Oval Detection Report

2022 November General, Somerset County, MD

Audit Engine version:'v2.32.X'

Run Date: 2026-09-10 17:28:49.018590 Copyright (c) Citizens' Oversight

Return to Master Report Index

Settings in effect for this report

setting	value	note
vendor	'ES&S'
ml_min_detection_probability_pct	96	positions scoring below this are never detected at all
grid_rows_to_drop	2	last N y-grid rows excluded from candidate positions entirely -- no in-code default, vendor-specific unless a job overrides it
ml_target_exclude_regions	none
ml_target_eval_w x ml_target_eval_h	72 x 32	classifier's own evaluation-clip size
target_offset_x/y (page 1)	0, 0
target_offset_x_p1/y_p1 (page 2+)	0, 0
mapping_ocr_detect_only	False
mapping_ocr_match_only	True	map_option_names_ocr()'s own two-flag split -- affects whether map/ml_detected_targets.csv reflects a real detection pass or a reused one, not this report's own generation

Summary

23 of 23 styles have detected oval count exactly matching the EIF-expected count.

No mismatches.

Full snapgrid (every 'top'/'lft' line, edge to edge) in thin red, and the oval classifier's own evaluation-clip boundary at EVERY candidate grid position (not just accepted detections, keepout regions already excluded) in thin green -- lets you check grid registration against the page's real timing marks and spot an eval window overlapping neighboring ballot content directly. On top of that: for every style with detections in map/ml_detected_targets.csv, a bold red box + 'x,y,confidence%' around every detected oval, a bold blue box around the region that will be sent to the AI/OCR matching stage, and a bold green box previewing the eventual crop boundary. 46 images across 23 styles.