HYTOS

        app_doc_data = AppDocData.instance()

        project = app_doc_data.getCurrentProject()

        configs = app_doc_data.getConfigs('Text Size', 'Max Text Size')

        maxTextSize = int(configs[0].value) if 1 == len(configs) else 100

        minSize = 5

        ocr_image = np.ones(imgGray.shape, np.uint8) * 255

        binaryImg, mask = cv2.threshold(imgGray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)

        contours, hierarchy = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)

        for contour in contours:

            # remove too big one or horizontal/vertical line

            [x, y, w, h] = cv2.boundingRect(contour)

            area = cv2.contourArea(contour, True)

            # skip one which size is greater than max size or less then minimum size

            if area >= 0:

                if (w > maxTextSize or h > maxTextSize) or (w <= minSize and h <= minSize):

                    continue

            if area >= 0:

                cv2.drawContours(ocr_image, [contour], -1, (0, 0, 0), -1)

                cv2.drawContours(ocr_image, [contour], -1, (255, 255, 255), 1)

            else:

                cv2.drawContours(ocr_image, [contour], -1, (255, 255, 255), -1)

        path = os.path.join(project.getTempPath(), 'OCR_{}.png'.format(app_doc_data.imgName))

        cv2.imwrite(path, ocr_image)

        rects = []

        configs = app_doc_data.getConfigs('Text Recognition', 'Expand Size')

        expandSize = int(configs[0].value) if 1 == len(configs) else 10

        configs = app_doc_data.getConfigs('Text Recognition', 'Shrink Size')

        shrinkSize = int(configs[0].value) if 1 == len(configs) else 0

        eroded = cv2.erode(ocr_image, np.ones((expandSize, expandSize), np.uint8))

        eroded = cv2.bitwise_not(eroded)

        bboxes = []

        contours, hierarchy = cv2.findContours(eroded, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

        for contour in contours:

            area = cv2.contourArea(contour, True)

            if area < 0:

                [x, y, w, h] = cv2.boundingRect(contour)

                bboxes.append(QRect(x, y, w, h))

        # exclude bounding boxes contains child bounding box

        not_containing_bbox = []

        for bbox in bboxes:

            matches = [_bbox for _bbox in bboxes if bbox != _bbox and bbox.contains(_bbox)]

            if not matches:

                not_containing_bbox.append(bbox)

        # up to here

        for bbox in not_containing_bbox:

            x, y = bbox.left(), bbox.top()

            w, h = bbox.width(), bbox.height()

            img = ocr_image[bbox.top():bbox.bottom(), bbox.left():bbox.right()]

            img = cv2.bitwise_not(img)

            horizontal, max_width = 0, 0

            vertical, max_height = 0, 0

            _contours, _ = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

            for xx in _contours:

                [_x, _y, _w, _h] = cv2.boundingRect(xx)

                max_width = _x if _x > max_width else max_width

                max_height = _y if _y > max_height else max_height

                if (_w < _h) or (_w > maxTextSize > _h):  # width is greater than height

                    horizontal += 1 + (_w * _h) / (w * h)

                    vertical += 1 + (_w * _h) / (w * h)

            if (w < minSize and h < minSize) or (max_width > maxTextSize and max_height > maxTextSize):

                continue  # skip too small or big one

            rects.append([0 if horizontal > vertical else 90, QRect(x, y, w, h)])

        configs = app_doc_data.getConfigs('Text Recognition', 'Merge Size')

        mergeSize = int(configs[0].value) if 1 == len(configs) else 10

        # merge rectangles

        interestings = []

        while rects:

            rect = rects.pop()

            if 0 == rect[0]:    # x-direction text

                rectExpand = rect[1].adjusted(-mergeSize, 0, mergeSize, 0)

                matches = [x for x in rects if (x[0] == rect[0]) and

                           abs(x[1].height() - rect[1].height()) < (x[1].height() + rect[1].height())*0.5 and

                           abs(x[1].center().y() - rect[1].center().y()) < rect[1].height()*0.5 and

                           rectExpand.intersects(x[1])]

            else:               # y -direction text

                rectExpand = rect[1].adjusted(0, -mergeSize, 0, mergeSize)

                matches = [x for x in rects if (x[0] == rect[0]) and

                           abs(x[1].width() - rect[1].width()) < (x[1].width() + rect[1].width())*0.5 and

                           abs(x[1].center().x() - rect[1].center().x()) < rect[1].width()*0.5 and

                           rectExpand.intersects(x[1])]

            if matches:

                for _rect in matches:

                    rect[1] = rect[1].united(_rect[1])

                    if _rect in rects:

                        rects.remove(_rect)

                rects.append(rect)

            else:

                interestings.append(rect)

        list = []

        for rect in interestings:

            angle = rect[0]

            list.append(ti.TextInfo('', round(offsetX) + rect[1].x(), round(offsetY) + rect[1].y(), rect[1].width(),

                                    rect[1].height(), angle))

            text_info_array = np.array_split(tInfoList, THREAD_MAX_WORKER)

                """

                future = pool.submit(TextDetector.recognizeTextFromImage, tInfo, imgSrc, offset,

                                     searchedSymbolList, worker, listWidget, maxProgressValue)

                """

            """

    def removeTextFromImage(self, imgSrc, offset):

        appDocData = AppDocData.instance()

        project = appDocData.getCurrentProject()

        path = os.path.join(project.getTempPath(), 'OCR_{}.png'.format(appDocData.imgName))

        if os.path.isfile(path):

            imgOCR = cv2.imread(path)

            imgOCR = \

            cv2.threshold(cv2.cvtColor(imgOCR, cv2.COLOR_BGR2GRAY), 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]

            # remove recognized text from image

            for text in self.textInfoList:

                x = round(text.getX() - offset[0])

                y = round(text.getY() - offset[1])

                width = round(text.getW())

                height = round(text.getH())

                self.removeText(imgSrc, (round(text.getX()), round(text.getY())), imgOCR[y:y + height, x:x + width])

            # up to here

    '''

        @brief  remove text from image by using ocr image

        @author

    '''

    def removeText(self, img, pt, imgOCR):

        try:

            x = round(pt[0])

            y = round(pt[1])

            width, height = imgOCR.shape[::-1]

            temp = img[y:y + height, x:x + width]

            imgOCR = cv2.erode(imgOCR, np.ones((3, 3), np.uint8))

            mask = cv2.bitwise_or(temp, imgOCR)

            imgXOR = cv2.bitwise_xor(temp, mask)

            img[y:y + height, x:x + width] = cv2.bitwise_not(imgXOR)

        except Exception as ex:

            print('error occurred({}) in {}:{}'.format(ex, sys.exc_info()[-1].tb_frame.f_code.co_filename,

                                                       sys.exc_info()[-1].tb_lineno))

        return img