...
| Code Block | ||||||
|---|---|---|---|---|---|---|
| ||||||
// Input CSV Data: fsa1997018564#True#True#139.37#42.41
{
"loc_id": "fsa1997018564",
"stryker_hole_presence": true,
"border_presence": true,
"mean_grayscale_value": 139.37,
"std_grayscale_value": 42.41
} |
LocationInfo
| Sl. No. | Database Column Name | JSON Metadata Field Name | Field Description | Remarks |
|---|---|---|---|---|
| 1 | id | loc_id | LOC Index | String; |
| 2 | lat | latitude | Latitude coordinate | Float; |
| 3 | long | longitude | Longitude coordinate | Float; |
| 4 | state | state | Abbreviation or state name (if abbreviation not found) or "United States" if no. Other country names are kept as it is. | String; |
| 5 | city | city | City name, when available | String; |
| 6 | county | county | County name, when available (this value is mostly unavailable) | String; |
| Code Block | ||||||
|---|---|---|---|---|---|---|
| ||||||
// Input CSV Data: fsa1997018591#40.106639#-83.767142#OH#Urbana#nop
{
"loc_id": "fsa1997018591",
"latitude": 40.106639,
"longitude": -83.767142,
"state": "OH",
"city": "Urbana",
"county": null
} |
OCRInfo
| Sl. No. | Database Column Name | JSON Metadata Field Name | Field Description | Remarks |
|---|---|---|---|---|
| 1 | id | loc_id | LOC Index | String; |
| 2 | ocr_pred | overall_ocr_prediction | Overall prediction of whether or not text is present in image. 'nop' means OCR found nothing. Where if any one box predicted text then the final prediction is set to T. | String; nop means no text was found; F means after finding possible text regions, it was ruled out not to be text; |
| 3 | scores | ocr_scores | Prediction scores. A string that consists of sets of 3 numbers (separated by semicolon) where, for each OCR text box found, a 0/1 classification value indicating no-text/text predicted, 2 floats indicating classification score for no-text/text | String; |
| 4 | box_sum | num_text_predictions | A count of number of 1's found across text box score sets | Integer; |
| 5 | box_cnt | num_text_boxes | Number of text boxes. Note that box_sum / box_cnt is another possible score instead of the T/F above. | Integer; box_sum is the count of '1's while box_cnt is the count of 'T's. |
| 6 | box_txt | ocr_results | Set of strings separated by semicolon. One string for each text box found in OCR process | String; |
| 7 | box_locs | ocr_text_boxes | A string that consists of sets of 4 numbers (separated by semicolon) one set for each text box, where the numbers are upper left x coordinate, upper left y coordinate, box width, box height. | String; |
...