Todo List

page Hacking Tesseract V1.03

Fix broken references: 78: Warning: unable to resolve reference to `tess_api' for command 139: Warning: unable to resolve reference to `stacktraces' for command

Member word_blob_quality

outword is word on edges of block vs inword is any word within a block, right (in word_blob_quality())?

Member compute_height_modes

Assuming that the baseline represents the median height, ascenders would be one "mode" and descenders would be a second "mode". Since different ascenders/descenders "ascend"/vs only so high/vs, there may be a half dozen "modes"... but why is the limit (MAX_HEIGHT_MODES) so high (12)?

Member vigorous_noise_removal

Is it ONLY done in preparation for restore_underlined_blobs()?

Member AddToNormProtosList

Not sure if it adds ALL of them

Member ParseArguments

The usage printed on error is out of sync with above

Member ParseArguments

The usage printed on error is out of sync with above

Member WriteNormProtos

Ask Ray for definition of significant and insignificant features and why this is needed to begin with (guess: extract "decisive" features from "fluff" caused by the many different fonts used in training)

Member EvidenceOf

This needs a higher-level explanation of what it does and how

Member TABLE_SIZE

fmg: What effect does dec/increasing this have?

Page Glossary of OCR terms (as used in Tesseract) V0.04

Add reference to entry to read after Edge Detection

while callpicofeat() is called, it's from a somewhat unexpected place

• Baseline normalized Feature: type of 'Extracted Feature', NOT called usually, see GetBaselineFeatures
• Character normalized Feature: type of 'Extracted Feature', see GetIntCharNormFeatures

above really needs a BS-check, courtesy Ray Smith.

Page Glossary of OCR terms (as used in Tesseract) V0.04

Some of these questions (which were for myself) need answers and/or BS-check by someone more knowledgeable.

Page Glossary of OCR terms (as used in Tesseract) V0.04

need to verify exact relationship between color xsition & sign

Page Glossary of OCR terms (as used in Tesseract) V0.04

there have been reports to the contrary on the forums on this exact issue - need to check why

Page Glossary of OCR terms (as used in Tesseract) V0.04

While InitMicroFXVars() called, Microfeatures never extracted...

• Pico-feature: type of 'Extracted Feature',

Page Glossary of OCR terms (as used in Tesseract) V0.04

next part needs work, hard-hat & barf-bag area

Page Glossary of OCR terms (as used in Tesseract) V0.04

How the heck does MySqrt2() work? What's the multiplication by '41943' for?

Page Glossary of OCR terms (as used in Tesseract) V0.04

list should describe whether each object is temporary (i.e,, bucket); can be de/serialized (?block?); exists at the same time but for different purpose (outlines & blobs) and what those different purposes are; is derived from user's image or developer/pre-training; serves a pivotal/conceptually important derivation; etc.

Page Glossary of OCR terms (as used in Tesseract) V0.04

Q: What's the difference between seam and edge (A: Edges are pre-outline while seams are post-row)?

Page Glossary of OCR terms (as used in Tesseract) V0.04

Put "i" dot ref and note here.

Page Glossary of OCR terms (as used in Tesseract) V0.04

Fix broken references:

Page DAWG = Directed Acyclic Word Graphs

Need to add info here on:

• how to view/list words ALREADY IN "tessdata/word-dawg"
• how to CREATE A NEW "tessdata/word-dawg"
• which constants need to be tweaked when adding words to "tessdata/word-dawg"
• which constants need to be tweaked when adding words to "tessdata/user-words" (because a poster on the forums said that after about 5000 words are added guano happens)
• why/what for is rand() used in add_word_to_dawg()
• what to do when the dreaded "DAWG Table is too full" error occurs AFTER Ray Smith's patch is already applied...

Page A note on transitions

None of the functions in blkocc.cpp seem to be called during standard processing of an image - are they only for development?

---