OCR之find_text_dongle.hdev

* This example demonstrates how to use the operator
* find_text to segment text in an image before
* performing OCR.
* 关闭更新
dev_update_off ()
dev_close_window ()
*读取图像
read_image (Image, 'ocr/dongle_01')
*开启窗体
dev_open_window_fit_image (Image, 0, 0, -1, -1, WindowHandle)
*设置显示字体
set_display_font (WindowHandle, 14, 'mono', 'true', 'false')
* 读取训练好的OCR文件
* Read the OCR classifier from file
read_ocr_class_mlp ('DotPrint_NoRej', OCRHandle)
* 创建一个文字读取器
* Create the text model and specify the text properties
create_text_model_reader ('manual', [], TextModel)
* 设置一些参数，字符宽高，是否是点印，文字行数，是否识别返回标点，是否返回分隔符等
set_text_model_param (TextModel, 'manual_char_width', 24)
set_text_model_param (TextModel, 'manual_char_height', 33)
set_text_model_param (TextModel, 'manual_is_dotprint', 'true')
set_text_model_param (TextModel, 'manual_max_line_num', 2)
set_text_model_param (TextModel, 'manual_return_punctuation', 'false')
set_text_model_param (TextModel, 'manual_return_separators', 'false')
set_text_model_param (TextModel, 'manual_stroke_width', 4)
set_text_model_param (TextModel, 'manual_eliminate_horizontal_lines', 'true')
* *定义一行文字的机构情况：第一行定义为"6 1 8"表示有两个分隔符吧这段文字分割成3部分
*因为"/"有时候被定义为字符，有时候被定义为分隔符，所以第二段定义为两种方式。”8 10“有一个分隔符和“19“ 没有分隔符
*Define different text line structures for each line.
* Note that for the second line two structures are defined,
* because sometimes the '/' is classified as separator and
* sometimes as character.

set_text_model_param (TextModel, 'manual_text_line_structure_0', '6 1 8')
set_text_model_param (TextModel, 'manual_text_line_structure_1', '8 10')
set_text_model_param (TextModel, 'manual_text_line_structure_2', '19')
*定义两段文字的构成方式
* Define the regular expression, which is later used
* in do_ocr_word_mlp to increase the robustness of the OCR.
TextPattern1 := '(FLEXID[0-9][A-Z][0-9]{3}[A-F0-9]{4})'
TextPattern2 := '([A-Z]{3}[0-9]{5}.?[A-Z][0-9]{4}[A-Z][0-9]{4})'
Expression := TextPattern1 + '|' + TextPattern2
*
* Main loop
*主循环
NumImages := 8
for I := 1 to NumImages by 1
    *读取图像
    read_image (Image, 'ocr/dongle_' + I$'02')
    * 处理图像
    * Preprocessing:
    *
    * The domain is reduced to the dark area where the
    * text is assumed to be found.
    * Then, the contrast is improved and the image
    * is aligned horizontally
    *二值化阈值分割
    binary_threshold (Image, Region, 'max_separability', 'dark', UsedThreshold)
    *矩形掩码开运算，抑制噪声
    opening_rectangle1 (Region, RegionOpening, 400, 50)
    *矩形掩码腐蚀运算
    erosion_rectangle1 (RegionOpening, RegionOpening, 11, 11)
    *联通区域
    connection (RegionOpening, ConnectedRegions)
    *选择目标区域
    select_shape_std (ConnectedRegions, SelectedRegion, 'max_area', 70)
    *裁剪区域
    reduce_domain (Image, SelectedRegion, ImageReduced)
    *增强对比度
    scale_image_max (ImageReduced, ImageScaleMax)
    *求目标区域中文字的与水平轴的角度
    text_line_orientation (SelectedRegion, ImageScaleMax, 30, rad(-30), rad(30), OrientationAngle)
    *把图转到文字水平位置
    rotate_image (ImageScaleMax, ImageRotate, deg(-OrientationAngle), 'constant')
    * 识别文字，显示每一个目标区域识别结果
    * Find text and display results for every segmented region
    find_text (ImageRotate, TextModel, TextResult)
    *获取文字行数
    get_text_result (TextResult, 'manual_num_lines', NumLines)
    *显示转正图像
    dev_display (ImageRotate)
    *线一行一行的去识别每一个字符
    for J := 0 to NumLines - 1 by 1
        *获取第一行内容
        get_text_object (Line, TextResult, ['manual_line',J])
        * The OCR uses regular expressions to read the text
        * more robustly.
        *这个算子的意思是，识别有关联的一组文字,用do_ocr_multi_class_mlp 也是完全可以的
        *do_ocr_multi_class_mlp (Line, ImageRotate, OCRHandle, Class1, Confidence1)
        do_ocr_word_mlp (Line, ImageRotate, OCRHandle, Expression, 3, 5, Class, Confidence, Word, Score)
        * 显示结果
        * Display results
        *求一行的最小外接矩形
        smallest_rectangle1 (Line, Row1, Column1, Row2, Column2)
        *获取识别到的文字数量
        count_obj (Line, NumberOfCharacters)
        *设置显示颜色
        dev_set_colored (6)
        *显示一行
        dev_display (Line)
        *设置显示颜色为白色
        dev_set_color ('white')
        *在OCR区域下方，显示对应的字符
        for K := 1 to NumberOfCharacters by 1
            select_obj (Line, Character, K)
            set_tposition (WindowHandle, Row2[0] + 4, Column1[K - 1])
            write_string (WindowHandle, Word{K - 1})
        endfor
    endfor
    *如果图片没识别完，就在右下角继续显示'Press F5 to continue'
    if (I < NumImages)      
        disp_continue_message (WindowHandle, 'black', 'true')
        stop ()
    endif
    *销毁句柄释放内存
    * Clean up memory
    clear_text_result (TextResult)
endfor
* Clean up memory
*清除Text_model句柄
clear_text_model (TextModel)
*清除OCR句柄
clear_ocr_class_mlp (OCRHandle)