try (CraftTextDetector detector = CraftTextDetector.builder().build()) {
    List<TextRegion> regions = detector.detect(Path.of("document.jpg"));
    for (TextRegion r : regions) {
        System.out.printf("Text at [%.0f, %.0f, %.0f, %.0f] (confidence=%.2f)%n",
            r.box().x1(), r.box().y1(), r.box().x2(), r.box().y2(),
            r.confidence());
    }
}

Model Details

Property	Value
Architecture	VGG16-BN backbone + U-Net decoder
Task	Text detection (character-level region + affinity maps)
Training data	SynthText + ICDAR 2013/2017 (MLT)
Weights	`craft_mlt_25k.pth` from clovaai/CRAFT-pytorch
ONNX opset	17
Input	`[batch, 3, height, width]` — RGB, ImageNet-normalized, dimensions must be multiples of 32
Output: score_map	`[batch, height/2, width/2, 2]` — channel 0: region score, channel 1: affinity score
Output: feature_map	`[batch, 32, height/2, width/2]` — intermediate features (optional, for refinement)
Dynamic axes	Batch, height, and width are dynamic

Preprocessing

Resize maintaining aspect ratio (long side to target size, e.g. 1280)
Round both dimensions to nearest multiple of 32
ImageNet normalization: (pixel / 255 - mean) / std
- mean = [0.485, 0.456, 0.406]
- std = [0.229, 0.224, 0.225]
NCHW layout: [1, 3, H, W]

Postprocessing

Combine: clip(region_score + affinity_score, 0, 1)
Binary threshold at low_text_threshold (default 0.4)
Connected component labeling (4-connectivity)
For each component: compute mean region score, filter by text_threshold (default 0.7)
Extract axis-aligned bounding box, scale back to original image coordinates

Original Paper

Baek, Y., Lee, B., Han, D., Yun, S., & Lee, H. (2019). Character Region Awareness for Text Detection. CVPR 2019. arXiv:1904.01941

License

The original CRAFT model weights are released under the MIT License by Clova AI Research (NAVER Corp).

inference4j/craft-mlt-25k

CRAFT Text Detection (MLT 25K) — ONNX

Usage with inference4j

Model Details

Preprocessing

Postprocessing

Original Paper

License

inference4j/
craft-mlt-25k