image itself. There's no way to attach keywords, though…",[51,56,60],{"value":52,"source":45,"evidence":53},"Kubernetes",[54],{"id":55},"post",{"value":57,"source":45,"evidence":58},"Elasticsearch",[59],{"id":55},{"value":61,"source":62,"evidence":63},"image-match library (Goldberg algorithm)","commenter",[64],{"id":65,"by":66,"text":67},"11288394","rhsimplex","Hi everyone, I'm the author of the underlying image matching library ( https:\u002F\u002Fgithub.com\u002Fascribe\u002Fimage-match ). First, thank you Alex for your contribution -- it makes…","open_source","beta","unknown",{"praise":72,"objections":84,"requests":96,"questions":111,"alternatives":129},[73],{"value":74,"source":62,"evidence":75},"Cool project",[76,80],{"id":77,"by":78,"text":79},"11285419","teraflop","This is cool! I'm curious about which perceptual hashing algorithm is being used. The README says it's \"invariant to scaling and rotation\" but the approach described in the…",{"id":81,"by":82,"text":83},"11291069","justinsayarath","wow super cool.",[85,89],{"value":86,"source":62,"evidence":87},"Goldberg algorithm is not robust to arbitrary rotation, only about ±5 degrees",[88],{"id":65,"by":66,"text":67},{"value":90,"source":62,"evidence":91},"API looks very similar to TinEye",[92],{"id":93,"by":94,"text":95},"11286623","XiZhao","Actually, the API looks remarkably similar. 1-1 even.",[97,104],{"value":98,"source":62,"evidence":99},"A demo site with an image uploader",[100],{"id":101,"by":102,"text":103},"11286036","rjvir","Would be useful if they put up a simple site with an image uploader that demos the search",{"value":105,"source":62,"evidence":106},"A scalable web crawler\u002Fimage indexer",[107],{"id":108,"by":109,"text":110},"11286414","impostervt","How about a scalable web crawler\u002Fimage indexer? ;)",[112,116,123],{"value":113,"source":62,"evidence":114},"Which perceptual hashing algorithm is used and is it rotation invariant",[115],{"id":77,"by":78,"text":79},{"value":117,"source":62,"evidence":118},"Is it exact reverse search or semantic similarity",[119],{"id":120,"by":121,"text":122},"11286079","aub3bhat","Is it built for exact reverse image search or is it able to retrieve semantically similar objects?",{"value":124,"source":62,"evidence":125},"Does the hash be binary or real-valued vector",[126],{"id":127,"by":121,"text":128},"11286454","Does the algorithm generate a binary hash? or does it generates a real valued vector? I have been using Tensor Flow to build something similar, though its significantly more…",[130],{"value":131,"source":62,"evidence":132},"TinEye",[133],{"id":134,"by":109,"text":135},"11286437","So tineye?",{"comments":137,"answered":34,"key":138},4,[139,142,145],{"id":140,"text":141},"11285732","Thanks! :) I've added a bit of documentation for the `all_orientations` parameter on POST \u002Fsearch and clarified what we mean by \"rotation\". By default, Match search for all 90…",{"id":143,"text":144},"11286376","That would be awesome. A demo is in the works. :)",{"id":48,"text":49},{"commenters":35,"max_depth":137,"maker_replies":137,"first_comment_mins":147,"lifespan_hours":148},101,22,[150,152,154,156,158,160,161,162,163,164,167,169,171],[65,33,33,151,66,33],"other\u002Fneutral\u002Fnone",[77,31,40,153,78,33],"project\u002Fneutral\u002Fidea",[140,31,33,155,11,31],"maker\u002Fneutral\u002Fdocs",[101,34,40,157,102,33],"project\u002Fneutral\u002Fdesign",[143,34,33,159,11,31],"maker\u002Fpositive\u002Fdesign",[120,40,40,153,121,33],[48,40,33,153,11,31],[127,40,40,153,121,33],[108,137,40,153,109,33],[165,137,33,166,11,31],"11286422","maker\u002Fneutral\u002Fidea",[134,137,31,168,109,33],"project\u002Fcritical\u002Fidea",[93,137,31,170,94,33],"project\u002Fcritical\u002Fdesign",[81,32,32,172,82,33],"project\u002Fpositive\u002Fnone",[],[175,180,185,189,193,197],{"id":176,"name":177,"points":178,"category":179},"11290720","Podcat",401,"productivity",{"id":181,"name":182,"points":183,"category":184},"11287540","amplify",279,"dev_tools",{"id":186,"name":187,"points":188,"category":184},"11283978","Zube 1.0",206,{"id":190,"name":191,"points":192,"category":184},"11261953","GitHub News (gitlogs)",184,{"id":194,"name":195,"points":196,"category":184},"11260956","Spotbot",179,{"id":198,"name":199,"points":200,"category":201},"11282344","CodeMill",169,"web_saas",false,"v2",{"id":205,"name":5,"line":6,"ai":202,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":206,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":207,"url":9,"mix":208,"praise":74,"objection":86,"sub":21},11284733,[21,24,25,26,27],"0303030330115",[31,32,33,34],1794036542106]