ANSCORE/modules/ANSOCR/ANSONNXOCR/PaddleOCRV5Engine.h

#pragma once

#include "ONNXOCRTypes.h"
#include "ONNXOCRDetector.h"
#include "ONNXOCRClassifier.h"
#include "ONNXOCRRecognizer.h"

#include <memory>
#include <mutex>
#include <string>
#include <vector>

namespace ANSCENTER {
namespace onnxocr {

// PaddleOCR V5 pipeline engine: Detection -> (Classification) -> Recognition
// Mirrors the PaddleOCR::PPOCR interface for drop-in replacement
class PaddleOCRV5Engine {
public:
    PaddleOCRV5Engine() = default;
    ~PaddleOCRV5Engine() = default;

    // Initialize the OCR pipeline
    // clsModelPath can be empty to skip classification
    bool Initialize(const std::string& detModelPath,
                    const std::string& clsModelPath,
                    const std::string& recModelPath,
                    const std::string& dictPath);

    // Run full OCR pipeline on an image
    // Returns results matching PaddleOCR::OCRPredictResult format
    std::vector<OCRPredictResult> ocr(const cv::Mat& img);

    // Run recognizer only on a pre-cropped text image (no detection step)
    TextLine recognizeOnly(const cv::Mat& croppedImage);

    // Configuration setters (matching OCRModelConfig parameters)
    void SetDetMaxSideLen(int val)          { _maxSideLen = val; }
    void SetDetDbThresh(float val)          { _detDbThresh = val; }
    void SetDetBoxThresh(float val)         { _detBoxThresh = val; }
    void SetDetUnclipRatio(float val)       { _detUnclipRatio = val; }
    void SetClsThresh(float val)            { _clsThresh = val; }
    void SetUseDilation(bool val)           { _useDilation = val; }

private:
    std::unique_ptr<ONNXOCRDetector>    detector_;
    std::unique_ptr<ONNXOCRClassifier>  classifier_;   // nullptr if not used
    std::unique_ptr<ONNXOCRRecognizer>  recognizer_;

    std::recursive_mutex _mutex;

    // Detection parameters
    int   _maxSideLen    = kDetMaxSideLen;
    float _detDbThresh   = kDetDbThresh;
    float _detBoxThresh  = kDetBoxThresh;
    float _detUnclipRatio = kDetUnclipRatio;
    bool  _useDilation   = false;

    // Classifier parameters
    float _clsThresh     = kClsThresh;

    bool _initialized = false;
};

} // namespace onnxocr
} // namespace ANSCENTER