get_deep_ocr_paramT_get_deep_ocr_paramGetDeepOcrParamGetDeepOcrParamget_deep_ocr_param获取深度光学字符识别参数(算子)

名称

get_deep_ocr_paramT_get_deep_ocr_paramGetDeepOcrParamGetDeepOcrParamget_deep_ocr_param — 返回深度 OCR 模型的参数。

签名

get_deep_ocr_param( : : DeepOcrHandle, GenParamName : GenParamValue)

Herror T_get_deep_ocr_param(const Htuple DeepOcrHandle, const Htuple GenParamName, Htuple* GenParamValue)

void GetDeepOcrParam(const HTuple& DeepOcrHandle, const HTuple& GenParamName, HTuple* GenParamValue)

HTuple HDlModelOcr::GetDeepOcrParam(const HString& GenParamName) const

HTuple HDlModelOcr::GetDeepOcrParam(const char* GenParamName) const

HTuple HDlModelOcr::GetDeepOcrParam(const wchar_t* GenParamName) const   ( Windows only)

static void HOperatorSet.GetDeepOcrParam(HTuple deepOcrHandle, HTuple genParamName, out HTuple genParamValue)

HTuple HDlModelOcr.GetDeepOcrParam(string genParamName)

def get_deep_ocr_param(deep_ocr_handle: HHandle, gen_param_name: str) -> Sequence[HTupleElementType]

def get_deep_ocr_param_s(deep_ocr_handle: HHandle, gen_param_name: str) -> HTupleElementType

描述

get_deep_ocr_paramget_deep_ocr_paramGetDeepOcrParamGetDeepOcrParamGetDeepOcrParamget_deep_ocr_param 返回深度 OCR 模型 DeepOcrHandleDeepOcrHandleDeepOcrHandleDeepOcrHandledeepOcrHandledeep_ocr_handle 中参数 GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name 的参数值 GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value

参数可适用于整个模型,也可针对特定组件进行设置。下表概述了可设置的参数、可检索的参数以及它们适用的模型部分。

GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name参数名称 Model模型 Det. comp.检测组件 Recog. comp.识别组件
'device'"device""device""device""device""device"
'detection_device'"detection_device""detection_device""detection_device""detection_device""detection_device"
'detection_image_dimensions'"detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions"
'detection_image_height'"detection_image_height""detection_image_height""detection_image_height""detection_image_height""detection_image_height"
'detection_image_size'"detection_image_size""detection_image_size""detection_image_size""detection_image_size""detection_image_size"
'detection_image_width'"detection_image_width""detection_image_width""detection_image_width""detection_image_width""detection_image_width"
'detection_min_character_score'"detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score"
'detection_min_link_score'"detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score"
'detection_min_word_area'"detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area"
'detection_min_word_score'"detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score"
'detection_model'"detection_model""detection_model""detection_model""detection_model""detection_model"
'detection_orientation'"detection_orientation""detection_orientation""detection_orientation""detection_orientation""detection_orientation"
'detection_sort_by_line'"detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line"
'detection_tiling'"detection_tiling""detection_tiling""detection_tiling""detection_tiling""detection_tiling"
'detection_tiling_overlap'"detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap"
'recognition_alphabet'"recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet"
'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal"
'recognition_alphabet_mapping'"recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping"
'recognition_batch_size'"recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size"
'recognition_device'"recognition_device""recognition_device""recognition_device""recognition_device""recognition_device"
'recognition_image_dimensions'"recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions"
'recognition_image_height'"recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height"
'recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width"
'recognition_model'"recognition_model""recognition_model""recognition_model""recognition_model""recognition_model"
'recognition_num_char_candidates'"recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates"
因此,符号和缩写表示以下含义:

在使用 optimize_dl_model_for_inferenceoptimize_dl_model_for_inferenceOptimizeDlModelForInferenceOptimizeDlModelForInferenceOptimizeDlModelForInferenceoptimize_dl_model_for_inference 优化模型后,仅可设置不改变模型架构的参数。这些参数的列表可在 optimize_dl_model_for_inferenceoptimize_dl_model_for_inferenceOptimizeDlModelForInferenceOptimizeDlModelForInferenceOptimizeDlModelForInferenceoptimize_dl_model_for_inference 中查阅。以下按参数所适用的模型部分进行分类说明:

整个模型:

'device'"device""device""device""device""device"

将在其上执行模型的设备句柄。要获取所有可用且可能支持深度 OCR 的计算设备句柄元组,请使用 query_available_dl_devicesquery_available_dl_devicesQueryAvailableDlDevicesQueryAvailableDlDevicesQueryAvailableDlDevicesquery_available_dl_devices

请注意,设备可针对单个组件进行重置,此时仅该句柄设备上可能残留的模型部分(例如剩余组件)将被执行。

默认值: 默认设备的句柄,因此在使用 get_systemget_systemGetSystemGetSystemGetSystemget_system 查询包含 'cuda_devices'"cuda_devices""cuda_devices""cuda_devices""cuda_devices""cuda_devices" 的设备列表时,该句柄对应索引为 0 的 GPU。若无可用设备,则返回空元组。

检测组件:

'detection_device'"detection_device""detection_device""detection_device""detection_device""detection_device"检测设备:

此参数将设置执行深度 OCR 模型检测组件的设备。更多说明请参见设备 'device'"device""device""device""device""device"

默认值: 与设备 'device'"device""device""device""device""device" 相同。

'detection_image_dimensions'"detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions"检测图像维度:

元组包含检测组件将处理的图像维度 ('detection_image_width'"detection_image_width""detection_image_width""detection_image_width""detection_image_width""detection_image_width"'detection_image_height'"detection_image_height""detection_image_height""detection_image_height""detection_image_height""detection_image_height"、通道数)。

输入图像将按 'detection_image_dimensions'"detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions" 进行缩放,同时保持原始宽高比。缩放后的图像如有必要将用灰度值 0 进行填充。因此,修改 'detection_image_height'"detection_image_height""detection_image_height""detection_image_height""detection_image_height""detection_image_height"'detection_image_width'"detection_image_width""detection_image_width""detection_image_width""detection_image_width""detection_image_width" 参数会影响检测结果。

默认值: [1024, 1024, 3]

'detection_image_height'"detection_image_height""detection_image_height""detection_image_height""detection_image_height""detection_image_height"检测图像高度:

检测组件将处理的图像高度。这意味着网络在处理前会将输入图像缩放至该高度上限,从而保持其宽高比。因此该尺寸会影响检测结果。

模型架构要求高度必须是 32 的倍数。若不符合此要求,则将高度向上舍入至最接近的 32 的整数倍。

建议值: 768, 1024, 1280

默认值: 1024

'detection_image_size'"detection_image_size""detection_image_size""detection_image_size""detection_image_size""detection_image_size"检测图像尺寸:

包含检测组件将处理的图像尺寸的元组('detection_image_width'"detection_image_width""detection_image_width""detection_image_width""detection_image_width""detection_image_width"'detection_image_height'"detection_image_height""detection_image_height""detection_image_height""detection_image_height""detection_image_height")。

默认值: [1024, 1024]

'detection_image_width'"detection_image_width""detection_image_width""detection_image_width""detection_image_width""detection_image_width"检测图像宽度:

检测组件将处理的图像宽度。这意味着网络在处理前会将输入图像缩放至该宽度上限,从而保持其宽高比。因此该尺寸会影响检测结果。

模型架构要求宽度必须是 32 的倍数。若非如此,则将宽度向上舍入至最接近的 32 的整数倍。

建议值: 768, 1024, 1280

默认值: 1024

'detection_min_character_score'"detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score"检测最小字符分数:

参数 'detection_min_character_score'"detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score" 用于指定字符分数图估算字符尺寸的下限阈值。通过调整该参数,可将建议的实例分割开来,或将相邻实例合并。

值范围:

默认值: 0.5

'detection_min_link_score'"detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score"检测最小连接分数:

参数 'detection_min_link_score'"detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score" 定义了两个定位字符之间所需的最低连接分数,以将这些字符识别为连贯的单词。

值范围:

默认值: 0.3

'detection_min_word_area'"detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area"检测最小单词面积:

参数 'detection_min_word_area'"detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area" 定义了被检测到的单词必须达到的最小尺寸才能被建议。该参数可用于过滤尺寸过小的建议词。

值范围:

默认值: 10.

'detection_min_word_score'"detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score"检测最小单词分数:

参数 'detection_min_word_score'"detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score" 定义了定位实例必须达到的最低分数阈值,才能被建议为有效词汇。通过此参数可过滤掉不确定词汇。

值范围:

默认值: 0.7

'detection_model'"detection_model""detection_model""detection_model""detection_model""detection_model"检测模型:

算子 get_deep_ocr_paramget_deep_ocr_paramGetDeepOcrParamGetDeepOcrParamGetDeepOcrParamget_deep_ocr_param 返回用于单词识别的深度 OCR 模型组件句柄。通过 set_deep_ocr_paramset_deep_ocr_paramSetDeepOcrParamSetDeepOcrParamSetDeepOcrParamset_deep_ocr_param 可指定句柄、文件名或特殊字符串。特殊字符串仅允许使用 'default'"default""default""default""default""default"'compact'"compact""compact""compact""compact""compact"。若为 'default'"default""default""default""default""default",则加载默认预训练的词检测组件(即 'pretrained_deep_ocr_detection.hdl'"pretrained_deep_ocr_detection.hdl""pretrained_deep_ocr_detection.hdl""pretrained_deep_ocr_detection.hdl""pretrained_deep_ocr_detection.hdl""pretrained_deep_ocr_detection.hdl"。诺为 'compact'"compact""compact""compact""compact""compact",则加载更高效的词检测组件(即 'pretrained_deep_ocr_detection_compact.hdl'"pretrained_deep_ocr_detection_compact.hdl""pretrained_deep_ocr_detection_compact.hdl""pretrained_deep_ocr_detection_compact.hdl""pretrained_deep_ocr_detection_compact.hdl""pretrained_deep_ocr_detection_compact.hdl")。若传入值为字符串,则模型将内部加载且批处理大小设为 1

建议值: 'default'"default""default""default""default""default", 'compact'"compact""compact""compact""compact""compact", filename.

默认值: 'default'"default""default""default""default""default"

'detection_orientation'"detection_orientation""detection_orientation""detection_orientation""detection_orientation""detection_orientation"检测方向:

此参数用于为单词检测设置预定义的方位角。若要恢复使用内部方位角估算的默认行为,请将 'detection_orientation'"detection_orientation""detection_orientation""detection_orientation""detection_orientation""detection_orientation" 设置为 'auto'"auto""auto""auto""auto""auto"

值范围:

默认值: 'auto'"auto""auto""auto""auto""auto"

'detection_sort_by_line'"detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line"按行检测排序:

单词(words)根据定位单词(word)实例的方向按行排序。若需按行和列方向排序,则需将参数 'detection_sort_by_line'"detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line" 设置为 'false'"false""false""false""false""false"

默认值: 'true'"true""true""true""true""true"

'detection_tiling'"detection_tiling""detection_tiling""detection_tiling""detection_tiling""detection_tiling"检测平铺:

输入图像会被自动分割为多个尺寸为 'detection_image_size'"detection_image_size""detection_image_size""detection_image_size""detection_image_size""detection_image_size" 的重叠图块,这些图块由检测组件分别处理。这使得系统能够处理远大于实际 'detection_image_size'"detection_image_size""detection_image_size""detection_image_size""detection_image_size""detection_image_size" 的图像,而无需对输入图像进行缩放。因此,当 'detection_tiling'"detection_tiling""detection_tiling""detection_tiling""detection_tiling""detection_tiling" = {'true'} 时,输入图像在处理前不会被缩放。

默认值: 'false'"false""false""false""false""false"

'detection_tiling_overlap'"detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap"检测平铺重叠:

该参数定义输入图像分割时相邻图块的重叠程度(参见 'detection_tiling'"detection_tiling""detection_tiling""detection_tiling""detection_tiling""detection_tiling")。重叠范围以像素为单位表示。

值范围:

默认值: 64

识别组件:

'recognition_alphabet'"recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet"识别字母表:

深度 OCR 模型能够识别的字符集。

它包含所有未映射到内部字母表空白字符的字符(参见参数 'recognition_alphabet_mapping'"recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping"'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal")。

字母表可根据需要进行修改或扩展。通过此参数修改字母表时,系统将编辑内部字母表及其映射关系,同时尽量保持内部字母表的长度不变。修改字母表后,建议使用应用程序特定数据对模型进行重新训练(参见 HDevelop 示例 deep_ocr_recognition_training_workflow.hdev)。对于先前未识别的字符,需要更多训练数据。

请注意,若内部字母表的长度发生变化,则最后的模型层需进行随机初始化,此时模型输出将为随机字符串(参见 'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal")。此种情况下必须重新训练模型。

'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal"识别字母表内部:

深度 OCR 识别组件经过训练的完整字符集。

内部字母表的首字符为特殊字符。在预训练模型中,该字符被指定为空白符(U+2800),切勿与空格混淆。空白字符不会出现在单词输出中,但可能出现在报告的候选字符列表里。该字符是必需的且不可省略。若修改内部字母表,首字符必须保持为空白字符。此外,当使用 'recognition_alphabet'"recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet" 参数变更字母表时,系统会自动将空白符号添加至字符集。

该元组的长度对应于模型中最后一个卷积层的深度。若长度发生变化,则最后一个卷积层及其之后的所有层都需要调整大小,并可能需要重新随机初始化。此类变更后,必须重新训练模型(参见 HDevelop 示例 deep_ocr_recognition_training_workflow.hdev)。

建议使用参数 'recognition_alphabet'"recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet" 来更改字母表,因为它会自动尝试保持内部字母表的长度。

'recognition_alphabet_mapping'"recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping"识别字母映射:

整数索引元组。

该映射由模型在每个单词的解码步骤中应用。该映射将覆盖 'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal" 字符表中某个字符,用 'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal" 字符表中特定索引处的字符替换该字符。

在解码步骤中,每个预测结果将根据该元组中指定的索引进行映射。该元组的长度必须与 'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal" 元组相同。映射中每个整数索引的取值范围必须在 0 到 |'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal"|-1 之间。

在某些应用场景中,将特定字符映射为其他字符可能有所帮助。例如,若应用程序中仅出现数字词汇,则可将字符“O”映射为“0”字符,而无需重新训练模型。

如果某个条目包含数字 0,则在单词中对应于 'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal" 的字符将不会被解码。

'recognition_batch_size'"recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size"识别批次大小:

批处理中传输至设备内存并在识别组件中并行处理的图像数量。更多详情请参阅 apply_dl_modelapply_dl_modelApplyDlModelApplyDlModelApplyDlModelapply_dl_model 参考文档中关于 'batch_size'"batch_size""batch_size""batch_size""batch_size""batch_size" 参数的说明。该参数可用于优化特定深度学习设备上 apply_deep_ocrapply_deep_ocrApplyDeepOcrApplyDeepOcrApplyDeepOcrapply_deep_ocr 的运行时性能。若识别组件需处理多个输入(单词words),并行处理多个输入可加速 apply_deep_ocrapply_deep_ocrApplyDeepOcrApplyDeepOcrApplyDeepOcrapply_deep_ocr 的执行。但需注意,增大 'recognition_batch_size'"recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size" 将消耗更多设备内存。

默认值: 1

'recognition_device'"recognition_device""recognition_device""recognition_device""recognition_device""recognition_device"识别设备:

此参数将设置执行深度 OCR 模型识别组件的设备。更多说明请参见 'device'"device""device""device""device""device"

默认值: 与设备 'device'"device""device""device""device""device" 相同。

'recognition_image_dimensions'"recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions"识别图像维度:

元组包含图像维度('recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width"'recognition_image_height'"recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height"、 通道数),识别组件将处理该图像。

这意味着,网络会首先将输入图像的局部区域放大至 'recognition_image_height'"recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height",同时保持输入图像的宽高比。若放大后图像的宽度小于 'recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width",则在图像右侧填充灰度值为 0 的区域;若放大后图像的宽度大于 'recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width",则将图像缩放至 'recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width"

默认值: [120, 32, 1]

'recognition_image_height'"recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height"识别图像高度:

图像识别组件将处理的图像高度。

默认值: 32

'recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width"识别图像宽度

图像识别组件将处理的图像宽度。

默认值: 120

'recognition_model'"recognition_model""recognition_model""recognition_model""recognition_model""recognition_model"识别模型:

算子 get_deep_ocr_paramget_deep_ocr_paramGetDeepOcrParamGetDeepOcrParamGetDeepOcrParamget_deep_ocr_param 返回用于单词识别的深度 OCR 模型组件句柄。

使用 set_deep_ocr_paramset_deep_ocr_paramSetDeepOcrParamSetDeepOcrParamSetDeepOcrParamset_deep_ocr_param 时,可指定句柄、文件名或 'default'"default""default""default""default""default"。若为 'default'"default""default""default""default""default",则加载预训练的单词识别组件(即 'pretrained_deep_ocr_recognition.hdl'"pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl""pretrained_deep_ocr_recognition.hdl")。若给定值为字符串,则模型在内部加载,批处理大小设为 1

建议值: 'default'"default""default""default""default""default", filename.

默认值: 'default'"default""default""default""default""default"

'recognition_num_char_candidates'"recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates"识别候选字符数量:

控制算子 apply_deep_ocrapply_deep_ocrApplyDeepOcrApplyDeepOcrApplyDeepOcrapply_deep_ocr 的结果中报告的字符候选项数量。

默认值: 3

执行信息

参数

DeepOcrHandleDeepOcrHandleDeepOcrHandleDeepOcrHandledeepOcrHandledeep_ocr_handle (输入控制)  deep_ocr HDlModelOcr, HTupleHHandleHTupleHtuple (handle) (IntPtr) (HHandle) (handle)

深度 OCR 模型的句柄。

GenParamNameGenParamNameGenParamNameGenParamNamegenParamNamegen_param_name (输入控制)  attribute.name HTuplestrHTupleHtuple (string) (string) (HString) (char*)

通用参数的名称。

默认值: 'recognition_model' "recognition_model" "recognition_model" "recognition_model" "recognition_model" "recognition_model"

值列表: 'detection_device'"detection_device""detection_device""detection_device""detection_device""detection_device", 'detection_image_dimensions'"detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions""detection_image_dimensions", 'detection_image_height'"detection_image_height""detection_image_height""detection_image_height""detection_image_height""detection_image_height", 'detection_image_size'"detection_image_size""detection_image_size""detection_image_size""detection_image_size""detection_image_size", 'detection_image_width'"detection_image_width""detection_image_width""detection_image_width""detection_image_width""detection_image_width", 'detection_min_character_score'"detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score""detection_min_character_score", 'detection_min_link_score'"detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score""detection_min_link_score", 'detection_min_word_area'"detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area""detection_min_word_area", 'detection_min_word_score'"detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score""detection_min_word_score", 'detection_model'"detection_model""detection_model""detection_model""detection_model""detection_model", 'detection_orientation'"detection_orientation""detection_orientation""detection_orientation""detection_orientation""detection_orientation", 'detection_sort_by_line'"detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line""detection_sort_by_line", 'detection_tiling'"detection_tiling""detection_tiling""detection_tiling""detection_tiling""detection_tiling", 'detection_tiling_overlap'"detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap""detection_tiling_overlap", 'recognition_alphabet'"recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet""recognition_alphabet", 'recognition_alphabet_internal'"recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal""recognition_alphabet_internal", 'recognition_alphabet_mapping'"recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping""recognition_alphabet_mapping", 'recognition_batch_size'"recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size""recognition_batch_size", 'recognition_device'"recognition_device""recognition_device""recognition_device""recognition_device""recognition_device", 'recognition_image_dimensions'"recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions""recognition_image_dimensions", 'recognition_image_height'"recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height""recognition_image_height", 'recognition_image_width'"recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width""recognition_image_width", 'recognition_model'"recognition_model""recognition_model""recognition_model""recognition_model""recognition_model", 'recognition_num_char_candidates'"recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates""recognition_num_char_candidates"

GenParamValueGenParamValueGenParamValueGenParamValuegenParamValuegen_param_value (输出控制)  attribute.value(-array) HTupleSequence[HTupleElementType]HTupleHtuple (integer / handle / string / real) (int / long / HHandle / string / double) (Hlong / HHandle / HString / double) (Hlong / handle / char* / double)

通用参数的值。

结果

如果参数有效,算子 get_deep_ocr_paramget_deep_ocr_paramGetDeepOcrParamGetDeepOcrParamGetDeepOcrParamget_deep_ocr_param 返回值 2 ( H_MSG_TRUE )。如有必要,则抛出异常。

可能的前趋

create_deep_ocrcreate_deep_ocrCreateDeepOcrCreateDeepOcrCreateDeepOcrcreate_deep_ocr, set_deep_ocr_paramset_deep_ocr_paramSetDeepOcrParamSetDeepOcrParamSetDeepOcrParamset_deep_ocr_param

可能的后继

set_deep_ocr_paramset_deep_ocr_paramSetDeepOcrParamSetDeepOcrParamSetDeepOcrParamset_deep_ocr_param, apply_deep_ocrapply_deep_ocrApplyDeepOcrApplyDeepOcrApplyDeepOcrapply_deep_ocr

另见

set_deep_ocr_paramset_deep_ocr_paramSetDeepOcrParamSetDeepOcrParamSetDeepOcrParamset_deep_ocr_param

模块

光学字符识别/光学字符验证