Changes

Jump to navigation Jump to search
Line 63: Line 63:     
* Test of an end-to-end model, through an API as a starter: Form Recognizer or Google Document AI API. If results are promising, we develop in-house end-to-end model, otherwise a layout model.
 
* Test of an end-to-end model, through an API as a starter: Form Recognizer or Google Document AI API. If results are promising, we develop in-house end-to-end model, otherwise a layout model.
* Thourough litterature review
+
* Thorough literature review
 
* Architecture choice
 
* Architecture choice
 
* Annotation campaign
 
* Annotation campaign
Line 70: Line 70:     
Ramzi: test of end-to-end model with Form Recognizer API.
 
Ramzi: test of end-to-end model with Form Recognizer API.
 +
 
Yichen: test of image preprocessing before Form Recognizer (layout model), test "manual" approaches.
 
Yichen: test of image preprocessing before Form Recognizer (layout model), test "manual" approaches.
 +
* tested a pre-processing method (ported from Mathematica to python)
 +
* OCR results worsen after binarization
 +
* testing method to morph deformed images (by detecting horizontal and vertical lines)
 +
* "manual" approaches: compare positions of bounding boxes of OCR, use borders if we have some
 +
** manual horizontal or vertical scans of bounding boxes, using the angles of bounding boxes
 +
** robotoff has python classes for importing/analyzing Google Cloud Vision
 +
 +
Raphaël: Literature review (to be continued)
 +
 +
= Notes 24/07 =
 +
 +
* Ramzi: tested end-to-end model with learning
 +
** missing one step, results expected next week
 +
* Yasmine + Yichen: working on pre-processing
 +
** Testing cylinders distortions -> flat rectangle
 +
*** open cv
 +
*** Tesseract performance very poor
 +
 +
Next week:
 +
* Ramzi
 +
** finish test end-to-end model
 +
** increase size of data set to get significant results
 +
* Yasmine + Yichen
 +
** Cylinder unwrapping (classic + deep learning models)
 +
*** review litterature
 +
*** create data set for Ramzi using paid API "perfect label"
 +
** table structure detection : associate bounding boxes to key value pairs
 +
* All
 +
** Create test set with cylindric photos + unwrapped photos
    
= Resources =
 
= Resources =

Navigation menu