Difference between revisions of "Artificial Intelligence/Robotoff/Adding new detections"
Jump to navigation
Jump to search
| (12 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | [[Category:Robotoff]] | ||
== Finding opportunities == | == Finding opportunities == | ||
| + | === Option 1 === | ||
# Download the OCR JSONL | # Download the OCR JSONL | ||
| − | # <pre> | + | # <pre>zgrep -n '05.01.07' FILE | wc -l</pre> |
| − | == | + | |
| + | === Option 2 === | ||
| + | # Right click on an image in a product page, in edit mode (eg 1.jpg) | ||
| + | # Replace `.jpg` by `.json` | ||
| + | # Find patterns or `logoAnnotations` in the JSON | ||
| + | |||
| + | == Adding detections using REGEXes == | ||
https://github.com/openfoodfacts/robotoff/tree/master/robotoff/insights/ocr | https://github.com/openfoodfacts/robotoff/tree/master/robotoff/insights/ocr | ||
=== Add a function to add the desired match === | === Add a function to add the desired match === | ||
| − | + | * Choose the relevant file within the insights/ocr directory (in this case: https://github.com/openfoodfacts/robotoff/blob/master/robotoff/insights/ocr/packager_code.py) | |
* Write the function | * Write the function | ||
| Line 16: | Line 24: | ||
</pre> | </pre> | ||
| − | + | === Add the function to the processing pipeline to plug it to Robotoff === | |
| − | + | This happens in the same file. | |
<pre> | <pre> | ||
PACKAGER_CODE: Dict[str, OCRRegex] = { | PACKAGER_CODE: Dict[str, OCRRegex] = { | ||
| Line 37: | Line 45: | ||
</pre> | </pre> | ||
| − | + | === Grab yourself a sandwich === | |
| − | === | + | == Adding detections using Flashtext == |
| + | https://github.com/openfoodfacts/robotoff/tree/master/data/ocr | ||
| + | === Expanding existing detections === | ||
| + | * Choose a file matching the detection you want to add | ||
| + | In this example: https://github.com/openfoodfacts/robotoff/blob/master/data/ocr/brand_logo_annotation.txt | ||
| + | * Add entries one per line. The raw `logoAnnotation` you find in the OCR JSON is on the left, the value you want to add in the brand field is on the right. | ||
| + | <pre> | ||
| + | alnatura||Alnatura | ||
| + | Andros France||Andros | ||
| + | andros||Andros | ||
| + | </pre> | ||
| − | == | + | === Add a new type of detection === |
| − | + | * Create a file `fishing_flashtext.txt` and add one value to extract per line | |
| + | |||
| + | === Add it to the Robotoff settings === | ||
| + | <pre> | ||
| + | robotoff/settings.py | ||
| + | OCR_LABEL_WHITELIST_DATA_PATH = OCR_DATA_DIR / "label_whitelist.txt" | ||
| + | OCR_FISHING_FLASHTEXT_DATA_PATH = OCR_DATA_DIR / "fishing_flashtext.txt" | ||
| + | </pre> | ||
| + | |||
| + | === Plug it into the OCR pipeline === | ||
| + | <pre> | ||
| + | robotoff/insights/ocr/packager_code.py | ||
| + | codes = text_file_iter(settings.OCR_FISHING_FLASHTEXT_DATA_PATH) | ||
| + | return generate_keyword_processor(("{}||{}".format(c.upper(), c) for c in codes)) | ||
| + | </pre> | ||
Latest revision as of 14:27, 23 February 2023
Finding opportunities
Option 1
- Download the OCR JSONL
zgrep -n '05.01.07' FILE | wc -l
Option 2
- Right click on an image in a product page, in edit mode (eg 1.jpg)
- Replace `.jpg` by `.json`
- Find patterns or `logoAnnotations` in the JSON
Adding detections using REGEXes
https://github.com/openfoodfacts/robotoff/tree/master/robotoff/insights/ocr
Add a function to add the desired match
- Choose the relevant file within the insights/ocr directory (in this case: https://github.com/openfoodfacts/robotoff/blob/master/robotoff/insights/ocr/packager_code.py)
- Write the function
def process_fsc_match(match) -> str:
fsc_code = match.group(1)
return "FSC-{}".format(fsc_code).upper()
Add the function to the processing pipeline to plug it to Robotoff
This happens in the same file.
PACKAGER_CODE: Dict[str, OCRRegex] = {
"fr_emb": OCRRegex(
re.compile(r"emb ?(\d ?\d ?\d ?\d ?\d) ?([a-z])?(?![a-z0-9])"),
field=OCRField.text_annotations,
lowercase=True,
processing_func=process_fr_emb_match,
),
"fsc": OCRRegex(
re.compile(r"fsc.? ?(c\d{6})"),
field=OCRField.text_annotations,
lowercase=True,
processing_func=process_fsc_match,
),
"eu_fr": OCRRegex(
re.compile(
Grab yourself a sandwich
Adding detections using Flashtext
https://github.com/openfoodfacts/robotoff/tree/master/data/ocr
Expanding existing detections
- Choose a file matching the detection you want to add
In this example: https://github.com/openfoodfacts/robotoff/blob/master/data/ocr/brand_logo_annotation.txt
- Add entries one per line. The raw `logoAnnotation` you find in the OCR JSON is on the left, the value you want to add in the brand field is on the right.
alnatura||Alnatura Andros France||Andros andros||Andros
Add a new type of detection
- Create a file `fishing_flashtext.txt` and add one value to extract per line
Add it to the Robotoff settings
robotoff/settings.py OCR_LABEL_WHITELIST_DATA_PATH = OCR_DATA_DIR / "label_whitelist.txt" OCR_FISHING_FLASHTEXT_DATA_PATH = OCR_DATA_DIR / "fishing_flashtext.txt"
Plug it into the OCR pipeline
robotoff/insights/ocr/packager_code.py
codes = text_file_iter(settings.OCR_FISHING_FLASHTEXT_DATA_PATH)
return generate_keyword_processor(("{}||{}".format(c.upper(), c) for c in codes))