Merge pull request #1656 from Evezerest/develop

Keep the develop branch of PPOCRLabel in sync with the dygraph branch

PPOCRLabel/PPOCRLabel.py

@@ -106,7 +106,7 @@ class MainWindow(QMainWindow, WindowMixin):
         getStr = lambda strId: self.stringBundle.getString(strId)
 
         self.defaultSaveDir = defaultSaveDir
-        self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=True, lang=lang)
+        self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False, lang=lang)
 
         if os.path.exists('./data/paddle.png'):
             result = self.ocr.ocr('./data/paddle.png', cls=True, det=True)
@@ -257,9 +257,6 @@ class MainWindow(QMainWindow, WindowMixin):
         self.imgsliderDock.setObjectName(getStr('IR'))
         self.imgsliderDock.setWidget(self.imgsplider)
         self.imgsliderDock.setFeatures(QDockWidget.DockWidgetFloatable)
-        # op = QGraphicsOpacityEffect()
-        # op.setOpacity(0.2)
-        # self.imgsliderDock.setGraphicsEffect(op)
         self.imgsliderDock.setAttribute(Qt.WA_TranslucentBackground)
         self.addDockWidget(Qt.RightDockWidgetArea, self.imgsliderDock)
 
@@ -277,6 +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)
@@ -292,20 +290,16 @@ 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)
         iconListContainer.setFixedHeight(100)
-        # iconListContainer.setFixedWidth(530)
-        # op = QGraphicsOpacityEffect()
-        # op.setOpacity(0.5)
-        # iconListContainer.setGraphicsEffect(op)
         
         ########### Canvas ###########
         self.canvas = Canvas(parent=self)
@@ -366,14 +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'))
-
-        # verify = action(getStr('verifyImg'), self.verifyImg,
-        #                 'space', 'verify', getStr('verifyImgDetail'))
 
         save = action(getStr('save'), self.saveFile,
                       'Ctrl+V', 'verify', getStr('saveDetail'), enabled=False)
@@ -381,7 +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'))
@@ -398,7 +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)
@@ -456,8 +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)
@@ -501,9 +490,6 @@ class MainWindow(QMainWindow, WindowMixin):
                                 icon='color', tip=getStr('shapeFillColorDetail'),
                                 enabled=False)
 
-        # labels = self.dock.toggleViewAction()
-        # labels.setText(getStr('showHide'))
-        # labels.setShortcut('Ctrl+Shift+L')
 
         # Label list context menu.
         labelMenu = QMenu()
@@ -515,7 +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)
@@ -523,7 +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,
@@ -532,9 +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=(
@@ -576,7 +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)
 
@@ -586,16 +571,6 @@ class MainWindow(QMainWindow, WindowMixin):
             action('&Copy here', self.copyShape),
             action('&Move here', self.moveShape)))
 
-        # self.tools = self.toolbar('Tools')
-
-        # self.actions.beginner = (
-        #     open, opendir, openNextImg, openPrevImg, verify, save, None, create, copy, delete, None,
-        #     zoomIn, zoom, zoomOut, fitWindow, fitWidth)
-        #
-        # self.actions.advanced = (
-        #     open, opendir, openNextImg, openPrevImg, save, None,
-        #     createMode, editMode, None,
-        #     hideAll, showAll)
 
         self.statusBar().showMessage('%s started.' % __appname__)
         self.statusBar().show()
@@ -944,6 +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()
@@ -1013,6 +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())]
@@ -1466,6 +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)
 
 
@@ -1780,6 +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()
 
@@ -1819,6 +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()
@@ -1850,6 +1863,7 @@ class MainWindow(QMainWindow, WindowMixin):
         self.dialog.exec_()
         if self.filePath:
             self.AutoRecognition.setEnabled(True)
+            self.actions.AutoRec.setEnabled(True)
 
 
     def modelChoose(self):

PPOCRLabel/README.md

+[English](README.md) | 简体中文
+
 # PPOCRLabel
 
 PPOCRLabel是一款适用于OCR领域的半自动化图形标注工具，使用python3和pyqt5编写，支持矩形框标注和四点标注模式，导出格式可直接用于PPOCR检测和识别模型的训练。
 
 <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
@@ -43,7 +49,7 @@ python3 PPOCRLabel.py --lang ch
 1. 安装与运行：使用上述命令安装与运行程序。
 2. 打开文件夹：在菜单栏点击 “文件” - "打开目录" 选择待标记图片的文件夹<sup>[1]</sup>.
 3. 自动标注：点击 ”自动标注“，使用PPOCR超轻量模型对图片文件名前图片状态<sup>[2]</sup>为 “X” 的图片进行自动标注。
-4. 手动标注：点击 “矩形标注”（推荐直接在英文模式下点击键盘中的 “W”)，用户可对当前图片中模型未检出的部分进行手动绘制标记框。点击键盘P，则使用四点标注模式（或点击“编辑” - “四点标注”），用户依次点击4个点后，双击左键表示标注完成。
+4. 手动标注：点击 “矩形标注”（推荐直接在英文模式下点击键盘中的 “W”)，用户可对当前图片中模型未检出的部分进行手动绘制标记框。点击键盘Q，则使用四点标注模式（或点击“编辑” - “四点标注”），用户依次点击4个点后，双击左键表示标注完成。
 5. 标记框绘制完成后，用户点击 “确认”，检测框会先被预分配一个 “待识别” 标签。
 6. 重新识别：将图片中的所有检测画绘制/调整完成后，点击 “重新识别”，PPOCR模型会对当前图片中的**所有检测框**重新识别<sup>[3]</sup>。
 7. 内容更改：双击识别结果，对不准确的识别结果进行手动更改。
@@ -70,6 +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。
@@ -86,15 +112,23 @@ python3 PPOCRLabel.py --lang ch
 
 ### 错误提示
 - 如果同时使用whl包安装了paddleocr，其优先级大于通过paddleocr.py调用PaddleOCR类，whl包未更新时会导致程序异常。
+  
 - PPOCRLabel**不支持对中文文件名**的图片进行自动标注。
-- 对于Linux用户，如果您在打开软件过程中出现**objc[XXXXX]**开头的错误，证明您的opencv版本太高，建议安装4.2版本：
-	```
-	pip install opencv-python==4.2.0.32
-	```
-- 如果出现''Missing string id '开头的错误，需要重新编译资源：
-	```
-	pyrcc5 -o libs/resources.py resources.qrc
-	```
+
+- 针对Linux用户：：如果您在打开软件过程中出现**objc[XXXXX]**开头的错误，证明您的opencv版本太高，建议安装4.2版本：
+    ```
+    pip install opencv-python==4.2.0.32
+    ```
+    
+- 如果出现 ```Missing string id``` 开头的错误，需要重新编译资源：
+    ```
+    pyrcc5 -o libs/resources.py resources.qrc
+    ```
+    
+- 如果出现``` module 'cv2' has no attribute 'INTER_NEAREST'```错误，需要首先删除所有opencv相关包，然后重新安装headless版本的opencv
+    ```
+    pip install opencv-contrib-python-headless
+    ```
 ### 参考资料
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)

PPOCRLabel/README_en.md

+English | [简体中文](README_ch.md)
+
 # PPOCRLabel
 
 PPOCRLabel is a semi-automatic graphic annotation tool suitable for OCR field. It is written in python3 and pyqt5, supporting rectangular box annotation and four-point annotation modes. Annotations can be directly used for the training of PPOCR detection and recognition models.
 
 <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
@@ -54,7 +60,7 @@ python3 PPOCRLabel.py
 
    4.1 Click 'Create RectBox' or press 'W' in English keyboard mode to draw a new rectangle detection box. Click and release left mouse to select a region to annotate the text area.
 
-   4.2 Press 'P' to enter four-point labeling mode which enables you to create any four-point shape by clicking four points with the left mouse button in succession and DOUBLE CLICK the left mouse as the signal of labeling completion.
+   4.2 Press 'Q' to enter four-point labeling mode which enables you to create any four-point shape by clicking four points with the left mouse button in succession and DOUBLE CLICK the left mouse as the signal of labeling completion.
 
 5. After the marking frame is drawn, the user clicks "OK", and the detection frame will be pre-assigned a "TEMPORARY" label.
 
@@ -90,6 +96,25 @@ 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.
@@ -111,13 +136,18 @@ For some data that are difficult to recognize, the recognition results will not
 
 - For Linux users, if you get an error starting with **objc[XXXXX]** when opening the software, it proves that your opencv version is too high. It is recommended to install version 4.2:
 
-	```
-	pip install opencv-python==4.2.0.32
-	```
+    ```
+    pip install opencv-python==4.2.0.32
+    ```
 - If you get an error starting with **Missing string id **,you need to recompile resources:
     ```
-	pyrcc5 -o libs/resources.py resources.qrc
-	```
+    pyrcc5 -o libs/resources.py resources.qrc
+    ```
+- If you get an error ``` module 'cv2' has no attribute 'INTER_NEAREST'```, you need to delete all opencv related packages first, and then reinstall the headless version of opencv
+    ```
+    pip install opencv-contrib-python-headless
+    ```
+    
 ### Related
 
 1.[Tzutalin. LabelImg. Git code (2015)](https://github.com/tzutalin/labelImg)

PPOCRLabel/libs/autoDialog.py

@@ -46,9 +46,10 @@ class Worker(QThread):
                             chars = res[1][0]
                             cond = res[1][1]
                             posi = res[0]
-                            strs += "Transcription: " + chars + " Probability: " + str(cond) + " Location: " + json.dumps(posi)
+                            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)  # It is better to remove this line
+                        self.listValue.emit(strs)
                         self.mainThread.result_dic = self.result_dic
                         self.mainThread.filePath = Imgpath
                         # 保存

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
\ No newline at end of file
+singleRe=重识别此区块
\ No newline at end of file

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
\ No newline at end of file
+singleRe=Re-recognition RectBox
\ No newline at end of file