Multi-Frame Consensus and Decision Gate for Recognizers

    1

    Detection and OCR are the easy part of a camera recognizer; deciding when to act is where the harm happens.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Multi-Frame Consensus and Decision Gate for Recognizers

    Example session with this skill installed

    Process a track of 5 frames for a suspected license plate. Two frames show 'ABC128', three frames show 'ABC12B' with low confidence on the last char. Check against the signed hotlist.

    • Read your context and instructions
    • Compiled the multi-frame consensus

    The tracker has fused 5 distinct frames, excluding 2 duplicates based on grayscale fingerprints. The look-alike rule was triggered for the 8/B ambiguity, resulting in a REVIEW status due to lack of a two-thirds integer majority.

    Decision Result

    FieldValue
    DecisionREVIEW
    TextABC12B
    Reasonslookalike_ambiguity_detected, insufficient_consensus_ratio, possible_target_match
    Review RequiredTrue
    Policy Version1.0.4
    Agreement Ratio3/5 (60%)
    Track PurityHigh
    List StatusVerified (HMAC OK)

    Next steps

    • Route this result to the manual verification queue for human operator confirmation of the final character.
    • Review the CharCandidate confidence scores for the 6th position in the raw telemetry to calibrate future GateConfig floors.
    • Check if the ABC128 string exists in the hotlist; the gate flagged this as REVIEW because a weak read cannot dismiss a potential target.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Detection and OCR are the easy part of a camera recognizer; deciding when to act is where the harm happens. This kit is the fusion and policy layer between any detector/reader pair and the action.

    consensus.py: per-position votes across frames of the same object with one vote per distinct frame (near-duplicate frames excluded by a fingerprint distance so a static scene cannot manufacture agreement); look-alike pairs 0/O, 1/I, 5/S, 8/B and 2/Z resolved only by a strict majority AND two thirds of the electorate tested as integers (a >= 0.67 test failed 2-of-3 by rounding, so a three-frame track could never resolve such a position); the plurality length with a tie broken toward the longer read, because a clipped end is the dominant real failure and insertion order once overwrote a correct read with its truncation; a read one character short aligned at the clipped end so it votes without changing the length; a tracker that associates boxes by IoU or centre distance, keeps separate objects distinct, picks the sharpest observation per frame and computes second-mode support as a track-purity signal.

    decision.py: four outcomes with reasons and a policy version. UNREADABLE for empty, short or low-confidence reads; REVIEW for any unresolved position, too few independent frames, a competing read, or a possible target with any weakness (never NO_MATCH on a possible target); NO_MATCH only for a clean, confident, multi-frame read off the list; MATCH only when the read is on a loaded, signed list and frames, agreement, confidence and purity all pass, and even then a human reviews. Frame agreement is compared as an exact fraction, so 4 of 6 meets two thirds. Thresholds have floors (and the one laxer-when-higher threshold a ceiling) checked on every call, so a configuration cannot weaken the policy after startup. Hotlist verifies an HMAC over canonical entries; a tampered list matches nothing and forces REVIEW on every read, so tampering can never dismiss a genuine target.

    Reference: the outcome table, why the floors exist, what counts as independent evidence, the evaluation discipline (frozen identity-disjoint confirmation set, baseline first, no challenger that raises false target alerts). 10 tests. Python 3.9+, standard library, no network.

    Requires pre-calculated sharpness and fingerprints. Format-specific string validation hooks are provided but empty. No built-in image processing functions.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 18 days ago

    Requires

    Python 3.9+

    Permissions

    Terminal / Shell
    Listed18 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a post-processing layer that aggregates multiple frames of raw OCR data to eliminate errors like motion blur, 'look-alike' character confusion (e.g., 0 vs O), and duplicate triggers from static video.

    The skill is framework-agnostic and written in pure Python 3.9+, making it compatible with any AI agent or pipeline that outputs standard bounding box and string data from libraries like OpenCV or PyTorch.

    The 'Four-Way Gating' system evaluates tracks against your verified hotlist to return one of four definitive states: MATCH, NO_MATCH, REVIEW (for low-confidence or tampered lists), or UNREADABLE, allowing you to automate gate triggers or manual alerts.

    You will receive the complete Python skill package, including the multi-frame fusion engine, the HMAC-secured hotlist validator, and technical documentation with implementation examples.

    Unlike LLMs, which may 'hallucinate' or guess characters based on context, this skill uses deterministic integer math and strict two-thirds majority rules to ensure every decision is grounded in verifiable frame data.

    Yes, the skill includes a feature that uses grayscale frame fingerprints to ensure that multiple frames of a stationary object do not falsely inflate the confidence score of a specific read.

    New in APIs & Backend