Google MLKit在iOS端无法检测票据问题求助

• 作为Google MLKit新手，我正在开发跨平台（安卓+iOS）的票据/收据检测功能，采用**目标检测（Object Detection）**技术，使用Google的Mobile Object Labeler V1模型，通过react-native-vision-camera处理检测结果。
• Android端用Java实现的逻辑完全正常，能稳定检测到票据；但iOS端使用逻辑一致的Objective-C代码时，始终无法检测到目标票据：日志输出的检测到的物体数量几乎为0，仅极少数情况会识别出键盘。
• 过去4天尝试过多种方案：更换其他TFLite模型、改用异步检测接口、检测前调整图片尺寸等，但问题依旧。

iOS端核心代码 #

#import <Foundation/Foundation.h>
#import <VisionCamera/FrameProcessorPlugin.h>
#import <VisionCamera/Frame.h>
#import <MLKit.h>

@interface VisionScanObjectsFrameProcessorPlugin : NSObject
+ (MLKObjectDetector*) objectDetector;
@end

@implementation VisionScanObjectsFrameProcessorPlugin

+ (MLKObjectDetector*) objectDetector {
  static MLKObjectDetector* objectDetector = nil;
  if (objectDetector == nil) {
    NSString *path = [[NSBundle mainBundle] pathForResource:@"lite-model_object_detection_mobile_object_labeler_v1_1" ofType:@"tflite"];
    MLKLocalModel *localModel = [[MLKLocalModel alloc] initWithPath:path];

    MLKCustomObjectDetectorOptions *options = [[MLKCustomObjectDetectorOptions alloc] initWithLocalModel:localModel];
    options.detectorMode = MLKObjectDetectorModeSingleImage;
    options.shouldEnableClassification = YES;
    options.classificationConfidenceThreshold = @(0.5);
    options.maxPerObjectLabelCount = 3;

    objectDetector = [MLKObjectDetector objectDetectorWithOptions:options];
  }

  return objectDetector;
}

static inline id scanObjects(Frame* frame, NSArray* arguments) {
  MLKVisionImage *image = [[MLKVisionImage alloc] initWithBuffer:frame.buffer];
  image.orientation = frame.orientation; // <-- TODO: is mirrored?

  NSError* error;
  NSArray<MLKObject*>* objects = [[VisionScanObjectsFrameProcessorPlugin objectDetector] resultsInImage:image error:&error];

  NSLog(@"Object detected : %ld", objects.count);

  NSMutableArray* results = [NSMutableArray arrayWithCapacity:objects.count];
  for (MLKObject* object in objects) {
    NSMutableArray* labels = [NSMutableArray arrayWithCapacity:object.labels.count];

    for (MLKObjectLabel* label in object.labels) {
      if (122 == label.index || 188 == label.index || 288 == label.index || 325 == label.index || 357 == label.index || 370 == label.index || 480 == label.index || 510 == label.index || 551 == label.index) {
        [labels addObject:@{
          @"index": [NSNumber numberWithFloat:label.index],
          @"label": label.text,
          @"confidence": [NSNumber numberWithFloat:label.confidence]
        }];
      }
    }

    if (labels.count != 0) {
      [results addObject:@{ 
        @"width": [NSNumber numberWithFloat:object.frame.size.width],
        @"height": [NSNumber numberWithFloat:object.frame.size.height],
        @"top": [NSNumber numberWithFloat:object.frame.origin.y],
        @"left": [NSNumber numberWithFloat:object.frame.origin.x],
        @"frameRotation": [NSNumber numberWithFloat:frame.orientation],
        @"labels": labels
      }];
    }
  }

  return results;
}

VISION_EXPORT_FRAME_PROCESSOR(scanObjects)

@end

内容的提问来源于stack exchange，提问作者Gaylord.P