tag:blogger.com,1999:blog-45284039964073628092024-09-14T14:08:36.049-07:00A blog dedicated to the research and development of successful OCR (Optical Character Recognition) methods used to solve CAPTCHAs.Zaptchahttp://www.blogger.com/profile/04446747075355821512noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-4528403996407362809.post-16066373123144350532011-05-23T12:12:00.000-07:002011-05-23T12:13:31.647-07:00I have been working on OCR'ing a new captcha.<br /> <br /> <div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjnV02159u0qE6IIxKPkFMtP31Hh66OOX63Cgmi-JeUHZ4-0tFYh6F_tpT1_02NtKD1Q3eXAoSHptmlVOdzAqCECUqJ92wL-90phL8F3qK87jLerutyS_9-7jLhc9rNb105IrZrB0f81ItV/s1600/1.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjnV02159u0qE6IIxKPkFMtP31Hh66OOX63Cgmi-JeUHZ4-0tFYh6F_tpT1_02NtKD1Q3eXAoSHptmlVOdzAqCECUqJ92wL-90phL8F3qK87jLerutyS_9-7jLhc9rNb105IrZrB0f81ItV/s1600/1.jpg" /></a></div>At first glance this one appears much more difficult than the one I solved earlier (<a href="http://zaptcha.blogspot.com/2011/05/i-have-decided-to-start-building.html">from d2jsp.org</a>) but after a few lines of pre-processing the image is cleaned up very nicely.<br /> <br /> <br /> <div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgE4LyT2SoxhlHjuPHayqNNpl-Crx8WbIlAKEYMjD8oxdPhxLSPDSbW8KVn0m3z3szLaa6z9DuyQY8BLAaZKLyeIZO9-ioUcDxgFrNNJ6l7k2VKS0HADAU_S66AQ3I4NdbSdzlou7nTEXK6/s1600/2.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgE4LyT2SoxhlHjuPHayqNNpl-Crx8WbIlAKEYMjD8oxdPhxLSPDSbW8KVn0m3z3szLaa6z9DuyQY8BLAaZKLyeIZO9-ioUcDxgFrNNJ6l7k2VKS0HADAU_S66AQ3I4NdbSdzlou7nTEXK6/s1600/2.jpg" /></a><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjS_Pdg4WXO7xv4Ozsp-Xp4F0K8kpNgny5WBRS-3EUrUfOvowvV95aX_QmVhMA3FbXExSpxZZ9voqsRy2qcTxu-2XDUS5k9p8r3QhlkDuVtofcKeNpgO2diVMeD2NaxCFwuczip_sxF8qNb/s1600/2out.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjS_Pdg4WXO7xv4Ozsp-Xp4F0K8kpNgny5WBRS-3EUrUfOvowvV95aX_QmVhMA3FbXExSpxZZ9voqsRy2qcTxu-2XDUS5k9p8r3QhlkDuVtofcKeNpgO2diVMeD2NaxCFwuczip_sxF8qNb/s1600/2out.jpg" /></a></div><br /> <br /> <div class="separator" style="clear: both; text-align: center;"></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh9YwcZMegqhEhE7rv8kPsfdhGIL7ApIBhRkAnNfnkVMIb_xLrbUcqr0Yreu4JIZJjBcQuAsgacUE11KV_lNKvRZGfUOWfABEC7fIb_cMIYEXUus7QTPNg8y845G21xe542Z20EACkH-0pr/s1600/3.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh9YwcZMegqhEhE7rv8kPsfdhGIL7ApIBhRkAnNfnkVMIb_xLrbUcqr0Yreu4JIZJjBcQuAsgacUE11KV_lNKvRZGfUOWfABEC7fIb_cMIYEXUus7QTPNg8y845G21xe542Z20EACkH-0pr/s1600/3.jpg" /></a><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhMNijFjMwOx_kKWnH-p12WYmTbd6CktMX_jub_As-W-Zqg1xAMwQ7-ccll8GlZP6ZCphzJzndPLj3mZwe5yLm3TXqcAxnoEvcErytCTkOHvxvWa5n_KQ7DD3bZrz89k2RNFzYSDi9sTJON/s1600/3out.jpg" /></div><br /> <div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiahUhGHaIrCNoarGP2FSS5FjyRDCd9yhQCWso6kP2J5A5IYvlYe3BF4Th2zg3XpLWdiLU372J7hhKX74PxxhmvydOrPW6Brlff5UHGmwB3sXXTFiDmk4n7Ix9jAjzzk28nKmegjKAXO9jv/s1600/4.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiahUhGHaIrCNoarGP2FSS5FjyRDCd9yhQCWso6kP2J5A5IYvlYe3BF4Th2zg3XpLWdiLU372J7hhKX74PxxhmvydOrPW6Brlff5UHGmwB3sXXTFiDmk4n7Ix9jAjzzk28nKmegjKAXO9jv/s1600/4.jpg" /></a><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi9K0M4WMJYaRX2bR2MoEJrN__IK9drw7tUqC75zaCd-8TVblumOXi8AuXTmOSlRm156iwhjWBkojJeM6CcScwHHObfb3mdD0puJl11XAPDwcANKSkhuV9KMZNRT_Ql3MngR-CjJkTKCPgt/s1600/4out.jpg" />&nbsp;</div><div class="separator" style="clear: both; text-align: center;"><br /> </div><div class="separator" style="clear: both; text-align: left;">&nbsp;&nbsp; From this pre-processing we are left with a single artifact to deal with, that centered vertical line. Since this artifact was in the same place every time, I simply just trained the OCR engine to recognize the letters with the line through them. I used a data set of 333 images to do the initial training.&nbsp;</div><div class="separator" style="clear: both; text-align: left;"><br /> </div><div class="separator" style="clear: both; text-align: left;">I ran another data set of 333 new images through to see what kind of recognition rates I was getting. I needed to train 28 of the 333 images, or 8.408% of them.</div><div class="separator" style="clear: both; text-align: left;"><br /> </div><div class="separator" style="clear: both; text-align: left;">On the third and final data set I ran an addition 333 new CAPTCHAs through. I had to train 19 of these, giving me a 5.706% training rate for the third data set.</div><div class="separator" style="clear: both; text-align: left;"><br /> </div><div class="separator" style="clear: both; text-align: left;">More to come later...&nbsp;</div><div class="separator" style="clear: both; text-align: left;"><br /> </div><div class="separator" style="clear: both; text-align: left;">PS: I'm new to this whole blogging thing, does anyone know if it is possible to use LaTeX in these posts? A plugin of some sort?&nbsp;</div>Zaptchahttp://www.blogger.com/profile/04446747075355821512noreply@blogger.com1tag:blogger.com,1999:blog-4528403996407362809.post-57827695368775771222011-05-23T09:13:00.000-07:002011-05-23T09:50:48.648-07:00I have decided to start building a library of captchas that I have successfully written OCR algorithms for. I am planning to use this blog to help me document my steps along the way and keep a sort of running tally of my progress.<br /> <br /> The first captcha I decided to do was one from <a href="http://d2jsp.org/">d2jsp.org</a>. It was definitely one of the easier captchas, as it had a constant font, no permutations, no artifacts, and no color differentiation.<br /> <br /> <div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgk0vz1a8zU2MFgSxD-8HpBC766kQ_QtQQxqHZyo7b5rdL6uKL7nvqpLG5NQvCXOCK7wSNkjtBhk4c0qxNBHd5bzWamsbS4ZwI-nz91Gug7_0qTt4GH4d9YnCVVc-2kKIu6ie82rICRkeMO/s1600/1.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgk0vz1a8zU2MFgSxD-8HpBC766kQ_QtQQxqHZyo7b5rdL6uKL7nvqpLG5NQvCXOCK7wSNkjtBhk4c0qxNBHd5bzWamsbS4ZwI-nz91Gug7_0qTt4GH4d9YnCVVc-2kKIu6ie82rICRkeMO/s1600/1.jpg" /></a></div><br /> <div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIIQgjTOspgId93oqtKdJg8y3KdbEKba4BHuyo8k1zmCtcm0Z1FShgOQOV03W_fmLIdt8rUF0d-9Q8KoYfhWbWoCEWAhJAs61jrRtUauCHncrr0k5ArEIw6g1_23Ax_sIhwdnOPe89pF4P/s1600/2.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIIQgjTOspgId93oqtKdJg8y3KdbEKba4BHuyo8k1zmCtcm0Z1FShgOQOV03W_fmLIdt8rUF0d-9Q8KoYfhWbWoCEWAhJAs61jrRtUauCHncrr0k5ArEIw6g1_23Ax_sIhwdnOPe89pF4P/s1600/2.jpg" /></a></div><br /> <br /> My testing has given me 100% accuracy in reading these captchas so far. These captchas required no pre-processing and were just run, as is, through my OCR engine.Zaptchahttp://www.blogger.com/profile/04446747075355821512noreply@blogger.com1