Merge pull request #1514 from Evezerest/dy3

Add single box re-recognition function and perfect shortcut keys
2020-12-19 11:33:28 +08:00 · 2020-12-19 11:33:28 +08:00 · 011104e09f
parent 7bd93832a1 fad11f89a8
commit 011104e09f
9 changed files with 4941 additions and 4916 deletions
--- a/PPOCRLabel/PPOCRLabel.py
+++ b/PPOCRLabel/PPOCRLabel.py
@ -274,6 +274,7 @@ class MainWindow(QMainWindow, WindowMixin):
        self.preButton.setIconSize(QSize(40, 100))
        self.preButton.clicked.connect(self.openPrevImg)
        self.preButton.setStyleSheet('border: none;')
+        self.preButton.setShortcut('a')
        self.iconlist = QListWidget()
        self.iconlist.setViewMode(QListView.IconMode)
        self.iconlist.setFlow(QListView.TopToBottom)
@ -289,12 +290,12 @@ class MainWindow(QMainWindow, WindowMixin):
        self.nextButton.setIconSize(QSize(40, 100))
        self.nextButton.setStyleSheet('border: none;')
        self.nextButton.clicked.connect(self.openNextImg)
+        self.nextButton.setShortcut('d')
        
        hlayout.addWidget(self.preButton)
        hlayout.addWidget(self.iconlist)
        hlayout.addWidget(self.nextButton)

-        # self.setLayout(hlayout)

        iconListContainer = QWidget()
        iconListContainer.setLayout(hlayout)
@ -359,11 +360,6 @@ class MainWindow(QMainWindow, WindowMixin):
        opendir = action(getStr('openDir'), self.openDirDialog,
                         'Ctrl+u', 'open', getStr('openDir'))

-        openNextImg = action(getStr('nextImg'), self.openNextImg,
-                             'd', 'next', getStr('nextImgDetail'))
-
-        openPrevImg = action(getStr('prevImg'), self.openPrevImg,
-                             'a', 'prev', getStr('prevImgDetail'))

        save = action(getStr('save'), self.saveFile,
                      'Ctrl+V', 'verify', getStr('saveDetail'), enabled=False)
@ -371,7 +367,7 @@ class MainWindow(QMainWindow, WindowMixin):
        alcm = action(getStr('choosemodel'), self.autolcm,
                                        'Ctrl+M', 'next', getStr('tipchoosemodel'))

-        deleteImg = action(getStr('deleteImg'), self.deleteImg, 'Ctrl+D', 'close', getStr('deleteImgDetail'),
+        deleteImg = action(getStr('deleteImg'), self.deleteImg, 'Ctrl+Shift+D', 'close', getStr('deleteImgDetail'),
                           enabled=True)

        resetAll = action(getStr('resetAll'), self.resetAll, None, 'resetall', getStr('resetAllDetail'))
@ -388,7 +384,7 @@ class MainWindow(QMainWindow, WindowMixin):
                        'w', 'new', getStr('crtBoxDetail'), enabled=False)

        delete = action(getStr('delBox'), self.deleteSelectedShape,
-                        'Delete', 'delete', getStr('delBoxDetail'), enabled=False)
+                        'backspace', 'delete', getStr('delBoxDetail'), enabled=False)
        copy = action(getStr('dupBox'), self.copySelectedShape,
                      'Ctrl+C', 'copy', getStr('dupBoxDetail'),
                      enabled=False)
@ -446,8 +442,11 @@ class MainWindow(QMainWindow, WindowMixin):
        reRec = action(getStr('reRecognition'), self.reRecognition, 
                      'Ctrl+Shift+R', 'reRec', getStr('reRecognition'), enabled=False)

+        singleRere = action(getStr('singleRe'), self.singleRerecognition,
+                            'Ctrl+R', 'reRec', getStr('singleRe'), enabled=False)
+
        createpoly = action(getStr('creatPolygon'), self.createPolygon,
-                            'p', 'new', 'Creat Polygon', enabled=True)
+                            'q', 'new', 'Creat Polygon', enabled=True)

        saveRec = action(getStr('saveRec'), self.saveRecResult,
                            '', 'save', getStr('saveRec'), enabled=False)
@ -491,6 +490,7 @@ class MainWindow(QMainWindow, WindowMixin):
                                icon='color', tip=getStr('shapeFillColorDetail'),
                                enabled=False)

+
        # Label list context menu.
        labelMenu = QMenu()
        addActions(labelMenu, (edit, delete))
@ -501,7 +501,6 @@ class MainWindow(QMainWindow, WindowMixin):

        # Draw squares/rectangles
        self.drawSquaresOption = QAction(getStr('drawSquares'), self)
-        self.drawSquaresOption.setShortcut('Ctrl+Shift+R')
        self.drawSquaresOption.setCheckable(True)
        self.drawSquaresOption.setChecked(settings.get(SETTING_DRAW_SQUARE, False))
        self.drawSquaresOption.triggered.connect(self.toogleDrawSquare)
@ -509,7 +508,7 @@ class MainWindow(QMainWindow, WindowMixin):
        # Store actions for further handling.
        self.actions = struct(save=save,  open=open,  resetAll=resetAll, deleteImg=deleteImg,
                              lineColor=color1, create=create, delete=delete, edit=edit, copy=copy,
-                              saveRec=saveRec,
+                              saveRec=saveRec, singleRere=singleRere,AutoRec=AutoRec,reRec=reRec,
                              createMode=createMode, editMode=editMode,
                              shapeLineColor=shapeLineColor, shapeFillColor=shapeFillColor,
                              zoom=zoom, zoomIn=zoomIn, zoomOut=zoomOut, zoomOrg=zoomOrg,
@ -518,9 +517,9 @@ class MainWindow(QMainWindow, WindowMixin):
                              fileMenuActions=(
                                  open, opendir, saveLabel,  resetAll, quit),
                              beginner=(), advanced=(),
-                              editMenu=(createpoly, edit, copy, delete,
+                              editMenu=(createpoly, edit, copy, delete,singleRere,
                                        None, color1, self.drawSquaresOption),
-                              beginnerContext=(create, edit, copy, delete),
+                              beginnerContext=(create, edit, copy, delete, singleRere),
                              advancedContext=(createMode, editMode, edit, copy,
                                               delete, shapeLineColor, shapeFillColor),
                              onLoadActive=(
@ -562,7 +561,7 @@ class MainWindow(QMainWindow, WindowMixin):
            zoomIn, zoomOut, zoomOrg, None,
            fitWindow, fitWidth))

-        addActions(self.menus.autolabel, (alcm, None, help)) #
+        addActions(self.menus.autolabel, (AutoRec, reRec, alcm, None, help)) #

        self.menus.file.aboutToShow.connect(self.updateFileMenu)

@ -572,6 +571,7 @@ class MainWindow(QMainWindow, WindowMixin):
            action('&Copy here', self.copyShape),
            action('&Move here', self.moveShape)))

+
        self.statusBar().showMessage('%s started.' % __appname__)
        self.statusBar().show()

@ -919,6 +919,7 @@ class MainWindow(QMainWindow, WindowMixin):
        self.actions.edit.setEnabled(selected)
        self.actions.shapeLineColor.setEnabled(selected)
        self.actions.shapeFillColor.setEnabled(selected)
+        self.actions.singleRere.setEnabled(selected)

    def addLabel(self, shape):
        shape.paintLabel = self.displayLabelOption.isChecked()
@ -988,6 +989,19 @@ class MainWindow(QMainWindow, WindowMixin):
        self.updateComboBox()
        self.canvas.loadShapes(s)

+    def singleLabel(self, shape):
+        if shape is None:
+            # print('rm empty label')
+            return
+        item = self.shapesToItems[shape]
+        item.setText(shape.label)
+        self.updateComboBox()
+
+        # ADD:
+        item = self.shapesToItemsbox[shape]
+        item.setText(str([(int(p.x()), int(p.y())) for p in shape.points]))
+        self.updateComboBox()
+
    def updateComboBox(self):
        # Get the unique labels and add them to the Combobox.
        itemsTextList = [str(self.labelList.item(i).text()) for i in range(self.labelList.count())]
@ -1441,6 +1455,8 @@ class MainWindow(QMainWindow, WindowMixin):
        self.haveAutoReced = False
        self.AutoRecognition.setEnabled(True)
        self.reRecogButton.setEnabled(True)
+        self.actions.AutoRec.setEnabled(True)
+        self.actions.reRec.setEnabled(True)
        self.actions.saveLabel.setEnabled(True)


@ -1755,6 +1771,7 @@ class MainWindow(QMainWindow, WindowMixin):
        self.loadFile(self.filePath) # ADD
        self.haveAutoReced = True
        self.AutoRecognition.setEnabled(False)
+        self.actions.AutoRec.setEnabled(False)
        self.setDirty()
        self.saveCacheLabel()

@ -1794,6 +1811,27 @@ class MainWindow(QMainWindow, WindowMixin):
        else:
            QMessageBox.information(self, "Information", "Draw a box!")

+    def singleRerecognition(self):
+        img = cv2.imread(self.filePath)
+        shape = self.canvas.selectedShape
+        box = [[int(p.x()), int(p.y())] for p in shape.points]
+        assert len(box) == 4
+        img_crop = get_rotate_crop_image(img, np.array(box, np.float32))
+        if img_crop is None:
+            msg = 'Can not recognise the detection box in ' + self.filePath + '. Please change manually'
+            QMessageBox.information(self, "Information", msg)
+            return
+        result = self.ocr.ocr(img_crop, cls=True, det=False)
+        if result[0][0] is not '':
+            result.insert(0, box)
+            print('result in reRec is ', result)
+            if result[1][0] == shape.label:
+                print('label no change')
+            else:
+                shape.label = result[1][0]
+            self.singleLabel(shape)
+            self.setDirty()
+        print(box)

    def autolcm(self):
        vbox = QVBoxLayout()
@ -1825,6 +1863,7 @@ class MainWindow(QMainWindow, WindowMixin):
        self.dialog.exec_()
        if self.filePath:
            self.AutoRecognition.setEnabled(True)
+            self.actions.AutoRec.setEnabled(True)


    def modelChoose(self):
--- a/PPOCRLabel/README.md
+++ b/PPOCRLabel/README.md
@ -6,6 +6,10 @@ PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field. I

 <img src="./data/gif/steps_en.gif" width="100%"/>

+### Recent Update
+
+- 2020.12.18: Support re-recognition of a single label box (by [ninetailskim](https://github.com/ninetailskim) ), perfect shortcut keys.
+
 ## Installation

 ### 1. Install PaddleOCR
@ -92,11 +96,30 @@ Therefore, if the recognition result has been manually changed before, it may ch

 ## Explanation

+### Shortcut keys
+
+| Shortcut keys    | Description                                      |
+| ---------------- | ------------------------------------------------ |
+| Ctrl + shift + A | Automatically label all unchecked images         |
+| Ctrl + shift + R | Re-recognize all the labels of the current image |
+| W                | Create a rect box                                |
+| Q                | Create a four-points box                         |
+| Ctrl + E         | Edit label of the selected box                   |
+| Ctrl + R         | Re-recognize the selected box                    |
+| Backspace        | Delete the selected box                          |
+| Ctrl + V         | Check image                                      |
+| Ctrl + Shift + d | Delete image                                     |
+| D                | Next image                                       |
+| A                | Previous image                                   |
+| Ctrl++           | Zoom in                                          |
+| Ctrl--           | Zoom out                                         |
+| ↑→↓←             | Move selected box                                |
+
 ### Built-in Model

 - Default model: PPOCRLabel uses the Chinese and English ultra-lightweight OCR model in PaddleOCR by default, supports Chinese, English and number recognition, and multiple language detection.

- Model language switching: Changing the built-in model language is supportable by clicking "PaddleOCR"-"Choose OCR Model" in the menu bar. Currently supported languagesinclude French, German, Korean, and Japanese.
+- Model language switching: Changing the built-in model language is supportable by clicking "PaddleOCR"-"Choose OCR Model" in the menu bar. Currently supported languagesinclude French, German, Korean, and Japanese. 
  For specific model download links, please refer to [PaddleOCR Model List](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/models_list_en.md#multilingual-recognition-modelupdating)

 - Custom model: The model trained by users can be replaced by modifying PPOCRLabel.py in [PaddleOCR class instantiation](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/PPOCRLabel/PPOCRLabel.py#L110) referring [Custom Model Code](https://github.com/PaddlePaddle/PaddleOCR/blob/develop/doc/doc_en/whl_en.md#use-custom-model)
--- a/PPOCRLabel/README_ch.md
+++ b/PPOCRLabel/README_ch.md
@ -6,6 +6,10 @@ PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，使用p

 <img src="./data/gif/steps.gif" width="100%"/>

+#### 近期更新
+
+- 2020.12.18: 支持对单个标记框进行重新识别（by [ninetailskim](https://github.com/ninetailskim) ），完善快捷键。
+
 ## 安装

 ### 1. 安装PaddleOCR
@ -72,6 +76,26 @@ python3 PPOCRLabel.py --lang ch
 |   crop_img    |   识别数据。按照检测框切割后的图片。与rec_gt.txt同时产生。   |

 ## 说明
+
+### 快捷键
+
+| 快捷键           | 说明                         |
+| ---------------- | ---------------------------- |
+| Ctrl + shift + A | 自动标注所有未确认过的图片   |
+| Ctrl + shift + R | 对当前图片的所有标记重新识别 |
+| W                | 新建矩形框                   |
+| Q                | 新建四点框                   |
+| Ctrl + E         | 编辑所选框标签               |
+| Ctrl + R         | 重新识别所选标记             |
+| Backspace        | 删除所选框                   |
+| Ctrl + V         | 确认本张图片标记             |
+| Ctrl + Shift + d | 删除本张图片                 |
+| D                | 下一张图片                   |
+| A                | 上一张图片                   |
+| Ctrl++           | 缩小                         |
+| Ctrl--           | 放大                         |
+| ↑→↓←             | 移动标记框                   |
+
 ### 内置模型

 - 默认模型：PPOCRLabel默认使用PaddleOCR中的中英文超轻量OCR模型，支持中英文与数字识别，多种语言检测。
--- a/PPOCRLabel/libs/autoDialog.py
+++ b/PPOCRLabel/libs/autoDialog.py
@ -46,8 +46,9 @@ class Worker(QThread):
                            chars = res[1][0]
                            cond = res[1][1]
                            posi = res[0]
-                            strs += "Transcription: " + chars + " Probability: " + str(
-                                cond) + " Location: " + json.dumps(posi) + '\n'
+                            strs += "Transcription: " + chars + " Probability: " + str(cond) + \
+                                    " Location: " + json.dumps(posi) +'\n'
+                        # Sending large amounts of data repeatedly through pyqtSignal may affect the program efficiency
                        self.listValue.emit(strs)
                        self.mainThread.result_dic = self.result_dic
                        self.mainThread.filePath = Imgpath
--- a/PPOCRLabel/libs/resources.py
+++ b/PPOCRLabel/libs/resources.py
--- a/PPOCRLabel/resources/strings/strings-zh-CN.properties
+++ b/PPOCRLabel/resources/strings/strings-zh-CN.properties
@ -94,4 +94,5 @@ ok=确认
 autolabeling=自动标注中
 hideBox=隐藏所有标注
 showBox=显示所有标注
-saveLabel=保存标记结果
+saveLabel=保存标记结果
+singleRe=重识别此区块
--- a/PPOCRLabel/resources/strings/strings-zh-TW.properties
+++ b/PPOCRLabel/resources/strings/strings-zh-TW.properties
@ -1,70 +0,0 @@
-saveAsDetail=將標籤保存到其他文件
-changeSaveDir=改變存放目錄
-openFile=開啟檔案
-shapeLineColorDetail=更改線條顏色
-resetAll=重置
-crtBox=創建區塊
-crtBoxDetail=畫一個區塊
-dupBoxDetail=複製區塊
-verifyImg=驗證圖像
-zoominDetail=放大
-verifyImgDetail=驗證圖像
-saveDetail=將標籤存到
-openFileDetail=打開圖像
-fitWidthDetail=調整到窗口寬度
-tutorial=YouTube教學
-editLabel=編輯標籤
-openAnnotationDetail=打開標籤文件
-quit=結束
-shapeFillColorDetail=更改填充顏色
-closeCurDetail=關閉目前檔案
-closeCur=關閉
-deleteImg=刪除圖像
-deleteImgDetail=刪除目前圖像
-fitWin=調整到跟窗口一樣大小
-delBox=刪除選取區塊
-boxLineColorDetail=選擇框線顏色
-originalsize=原始大小
-resetAllDetail=重設所有設定
-zoomoutDetail=畫面放大
-save=儲存
-saveAs=另存為
-fitWinDetail=縮放到窗口一樣
-openDir=開啟目錄
-copyPrevBounding=複製當前圖像中的上一個邊界框
-showHide=顯示/隱藏標籤
-changeSaveFormat=更改儲存格式
-shapeFillColor=填充顏色
-quitApp=離開本程式
-dupBox=複製區塊
-delBoxDetail=刪除區塊
-zoomin=放大畫面
-info=資訊
-openAnnotation=開啟標籤
-prevImgDetail=上一個圖像
-fitWidth=縮放到跟畫面一樣寬
-zoomout=縮小畫面
-changeSavedAnnotationDir=更改預設標籤存的目錄
-nextImgDetail=下一個圖像
-originalsizeDetail=放大到原始大小
-prevImg=上一個圖像
-tutorialDetail=顯示示範內容
-shapeLineColor=形狀線條顏色
-boxLineColor=日期分隔線顏色
-editLabelDetail=修改所選區塊的標籤
-nextImg=下一張圖片
-useDefaultLabel=使用預設標籤
-useDifficult=有難度的
-boxLabelText=區塊的標籤
-labels=標籤
-autoSaveMode=自動儲存模式
-singleClsMode=單一類別模式
-displayLabel=顯示類別
-fileList=檔案清單
-files=檔案
-iconList=XX
-icon=XX
-advancedMode=進階模式
-advancedModeDetail=切到進階模式
-showAllBoxDetail=顯示所有區塊
-hideAllBoxDetail=隱藏所有區塊
--- a/PPOCRLabel/resources/strings/strings.properties
+++ b/PPOCRLabel/resources/strings/strings.properties
@ -94,4 +94,5 @@ ok=OK
 autolabeling=Automatic Labeling
 hideBox=Hide All Box
 showBox=Show All Box
-saveLabel=Save Label
+saveLabel=Save Label
+singleRe=Re-recognition RectBox
--- a/StyleText/README.md
+++ b/StyleText/README.md
@ -78,6 +78,7 @@ python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_
 * Note 3: You can modify `use_gpu` in `configs/config.yml` to determine whether to use GPU for prediction.


+
 For example, enter the following image and corpus `PaddleOCR`.

 <div align="center">
@ -123,7 +124,7 @@ In actual application scenarios, it is often necessary to synthesize pictures in
     * `corpus_file`: Filepath of the corpus. Corpus file should be a text file which will be split by line-endings（'\n'）. Corpus generator samples one line each time.


-Example of corpus file:
+Example of corpus file: 
 ```
 PaddleOCR
 飞桨文字识别
@ -142,6 +143,7 @@ We provide a general dataset containing Chinese, English and Korean (50,000 imag
   ``` bash
   python3 tools/synth_dataset.py -c configs/dataset_config.yml
   ```
+
 We also provide example corpus and images in `examples` folder.
    <div align="center">
        <img src="examples/style_images/1.jpg" width="300">