License plate recognition

Overview

Automatic license plate recognition (ALPR) turns a camera view of a vehicle into a plate string. The usual chain has four links: find the vehicle, find the plate on it, cut out each character, and decide what each character is. An error in an early link cannot be repaired by a later one 1802.09567 §1.

Only one paper with a card covers this concept so far. The page therefore describes a single design and the constraints it was built for. It does not yet compare alternatives, so the "when to use which" table asks what you have on hand rather than ranking designs.

Variants

Detector cascade with per-vehicle voting (Brazilian plates)

Each link is a separate convolutional detector, so each can be tuned on its own 1802.09567 §4:

1. A vehicle detector on the full frame. The paper uses Fast-YOLO on the SSIG benchmark and YOLOv2 on UFPR-ALPR, because Fast-YOLO reached at most 97.33% vehicle recall there 1802.09567 §5.2.1.
2. A plate detector on a margin-enlarged vehicle crop, keeping only its most confident box 1802.09567 §4.1.
3. A character segmenter on the plate, stretched to a 2.75:1 aspect ratio before it runs. Overlapping boxes are merged, or the weakest are dropped, until seven remain 1802.09567 §4.2.
4. Two character recognisers: one for the first three positions (letters) and one for the last four (digits). Position alone decides which one runs 1802.09567 §4.3.
5. Across all frames of one vehicle, each character position takes its most frequent reading 1802.09567 §4.4.

The author-reported results, with the voting step, are 93.53% of vehicles read completely correct on SSIG 1802.09567 tab. 4 and 78.33% on UFPR-ALPR 1802.09567 tab. 6. Without voting, the per-frame figures are 85.45% and 64.89% 1802.09567 tab. 4 1802.09567 tab. 6. The author-reported speed is 47 FPS on SSIG 1802.09567 tab. 5 and 35 FPS on UFPR-ALPR 1802.09567 tab. 7, on one NVIDIA Titan Xp. The authors do not itemise the cropping and resizing time 1802.09567 §5.1.

Card: Laroca et al., YOLO-based ALPR.

Caveats before reuse:

• Layout-specific. The letter/digit split and the sort order assume a three-letter, four-digit plate, with characters ordered left to right on cars and top to bottom on motorcycles. The authors say the design does not fit countries with several plate layouts 1802.09567 §4.3.
• No code or weights from the authors. The paper links no repository, and it says the models are available for academic use only 1802.09567 §1. Plan to retrain on your own data. Commercial reuse of their weights would need a separate check.
• Thresholds and margins were tuned per dataset on the validation split 1802.09567 §5.
• Training data is small. The SSIG training set has under 800 examples. The authors add flipped and colour-inverted samples, and say augmentation was essential for the letters 1802.09567 §1 1802.09567 §5.1.4. See data augmentation for the general pattern.

The detectors build on Fast-YOLO and YOLOv2, and the character segmenter builds on CR-NET. None of these has a card here, so this page does not use their content.

When to use which

Implementation sketch

The common core of the cascade, in our own words. The per-stage thresholds and margins differ between datasets; see the card for the values.

# Read one vehicle track and vote per character position  [arxiv:1802.09567 §4]
# Input: frames of one vehicle, four trained detectors
# Output: a 7-character plate string

def read_track(frames):
    readings = []
    for frame in frames:
        # Find the vehicle; a frame with no vehicle gives no reading  [§4.1]
        vehicle = top_box(vehicle_detector(frame, thr=0.125))
        if vehicle is None:
            continue
        # Find the plate, keeping the top box even at low confidence  [§4.1]
        plate = top_box(plate_detector(margin_crop(frame, vehicle)))
        # Stretch to 2.75:1, then segment characters  [§4.2]
        plate_img = stretch(margin_crop(frame, plate), aspect=2.75)
        boxes = char_segmenter(plate_img)
        # Reduce to seven boxes by merging or dropping  [§4.2]
        boxes = reduce_to_seven(boxes, overlap_iou)
        # Letters first (three), then digits (four)  [§4.3]
        boxes = sort_for(vehicle.kind, boxes)
        readings.append([
            letter_net(b) if i < 3 else digit_net(b)
            for i, b in enumerate(boxes)
        ])
    # Most frequent reading at each position across frames  [§4.4]
    return [most_common(pos) for pos in zip(*readings)]

Contradictions

None known. Only one source paper is on file. Its per-frame and voted results are reported side by side, not in conflict.

Papers

• Laroca et al., YOLO-based ALPR: a four-stage detector cascade with separate letter and digit recognisers and per-vehicle voting, for Brazilian plates; introduces the UFPR-ALPR dataset.