What (and how) should I use for object detection in this case?












0












$begingroup$


I have read a few papers on object detection and analyzed several implementations of object detection applied to car number plates.



In my case, the task is a bit more difficult in that I need to detect a number (you might have seen the way containers are labeled using a sequence of letters and digits). Unlike car number plates, there is no unified form of the number plate, its location might differ etc.



The goal is to do object detection and then recognize (OCR) the code (as I said, this is a sequence of digits and letters. Good news this sequence is standard).



I have a few questions:



1) The first task is to perform object localization i.e. create a training dataset of annotated images ($x_{min}, y_{min},x_{max},y_{max}$, height,width).
There is an issue, however. Usually, this is not the only area on containers with digits and letters. Will the neural network be able to learn the right location?



2) Do I need to manually segment all digits and letters inside the "bounding box"? Or how should this stage be performed?



3) Is there any hope that Tesseract could be helpful for OCR? As far as I know, it's not very accurate for photos. If not, what is the best algorithm to do OCR after object detection?



4) Considering that I have almost no experience, would it be easier to start with Tensorflow Object Detection API or Yolo for object detection?



Below, I am attaching an example of the number which should be detected and recognized (BMOU 441929 7)



BMOU 441929 7 - an example of the number for recognition










share|improve this question







New contributor




Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    0












    $begingroup$


    I have read a few papers on object detection and analyzed several implementations of object detection applied to car number plates.



    In my case, the task is a bit more difficult in that I need to detect a number (you might have seen the way containers are labeled using a sequence of letters and digits). Unlike car number plates, there is no unified form of the number plate, its location might differ etc.



    The goal is to do object detection and then recognize (OCR) the code (as I said, this is a sequence of digits and letters. Good news this sequence is standard).



    I have a few questions:



    1) The first task is to perform object localization i.e. create a training dataset of annotated images ($x_{min}, y_{min},x_{max},y_{max}$, height,width).
    There is an issue, however. Usually, this is not the only area on containers with digits and letters. Will the neural network be able to learn the right location?



    2) Do I need to manually segment all digits and letters inside the "bounding box"? Or how should this stage be performed?



    3) Is there any hope that Tesseract could be helpful for OCR? As far as I know, it's not very accurate for photos. If not, what is the best algorithm to do OCR after object detection?



    4) Considering that I have almost no experience, would it be easier to start with Tensorflow Object Detection API or Yolo for object detection?



    Below, I am attaching an example of the number which should be detected and recognized (BMOU 441929 7)



    BMOU 441929 7 - an example of the number for recognition










    share|improve this question







    New contributor




    Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      0












      0








      0





      $begingroup$


      I have read a few papers on object detection and analyzed several implementations of object detection applied to car number plates.



      In my case, the task is a bit more difficult in that I need to detect a number (you might have seen the way containers are labeled using a sequence of letters and digits). Unlike car number plates, there is no unified form of the number plate, its location might differ etc.



      The goal is to do object detection and then recognize (OCR) the code (as I said, this is a sequence of digits and letters. Good news this sequence is standard).



      I have a few questions:



      1) The first task is to perform object localization i.e. create a training dataset of annotated images ($x_{min}, y_{min},x_{max},y_{max}$, height,width).
      There is an issue, however. Usually, this is not the only area on containers with digits and letters. Will the neural network be able to learn the right location?



      2) Do I need to manually segment all digits and letters inside the "bounding box"? Or how should this stage be performed?



      3) Is there any hope that Tesseract could be helpful for OCR? As far as I know, it's not very accurate for photos. If not, what is the best algorithm to do OCR after object detection?



      4) Considering that I have almost no experience, would it be easier to start with Tensorflow Object Detection API or Yolo for object detection?



      Below, I am attaching an example of the number which should be detected and recognized (BMOU 441929 7)



      BMOU 441929 7 - an example of the number for recognition










      share|improve this question







      New contributor




      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      I have read a few papers on object detection and analyzed several implementations of object detection applied to car number plates.



      In my case, the task is a bit more difficult in that I need to detect a number (you might have seen the way containers are labeled using a sequence of letters and digits). Unlike car number plates, there is no unified form of the number plate, its location might differ etc.



      The goal is to do object detection and then recognize (OCR) the code (as I said, this is a sequence of digits and letters. Good news this sequence is standard).



      I have a few questions:



      1) The first task is to perform object localization i.e. create a training dataset of annotated images ($x_{min}, y_{min},x_{max},y_{max}$, height,width).
      There is an issue, however. Usually, this is not the only area on containers with digits and letters. Will the neural network be able to learn the right location?



      2) Do I need to manually segment all digits and letters inside the "bounding box"? Or how should this stage be performed?



      3) Is there any hope that Tesseract could be helpful for OCR? As far as I know, it's not very accurate for photos. If not, what is the best algorithm to do OCR after object detection?



      4) Considering that I have almost no experience, would it be easier to start with Tensorflow Object Detection API or Yolo for object detection?



      Below, I am attaching an example of the number which should be detected and recognized (BMOU 441929 7)



      BMOU 441929 7 - an example of the number for recognition







      deep-learning cnn object-detection object-recognition ocr






      share|improve this question







      New contributor




      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question







      New contributor




      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question






      New contributor




      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked 2 days ago









      Don DraperDon Draper

      1




      1




      New contributor




      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      Don Draper is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          0






          active

          oldest

          votes











          Your Answer





          StackExchange.ifUsing("editor", function () {
          return StackExchange.using("mathjaxEditing", function () {
          StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
          StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
          });
          });
          }, "mathjax-editing");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "557"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          autoActivateHeartbeat: false,
          convertImagesToLinks: false,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: null,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });






          Don Draper is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46801%2fwhat-and-how-should-i-use-for-object-detection-in-this-case%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          0






          active

          oldest

          votes








          0






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          Don Draper is a new contributor. Be nice, and check out our Code of Conduct.










          draft saved

          draft discarded


















          Don Draper is a new contributor. Be nice, and check out our Code of Conduct.













          Don Draper is a new contributor. Be nice, and check out our Code of Conduct.












          Don Draper is a new contributor. Be nice, and check out our Code of Conduct.
















          Thanks for contributing an answer to Data Science Stack Exchange!


          • Please be sure to answer the question. Provide details and share your research!

          But avoid



          • Asking for help, clarification, or responding to other answers.

          • Making statements based on opinion; back them up with references or personal experience.


          Use MathJax to format equations. MathJax reference.


          To learn more, see our tips on writing great answers.




          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f46801%2fwhat-and-how-should-i-use-for-object-detection-in-this-case%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          How to label and detect the document text images

          Vallis Paradisi

          Tabula Rosettana