HALCON示例程序train_characters_ocr.hdev使用SVM分類器訓練字體

小哥哥小姐姐覺得有用點個贊唄！

示例程序源碼（加注釋）

藍色字體均為算子解釋鏈接，可以前往查看解答

• 關于顯示類函數解釋
  read_image (Image, ‘ocr/chars_training_01.png’)
• 獲取單通道圖像的指針
  get_image_pointer1 (Image, Pointer, Type, Width, Height)
  dev_close_window ()
  dev_open_window (0, 0, Width, Height, ‘white’, WindowHandle)
  set_display_font (WindowHandle, 12, ‘mono’, ‘true’, ‘false’)
  dev_set_draw (‘margin’)
  dev_set_line_width (2)
  dev_display (Image)
  dev_update_window (‘off’)
  dev_update_pc (‘off’)
  dev_update_var (‘off’)
• 創建一個 SVM 分類器內容，從A-G
  ClassNames := [‘A’,‘B’,‘C’,‘D’,‘E’,‘F’,‘G’]
• 創建OCR分類器
  create_ocr_class_svm (8, 10, ‘constant’, [‘convexity’,‘num_holes’,‘projection_horizontal’,‘projection_vertical’], ClassNames, ‘rbf’, 0.02, 0.05, ‘one-versus-one’, ‘normalization’, 10, OCRHandle)

for i := 1 to 7 by 1
read_image (Image, ‘ocr/chars_training_’ + i$’.2d’)
dev_display (Image)
* halcon自定義函數大括號內為其代碼
get_regions (Image, SortedRegions)
{
dev_set_color (‘white’)

• 二值化
  threshold (Image, Region, 0, 125)
• 分割連通域
  connection (Region, ConnectedRegions)
• 通過面積篩選區域
  select_shape (ConnectedRegions, SelectedRegions, ‘area’, ‘and’, 50, 999999)
• 對區域進行排序
  sort_region (SelectedRegions, SortedRegions, ‘character’, ‘true’, ‘row’)
  return ()
  }
  • 對元素進行計數
    count_obj (SortedRegions, NumberObjects)
    for j := 1 to NumberObjects by 1
  • 選取數組內指定元素
    select_obj (SortedRegions, ObjectSelected, j)
    if (i == 1 and j == 1)
    • 將訓練字符儲存到指定文件
      write_ocr_trainf (ObjectSelected, Image, ClassNames[j - 1], ‘train_characters_ocr.trf’)
      else
    • 向訓練文件中添加對象
      append_ocr_trainf (ObjectSelected, Image, ClassNames[j - 1], ‘train_characters_ocr.trf’)
      endif
      dev_set_color (‘gray’)
      dev_display (ObjectSelected)
      disp_message (WindowHandle, ClassNames[j - 1], ‘window’, 10, 10 + (j * 20), ‘black’, ‘true’)
      endfor
      disp_continue_message (WindowHandle, ‘black’, ‘true’)
      stop ()
      endfor
      讀訓練文件并轉化為圖像
      read_ocr_trainf (Characters, ‘train_characters_ocr.trf’, CharacterNames)
      count_obj (Characters, NumberCharacters)

for i := 1 to NumberCharacters by 1
select_obj (Characters, CharacterSelected, i)
dev_clear_window ()
dev_display (CharacterSelected)
disp_message (WindowHandle, CharacterNames[i - 1], ‘window’, 10, 10, ‘black’, ‘true’)
endfor

• 訓練OCR分類器
  trainf_ocr_class_svm (OCRHandle, ‘train_characters_ocr.trf’, 0.001, ‘default’)
• 縮減SVM分類器，以減少分類所用時間。
  reduce_ocr_class_svm (OCRHandle, ‘bottom_up’, 2, 0.001, OCRHandleReduced)
• 將訓練出的分類器寫入文件
  write_ocr_class_svm (OCRHandleReduced, ‘font_characters_ocr’)
• 清除OCR分類器
  clear_ocr_class_svm (OCRHandle)
  clear_ocr_class_svm (OCRHandleReduced)
  stop ()
  dev_clear_window ()
  disp_message (WindowHandle, ‘No more lines to execute’, ‘window’, 10, 10, ‘black’, ‘true’)

處理思路

這個例子是主要講解了如何使用，SVM分類器進行OCR字符訓練。

后記

大家有什么問題可以向我提問哈，我看到了第一時間回復，希望在學習的路上多多結交良師益友。